Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Research Practice

Social Work Research SWK 321
by

Rhondda Waddell

on 29 September 2016

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Research Practice

Developing Research Questions
From Concepts to Observations
Measurement
Preparing To Sample
Sampling
Let's Start With A Story
Ethical and Scientific, Guidelines for Social Work Rearch
The Process of Social Work Research
Science, Society, and Social Work Research
Reasoning About The Social World
Chapter 1
Chapter 2
Chapter 4
The Practice of Research in Social Work by Engel & Schutt
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Descriptive Research
Generally uses Survey Research

Gathering of Facts
Who are the homeless?
What are their needs?
How many people are homeless?

Social Work Research in Practice

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Comparing Overgeneralization and Selective Observation

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Cultural context
Groups of individuals often develop alternative norms or definitions associated with particular events or topics.

Researchers need to keep in mind cultural context
Reluctance of diverse groups to participate in research
Cultural differences and validity
Data analysis

Social Work Research in a Diverse Society

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Causal Validity (Internal Validity)
Exists when a conclusion that A causes B is correct.
Establishing causal validity can be QUITE DIFFICULT.
What helps us establish causal validity?
For example, if we want to know if computer-mediated
counseling can be as effective as face-to-face counseling:
Experimental design
Statistics



Striving for Validity

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Measurement Validity
Exists when a measure measures what we think it measures.
We may think we are measuring depression, but we may be measuring
a normal reaction to a horrible situation.

Must also ensure that the measure is still accurate when we apply it to a certain subgroup of the population:
Older adults
Women
Gay men
Asian Americans

Striving for Validity

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Striving for Validity
When is knowledge VALID?
When our conclusions about empirical reality are correct.
Three aspects of validity that concern social work practitioners:
Measurement Validity
Generalizability
Causal (internal) Validity

Science, Society, and Social Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Quantitative
Methods that record variations in social life
Surveys
Experiments
Data that are treated as quantitative
Numbers or attributes that can be ordered in terms of magnitude (more to less, etc.)
Qualitative
Methods that are designed to capture social life as it is experienced
Participant observation
Intensive interviewing
Focus groups
Data that are treated as qualitative
Written or spoken word
Observations that do not have a numerical interpretation

Quantitative and Qualitative Research Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Difference in the research design and type of data

Quantitative = numerical data

Qualitative = personal narrative/original text

Quantitative and Qualitative Research Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Evaluation Research
Also known as practice evaluation or program evaluation
Goes beyond understanding if a program is effective

Involves searching for practical knowledge
Implementation of social policies
Effects of social policies
Impact of social service programs

Intention to generate generalizable knowledge

Social Work Research in Practice

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Exploratory Research
Commonly uses Qualitative Research Methods

Seek to understand how individuals live under particular situations:
How do people get along in this environment?
What meaning do they give to their actions?
What concerns them?

Social Work Research in Practice

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Purposes of Social Work Research include:
Description
Generating facts

Exploration
How people live under specific circumstances

Explanation
Cause and effect

Evaluation
Programmatic theory and impact

Science, Society, and Social Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Barriers to EBP
Inadequate resources or funding to access research evidence
Staff lack skills and knowledge
Agency culture
Professional’s attitudes towards research
Inadequate supervision

Examples of these barriers from experience?

Evidence-Based Practice

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Social Science Research
Relies on systematic investigations

Evidence-Based Practice
EBP suggests that social workers should integrate the best current research
evidence (knowledge derived from research) to achieve a particular outcome.
Client values
Client circumstances
Clinical experiences

Science, Society, and Social Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Social Science Approach
Systematic method of research that reduces errors in reasoning

How does social science reduce the likelihood of the following errors?
Overgeneralization?
Selective observation?
Illogical reasoning?
Adherence to authority?



Science, Society, and Social Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Adherence to Authority:

We believe that the person who makes the claim knows best.
From whom did YOU learn about what causes homelessness?

To avoid adherence to authority, one must critically evaluate the
ideas of those in positions of authority.

Everyday Errors in Reasoning

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Resistance to Change:

The reluctance to change our ideas in light of new information
Ego-based commitments
Ideas meet our own needs
Too tough to admit we were wrong
Excessive devotion to tradition
We have always believed this, so it must be right

Everyday Errors in Reasoning

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Illogical Reasoning:

Premature jump to conclusions
Arguing on the basis of invalid assumptions
Example: People who are homeless DO NOT want to work.
WHY is the statement above NOT LOGICAL?

Everyday Errors in Reasoning

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Selective or Inaccurate Observation:

Choosing to look at things that are in line with our preferences or beliefs:
We believe that people who are homeless struggle with addiction, and when we read about people
who are homeless, we only PAY ATTENTION to those who are also addicted and IGNORE stories about those who become homeless for other reasons, such as:
Intimate partner violence
Job loss
Illness
Natural disaster

Everyday Errors in Reasoning

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Overgeneralization:

Occurs when we conclude that what we have observed or what we know to be true for SOME cases is true for ALL cases.
For example, Burt is an alcoholic, therefore ALL homeless people struggle with addiction.

Everyday Errors in Reasoning

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Everyday Errors in Reasoning:
There are several explanations as to why errors in logic occur frequently.
Understanding these everyday errors will help you to avoid
them as a social work researcher.
These errors include:

Overgeneralization
Selective Observation
Illogical Reasoning
Resistance to Change
Adherence to Authority

Science, Society, and Social Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Science, Society, and Social Research

CHAPTER ONE

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Generalizability
The extent to which the information gleaned can be used to inform
us about people, places, or events not studied.
Two aspects
Sample Generalizability
Exists when a conclusion based on a sample (subset) of the larger population holds true for that population.
External Validity (Cross Population Generalizability)
Exists when findings about one group, population, or setting holds true for other groups, populations, or settings.




Striving for Validity

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Explanatory Research
Commonly uses Experimental Research Methods

Seeks to identify causes and effects
Poverty -> homelessness?

Depends on our ability to
Rule out alternative explanations
Demonstrate a time order between two events
Show that the two events are related

Social Work Research in Practice

Learning Objectives:
1. Learn why research is import
2. Discuss Research Practice
3. Paradigms
Explore Validity

Agenda
Introductions
Review Class Expectations
Review The Syllabus
Discuss Chapter 1
Class Activity: Assign Groups & Chapters
SLU Cor Value: Community & Respect
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

The Process and Problems of Social Work Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Social Work Research Questions

A social work research question is a question you seek to answer
through the collection and analysis of data that is:

Firsthand

Verifiable

Empirical

The Process and Problems of Social Work Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

The Process and Problems of Social Work Research

CHAPTER 2

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

The Process and Problems of Social Work Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Critical Theory-A research focus on examining structures, patterns of behavior, and meanings but rests on the premise that power differences, often manifested by discrimination and oppression, have shaped these structures and patterns.

Feminist Research- Research with a focus on women's lives and often including an orientation to personal experience, subjective orientations, and the researcher's standpoint. Interpretivist and constructivists views social world as complex and interrelated
Sensitive to the impact of social differences (identity)

Participatory Action Research- A type of research in which the researcher involves some community and/or organizational members as active participants throughout the study.
Reduces the distinction between researcher and subjects, adds a collaborative process of creating knowledge as the research empowers and works with participants

Alternative Research Philosophies

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Research Paradigms
Positivist-The belief that there is a reality that exists quite apart from our own perception of it, that it can be understood through observation and that it follows general laws. Quantitative researchers are often guided by a positivist philosophy. Objective reality exists apart from the perceptions of those who observe it.

Post-positivist-is a philosophy of reality that is cclosely related to positivism because it assumes that there is external, objective reality, but it acknowledges the complexity of this reality and the limitations of the researchers who study it. Ex. The researchers may be biased toward the subject they are studying...Thus wee can never be sure that the scientific methods allow us to perceive object reality. Researchers can never be certain that biases do not influence results.
Goal is intersubjective agreement-Community of researchers develop a more unbiased account of reality.

Interpretivist-The belief that reality is socially constructed and that the goal of social scientists is to understand what meanings people give to that reality.
Reality is socially constructed.

Constructivist- A perspective that emphasizes how different stakeholders in social settings construct their beliefs. Extension of interpretivism that emphasizes how different stakeholders in social settings construct their beliefs.



The Process and Problems of Social Work Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Descriptive Research:

Does not involve connecting theory and data.

Begins with data and only proceeds to making empirical
generalizations based on those data.

Much research for governments and organizations is primarily descriptive.

The Process and Problems of Social Work Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Inductive Research
Begins with data that are then used to develop (induce) a information to explain the data.

Can be intentional, as in exploratory research.

Can be used when analyzing empirical generalizations discovered while tentative hypothesis testing.

The Process and Problems of Social Work Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Deductive Research: Starts With Theory:
Hypothesis-A tentative statement about an empiracal reality involving a relationship between two or more variables.

Variables-Characteristics or properties that can take on different values or attributes.

Independent-A variable that is hypothesized to cause, or lead to, variation in another variable.

Dependent- A variable that is hypothesized to vary depending on or under the influence of another variable.

The Process and Problems of Social Work Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Theory and Social Work Research

Theory is a logically interrelated set of propositions about empirical reality.

Theories help us:
Understand how social problems emerge
Guide in the design of interventions
Explain relationships
Design social policy





The Process and Problems of Social Work Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Examining Research Literature
Two-stage process
Assess each article separately
Assess the implications of articles in totality

Literature for Evidence-Based Practice
Systematic Reviews (meta-analysis)
Campbell Collaboration pg. 31
Government Supported Resources




The Process and Problems of Social Work Research

Learning Objectives:
1. Learn How to Develop A Research Question
2. Explore the Research Literature
3. Discuss Research Philosophies
Agenda
Roll Call
Reflection
Chapter 2 Review
Prezi Time
Class Activity
SLU Core Values: Community & Respect
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Ethical Guidelines for Research

CHAPTER 3

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

The Internet allows for new ways of doing research
Likewise new ethical issues arise, such as:
Distinction between public and private space
Maintaining confidentiality
Emotional harm
Process of informed consent

Internet Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Involvement of the following research subjects will likely result in a full committee review:
Prisoners
Children under 18
Pregnant women
Individuals with an inability to provide consent

Full Board Involves:
Extensive review and questioning of the research methods and purpose
Research proposal is voted on by the full committee

IRB: Full Committee Review

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Involves minimal risk of harm to human subjects

This includes:
Research involving data that will be collected solely for non-research purposes (i.e., medical treatment) Voice, video, digital, or image data collected for research purposes
Research on individual or group behavior
Survey, interview, oral history, focus group, program evaluation, quality assurance, etc.

IRB: Expedited Review

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Involves minimal human subject interaction
Does not involve individuals <18 or prisoners

This includes:
Research in an established educational setting
Research that uses educational tests, surveys, interviews, or observation of public behavior
Research that uses existing data so long as human subjects cannot be identified

IRB: Exempt Status

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

IRB criteria differs for the level of potential risk/harm to human subjects

Three categories of the review process:
Exempt
Expedited
Full Committee

Institutional Review Boards

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Federal regulations require that institutions that seek federal funding for research on human beings have an institutional review board

Boards are uniquely composed given the institution but are required to have members of diverse backgrounds

IRBs are monitored by the Office for Human Research Protections at NIH

Institutional Review Boards

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Difficult to separate research and advocacy
Social work researchers working for organizations will likely encounter this issue
Know your contractual obligations ahead of time
Negotiate the reporting process in advance

Appropriate Application

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Validity is necessary to finding objective knowledge

Need accurate measurements and a design appropriate for the task

Ensuring participants are treated equally


Achieving Valid Results

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Researchers’ obligation to the scientific community

Must present and make available an honest and detailed account of methodology and results

Honesty and Openness

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Avoiding harm
Obtaining voluntary and informed consent
Consent must be written and in plain language
State clearly who is doing the research
Describe the study and how records are kept
Consent can be withdrawn at any time
Maintaining privacy and confidentiality
State and federal laws may complicate, such as reporting child abuse
Must make the scope of confidentiality realistic

Protecting Research Subjects

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Protect research subjects
Maintain honesty and openness
Achieve valid results
Encourage appropriate application of findings

Milgram experiment teaches us why these ethical principles are necessary

Ethical Principles

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Test ideas empirically, avoid becoming too personally involved
Work systematically
Document all procedures and make them available to the public
Acknowledge and clarify any assumptions
Specify the meaning of all terms
Maintain skepticism towards current knowledge
Replicate existing research to build social theory
Search for patterns, also acknowledge irregularities

8 Guidelines for social work research

Chapter 3
Agenda
Roll Call
Chapter 3 Review
Prezi Time
Class Activity
SLU Core Values: Community & Respect
Learning Objectives:
1. Review Research Historical Background of Ethics
2. Explore the IRB Purpose
3. NASW Code of Ethics
Agenda
Roll Call
Chapter 4 Measurement
Prezi Time
Class Activity
SLU Core Values: Community & Respect
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Nominal , Ordinal






Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Concepts
Mental images that summarize a set of similar:
Observations
Feelings
Ideas



Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Conceptualization and Measurement

CHAPTER 4

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.


Practical considerations when selecting scales
Administration of scale
Cost
Sensitivity to change
Reactivity
Acceptability


Conceptualization & Measurement

Four approaches to assess measurement validity

Face validity (subjective)
Obviously pertains to what it is measuring

Content validity (subjective)
Measure covers the full range of the concept’s meaning

Criterion validity
Scores on one measure are similar to scores obtained on a
more direct or validated measure
Concurrent
Predictive

Construct validity
Measure is related to a variety of others as specified in a theory

Convergent Validity
Known Groups Validity

Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Assessing Measurement Accuracy
Reliability
Measurement yields consistent results
Is a PREREQUISITE for validity

How do we assess reliability?


Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Measurement Error
Systematic
Social Desirability
Acquiescence Bias
Leading Questions
Random
Regression to the mean


Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Dichotomies: variables having only two values (attributes)
Example: Depressed or not depressed
Can be treated as ordinal variables (presence of/absence of)

Mathematical Comparisons
All four levels allow assignment of different values to different cases

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Interval
Numbers represent fixed measurement units but have no absolute zero point
There are few true interval level measures in social work
Addition and subtraction are possible

Ratio
Numbers represent fixed measurement units where zero means (an absolute zero point)

Multiplication and division are possible, so ratios are meaningful
Highest level of mathematical precision

Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Nominal
Qualitative, with no mathematical interpretation
Exhaustive: Every case can be classified
Mutually Exclusive: Every case can have only one attribute

Ordinal
Specifies only the order of cases
Greater than/less than operations
Indicates relative position of cases
Example: Client satisfaction

Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Combining Measurement Operations:
Triangulations: Use of two or more different measures of the same variable
Why use triangulation?

Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Treatment as a Variable
Description of an intervention and how it was implemented – used
to operationalize a specific “treatment” or “intervention”

Why would a nominal definition be inadequate?
How is an operational definition better?

Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Scales and Indexes
When several questions are used to measure one concept, the responses may be combined by taking the sum or average of the responses.

Composite measure based on this sum or average is termed a SCALE or INDEX.

Do I need to create a scale?
Not necessarily….scales have already been developed to measure many concepts and deemed reliable in a range of studies.



Conceptualization & Measurement


Operationalization
Operational definition:

What is measured?
How are indicators measured?
What are the rules used to assign values to what is observed?

Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Operationalization
The
process
of specifying operations that will indicate the effect of the researchers action on a variable

Operation: A
procedure
for identifying or indicating the researchers action on a variable

Measurement can be based on diverse methods of data collection
Variables and operations should be consistent with the research question

Time and resource limitations must be taken into account when selecting variables and devising operations






Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Variables and Constants:

Variable:
Concept that varies, from which we select concrete indicators

Constant:
A concept that does not vary

Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Deciding which concepts to consider and which variables to measure requires the researcher to:
Examine relevant theories
Review previous research
Consider:
Constraints
Opportunities
Understand the definition of any one concept rests on shared
understandings of other terms used in the definition




Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Conceptualization
Process of specifying what is meant by a term.

In deductive research
Helps to translate portions of abstract theory into testable
hypotheses involving specific variables

Inductive research Is an important part of the process used to make sense of related observations


Conceptualization & Measurement

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Screening and Cut-Off Scores
Validity of cut-off score must be assessed
true negative (specificity)
true positive (sensitivity)
false negative
false positive

Conceptualization & Measurement

Learning Objectives:
1. Learn About types of Concepts in Research
2. Explore how to operationalize research
3. Explore Levels of Measurement

Agenda
Roll Call
Chapter 5 Review
Prezi Time
Class Activity
SLU Core Values: Community & Respect
Learning Objectives:
1. Learn how to Sample
2.Explore Sampling Methods
3. Discuss Sampling Distribution
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Nonprobability Sampling

Four methods commonly used

Availability
Quota
Purposive
Snowball


Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Probability v. non-probability






Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Sampling

CHAPTER 5

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Recruitment Strategies with Diverse Populations

Involve key members of the community and organizations

Demonstrate benefit to the community

Understand cultural barriers

Train interviewers

Go where potential participants are

Sampling

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Unit of Analysis and United of Observation

Units of analysis (the level of social life for which a research question is focused) vs. Units of observation (The cases about which measures actually are obtained in a sample)

Fallacy- Fallacy is committed when a person draws a conclusion about a population based on a sample that is biased or prejudiced in some manner.

Ecological fallacy-An error in reasoning in which the incorrect conclusions about individual-level processes are drawn from group-level data.

Reductionist fallacy-An error in reasoning that occurs when an incorrect conclusion about group-level processes is based on individul-level data.


Sampling

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

The Sampling Distribution

Inferential statistics
Mathematical tool for assessing the likelihood that a statistical result
based on data from a random sample is representative of the population from which the sample is assumed to have been selected

Normal if produced by random sampling error, centered on the population parameter

In a normal distribution, a predictable proportion of cases falls within certain ranges from the population parameter, known as confidence intervals

Sample distributions are more compact when based on larger samples

Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Snowball Sampling

Identify one member of a population and speak to him/her and then ask that person to identify others in the population and speak to them, then ask them to identify others and so on
Useful for hard-to-reach and hard-to-identify populations


Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Purposive Sampling

Each element is selected for a purpose, usually because of unique position of the sample elements

Selecting informants Knowledge of area/arena/situation under study
Willingness to talk
Representativeness of range of points of view

Continue to select interviewees until you achieve:
Completeness
Saturation

Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Quota Sampling

Quota:
A pre-set number of elements based on characteristics in a population to ensure that the sample represents those characteristics in proportion to their prevalence in the population

Sample may be representative on characteristics specified by the quota, but it is probably not representative in any other way

Relevant characteristics must be known of entire population in order to set quotas

If you can’t draw a random sample, it may be better to draw a quota sample than to use no quotas

Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Availability

Selection of elements is done by what is available and/or convenient to researcher

Useful when in a new setting and in exploratory studies

Not rigorous or representative

Much popular research is based on convenience sampling

Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Non-probability Sampling Methods

Sampling methods that do not let us know in advance the likelihood of selecting each element

Often used in qualitative research
Used in quantitative studies when probability selection is not possible
Does not yield representative samples; lowers ability to generalize findings

Useful in preliminary, exploratory studies

Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Cluster Sampling
Useful when sampling frame is not available

Cluster
A naturally occurring, mixed aggregate of elements in a population,
with each element occurring in one and only one cluster

Procedure
Stage 1: Draw a random sample of clusters
Stage 2: Elements within randomly selected clusters are randomly selected

Multistage clustering
First stage are primary sampling units
Second stage are secondary sampling units, etc.



Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Stratified Random Sampling

Proportionate stratified sampling Each sampling stratum represents exactly its proportion in the population

Disproportionate stratified sampling The proportion of sampling strata are intentionally varied from what it is in the population

Probability of selection is known but differs by strata

Used to ensure that cases from smaller strata are included in sufficient number to use statistics and make comparisons

Facilitates comparisons between strata

Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Stratified Random Sampling

All elements in the sampling frame are distinguished
according to their value on some relevant characteristic(s)

That characteristic forms the sampling strata

The size of each stratum in the population must be known

Elements are randomly selected from within the strata

Each element may belong to one and only one strata

Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Systematic Random Sampling

First element is selected randomly, and then every nth element is selected
Convenient when populations are arranged sequentially

Periodicity
An error that results when a sequence varies in some periodic manner,
such that systematic random sampling doesn’t work because it selects a specific type of element

Sampling interval
The number of cases from one sampled case to another

Steps
Population is divided by number of cases required by sample, yielding the sampling interval

A number less than or equal to the sampling interval is selected randomly to identify the first case to be sampled Every nth case is selected, where n is the sampling interval




Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Simple Random Sampling
Identifies cases strictly on the basis of chance

Methods of simple random selection
Random number table
Lottery procedure
Computer generated
Random-digit dialing

Probability of selection is the same for all elements:
sample/population (Equal Probability Selection Method)

Replacement sample
Each element is returned to the sampling frame after it is selected so that it may be sampled again.


Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Probability Sampling: General Characteristics
Probability of selection is known

Probability of selection is not zero

No systematic bias: Nothing but chance determines which elements are included in the sample

More generalizable

All samples will have some sampling error

As sample size and homogeneity increase, error decreases

The proportion of the population that the sample represents does NOT affect sample representativeness

Larger sample size, more confidence in representativeness


Sampling Methods

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Homogeneity

Sampling is unnecessary if the elements in
a population are identical Representative sample:

“Looks like” the population from which it was selected in all respects

Sampling

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Evaluating Generalizability

Sample Generalizability
Is sample generalizable to population?

Sampling Error
Any difference between the characteristics of a sample and
the characteristics of a population from which it was drawn

The larger the sampling error, the less representative the sample





Sampling

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Sampling Frame:
A list of all elements or other units containing the elements in a population

Enumeration Units:
Units that contain one or more elements and that are listed
in a sampling frame

Sampling Units:
Units listed at each stage of a multistage sampling design

Primary
Secondary
Etc.



Sampling

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Preparing to Sample
Population: The entire set of individuals or other entities to\ which study findings are to be generalized

Elements: The individual members of the population whose characteristics are measured

Sample: A subset of the population that is used to study the whole

Sampling

Group Experimental Designs
Learning Objectives:
1. Learn About Threats to Validity
2. Explore reasons for experiments
3. Discuss Implications for EBP
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

True Experiments

Used when a social work researcher wants to show that an intervention (IV) is cause for a change in an outcome (DV)

Group Experimental Designs

Threats to Internal Validity Threats:

Noncomparable groups: Happens when the experimental group and comparison group are not comparable. Selection bias (problems with assigning groups ex. highly motivated/unmotivated) & Mortality (groups become different over time often due to drop out).

Endogenous change- Occur when natural developments in subjects, independent of the experimental treatment account for some or all of the observed changes. (respondents learn from the pretest, maturation, statistical regression respondents improve or get worseto reflect a bad day.

External events- Events occur outside the context of the experiment but affect the participants. (History
of an event affects the subjects, society changes secular drift, measures lack reliability.

Contamination- When the comparison or control group is affected by the treatment group. (Comparison group learns if differences, demoralization of comparison group, other group learns of treatment differences)

Treatment misidentification- The subjects experience something other than what the researchers believe they have experienced. (Cpmpensatory equalization of treatment, staff treat is not equalial, placebo effect)

Group Experimental Designs

Five criteria in deciding causality. A causal effect means that the variation in an independent variable will be followed by variation in the dependent variable, when all things are equal.:

Association- An observed variation sometimes called a correlation between the independent variable and dependent variable is identified.

Time order- Researcher must ensure the change in the independent variable (IV) occurred before the change in the dependent variable (DV).

Nonspuriousness- Must make sure the relationship between the IV and DV is not due to any other variable.

Casual Mechanism - This is the process that creates the connection between variation in the IV and variation in the DV.

Context - Research makes sure no cause has its effect apart from some larger contect involving other variables.

Group Experimental Designs

Group Experimental Designs

CHAPTER 6

Diversity, Group Design, and Evidence-based Practice

Representation- Important to select sample members that are diverse in representation as this is important for external validity.

Subgroup representation- You should do an analysis for specific groups such as women and specific ethnic groups to look at different treatment effects and report those that are often left out.

Group Experimental Designs

Implications for Evidence-based Practice

Randomization: You need to be careful to clarify how the actual assignments to groups were made, this important for internal validity.

Sample size- To be considered for figuring statistical power, the study needs a sample size large enough to detect statistical significance (smaller samples provide a greater chance of finding no effect).

Attrition- Some participants will drop out of the study, you must consider how to handle drop outs in the analysis.

Group Experimental Designs

Non-experimental designs:
Provide less evidence for causality
Three types
One group pretest-posttest designs:

Absence of a comparison group

Able to establish time order because there is a pretest/posttest

Weakness is spuriousness a problem with many thrests to internal validity lacks a compariosn group typically

One group Pretest-Postest designprovides answers to questions of interst to agency staff and funders dmenonstartes improvement occurred, how much change, how many individuals improved.




Group Experimental Designs

Quasi-Experimental Designs
Nonequivalent control group designs


Quasi-Experimental Design is one which may be able to rule out at least some alternative explanations to threats to internal validity.

Nonequivalent control group design (NCGD) Identical to pretest-posttest design EXCEPT for no random assignment into groups

Researchers select a comparison group as similar as possible

Matches can be found on waiting list at an agency

A statistical association can be demonstrated


Group Experimental Designs

Difficulties of True Experiment in Agency-based Research:

Program cannot change

Implementation depends on staff with different skills, etc.

Staff may complain about threats to professional judgment

Staff may want all clients to receive experimental treatment


Group Experimental Designs

2) True Experiments

Posttest only control group
Safeguards against reactive effects of testing and treatment

Assumes pretest measures are equal due to random assignment

3) Solomon four-group design
Can determine if there is a testing effect by combining features of the preceding designs
Of the four groups, two have pre- and posttests and two have post-tests only


Group Experimental Designs

1) True Experiments

Pretest-Posttest
Establish association
Internal validity due to random assignment

Weakness: Pretest measurement may affect posttest scores

Group Experimental Designs



3 Types of true experiments:

Pretest-Posttest: Classical Experimental design ramdomized test before/after control group design.

Posttest only control group: Randomized test of control group after-only design

Solomon four-group design- Four groups two with a pretest-post test and two with a posttest only randomized design.
(indicates a difference in outcome scores for the two experiemental groups and the two comparison groups).

Group Experimental Designs

True experiments:

Random assignment (to ensure internal validity)

Matching (match with gender, age, race, for example)

Block matching used when participants are grouped by their characteristics
Within each group, members are randomly assigned to treatment or control group

Aggregate matching is matching by group. (ex: older residents in a high rise might be grouped by floor)


Group Experimental Designs

True experiments have at least three features:

Two comparison groups - Simplest case is an experimental and control group.

Random assignment- to the two or more comparison groups to establish nonspuriousness (false or not genuine cause) for internal validity.

Variation in IV before assessment of change in the DV to establish time order.

Group Experimental Designs

Generalizability- being able to apply the findings to some clearly defined larger population and cross-population (subgroup)

Sample generalizability- Participants who can be recruited for a laboratory experiment randomly assigned and kept under controlled conditions for the study's duration.

External validity- The applicability of a treatment effect (or non effect) across subgroups within an experiment or across different populations or settings.

Reactivity- This occurs when the experiment treatment has an effect only when the particular conditions created by the experiment occur.

a) Interaction of testing and treatment-Problem happens when the treatment has an effect only if subjects have had a pretest (pre-test sensitizes the subjects to some issue).

b) Reactive effects of experimental arrangements- Hawthorne Effect

c) Interaction of selection and treatment- Problems relate to selection bias as in who receives treatment and who serves in the comparison group.


d) Multiple treatment interference- Happens when subjects have been exposed to other interventions prior to the experiment.


Group Experimental Designs Related Terms

Single-Subject Design
Measuring Targets of Intervention
Agenda
Roll Call
Chapter 8 Review
Prezi Time
Class Activity
SLU Core Values: Community & Respect
Learning Objectives:
1. Learn how to Analyze & Interpret Results
2. Discuss types of Single-subject Designs
3. Explore Related Ethical Issues
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Ethical Issues in Single-Subject Design
Informed consent
Must understand that onset of treatment is delayed until baseline established

Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Single-subject designs can be used to
Systematically test the effectiveness of a particular intervention
Monitor client progress

Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Single-Subject Design

CHAPTER 7

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Single-Subject Design in a Diverse Society
Measures must be acceptable and applicable (reliable and valid)
to diverse populations
Single-subject designs may be useful in engaging diverse groups who have been historically underrepresented in research

Single-Subject Design

Implications for Evidence-Based Practice

Strength: Focus on individuals

Weakness: Lack of generalizability

Generalizability from single subject designs requires direct replication, systematic replication, and clinical replication.

Enhance external validity by three sequential replication strategies as suggested by Barlow and Hersen:
Direct replication: Repestting the procedures, by the same researcher in the same setting & situation with different clients with same characteristics.
Systematic replication-Repeating the experiment in different settings by different providers and with other behaviors with increased numbers and types of clients.
Clinical replication -Combining different interventions into a clinical package to treat multiple problems. The replication takes place in the same setting with clients who have the same types of problems.



Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Problems with Interpreting Visual Patterns can include:

Widely discrepant scores in the baseline

Variability in how to interpret changes

Improvement happens in baseline phase (with no intervention)

Art of graphing can create visual distortions


Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Visual Analysis - Interocular

The process of looking at data to determine effectiveness of the intervention
Three concepts help guide visual inspection:

Level: Amount or magnitude or target variable

Trend: Direction or pattern of data points
Increasing
Decreasing

Cyclical
Curvilinear

Stabilty: when three or more consecutive data points are void of trend.

Variability: How different the scores are

Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Managing Reactivity

Reactivity: Process of gathering data may change a subject’s behavior
Example: Having client journal what she eats for a week may make her
more conscious about what she is eating and may be short in duration and repeated measurements of baseline might remedy the problem

Reactivity might be useful in clinical setting:
Woman journaling about food consumption may be more conscious about what she is eating and this is consistent with the therapy goal

Single-Subject Design

Graphing
Facilitates monitoring and evaluating the impact of intervention involving inspecting graphs of measurements.
The researcher may look for changes in level (magnitude), rate of directional changes in the trend line, or reductions in variability. Or if treatment has made a clinical difference.
X-axis: Units of time
Hours
Days
Weeks

Y-axis: Scores the dependent variable


Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Treatment Phase (B) follows Baseline A

This is the time period during which the intervention is implemented
Repeated measurement of the same dependent variable using same
measurement are obtained

Length of treatment should be as long as baseline phase

How to do a Single-Subject Design?

Internal Validity: Focused on when repeated measures are taken during the baseline phase, several threats to internal validity are controlled.

(Internal validity asks is the intervention and only the intervention responsible for the change in behavior)

Specifically, the following problems:
Maturation: Changes in outcome due to aging out, gained experience
Instrumentation: Types of testing measurements must be the same
Statistical Regression: People experience cyclical changes
Testing:Taking a pretest may influence posttest


See Exhibit 6.2 page 122 lists and definitions

Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Baseline Phase : Period in which the intervention is not offered (A)

Two measures of control
Establish pattern prior to intervention
Allows social work researcher to discount threats to internal validity

Baseline information is taken until a pattern emerges to include:

Stable line: A line that is flat with little variability in the scores so that the scores fall into a narrow band. This is preferable because changes can be easily detected

Trend
Increasing or decreasing during baseline period and dependent on time of measurement
Linear (constant rate)
Curvilinear (rate of change is accelerating over time)

Cycle
Pattern reflecting ups and downs depending on time of measurement

Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Repeated Measurement

Initial measures can be obtained during the assessment phase\ and continue during intervention

Repeated measures can also begin when the client begins intervention for other problems

Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Underlying principle is to see if an Intervention is effective ?

As a social work research tool, this type of design has three components:

Repeated measurement: Measures used to identify a client's status:


Baseline phase (A): The time period prior to the start of the intervention


Treatment phase (B): The time period during the intervention

Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Types of Single-Subject Designs
Basic Design (A-B)
Withdrawal Design

(A-B-A): Is there a carryover effect?

(A-B-A-B): Builds in a second intervention (B)

Multiple Baseline Designs: Implement one of the aforementioned
on at least three cases (case 2 and 3 act as controls)

Across subjects
Across target problems
Across settings

Multiple Treatment Designs
A-B-C-D
May also be used when combining two treatments


Single-Subject Design

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Measuring Targets of Intervention

Measures of behavior, status, or functioning are characterized four ways:

Frequency: Number of times a behavior occurs

Duration: Length of time symptom lasts

Interval: Length of time between events

Magnitude: Intensity of a particular behavior or psychological state


Single-Subject Design

Survey Research
Why Are Surveys Popular?
Agenda
Roll Call
Review Chapter 9
Prezi Time
Class activity
SLU Core Vlues: Community & Respect
Learning Objectives:
1. Learn about Errors in Survey Research
2. Explore Questionnaire Designs
3. Discuss Writing questions
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Electronic Surveys
Respondents complete surveys sent via e-mail or available on website
Prepared in two ways
E-mail
Web-based


Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Avoid Memory Questions
Recall loss
Telescoping effect

Survey research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Writing Questions
Write clear questions
Avoid confusing phrasing
Avoid vagueness
Provide a frame of reference
Avoid vague words
Avoid double negatives
Avoid double-barreled questions
Avoid jargon




Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Errors in Survey Research
Three sources of errors of non-observation
Non-response
Inadequate coverage of the population
Sampling error


Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Survey Research

CHAPTER 8

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Ethics in Survey Research
Fewer ethical dilemmas than in experimental or field research
Refusal is easy, methods are straightforward
Captive audiences must be free to decline to participate
Confidentiality is greatest concern
Answers may damage respondents if identities are discovered
Limit knowledge of respondents’ identities to staff and then only for specific
research purposes (e.g., follow-up mailings)
Only numbers should identify numbers on surveys
Electronic surveys should keep information encrypted

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Survey Research Design in a Diverse Society
Translating instruments
Content equivalence
Semantic equivalence
Technical equivalence
Criterion equivalence
Conceptual equivalence
Regional differences and particular language
Avoid colloquialisms or use alternate questions
Interview-respondent characteristic
Important dynamic to pay attention to

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Telephone Surveys
Interviewers question respondents over the phone and then record respondents’ answers.
Difficulties
Number of call-backs needed to reach respondents
Impersonal nature
Rapport
Careful interviewer training is essential




Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Group Administered Surveys
Completed by individual respondents assembled in a group
Advantages
Multiple respondents at a time (high response rate)
Low cost
Concerns
Seldom feasible
Respondents may potentially feel coerced



Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

May 24, 2015

Jane Doe
AIDS Coordinator
Shattuck Shelter
 
Dear Jane:
 
AIDS is an increasing concern for homeless people and for homeless shelters. The enclosed survey is about the AIDS problem and related issues confronting shelters. It is sponsored by the Life Lines AIDS Prevention Project for the Homeless—a program of the Massachusetts Department of Public Health.

As an AIDS coordinator/shelter director, you have learned about homeless persons’ problems and about implementing programs in response to these problems. The Life Lines Project needs to learn from your experience. Your answers to the questions in the enclosed survey will improve substantially the base of information for improving AIDS prevention programs.
 
Questions in the survey focus on AIDS prevention activities and on related aspects of shelter operations. It should take about 30 minutes to answer all the questions
Every shelter AIDS coordinator (or shelter director) in Massachusetts is being asked to complete the survey. And every response is vital to the success of the survey. The survey report must represent the full range of experiences.
 
You may be assured of complete confidentiality. No one outside of the university will have access to the questionnaire you return. (The ID number on the survey will permit us to check with nonrespondents to see if they need a replacement survey or other information.) All information presented in the report to Life Lines will be in aggregate form, with the exception of a list of the number, gender, and family status of each shelter’s guests.
 
Please mail the survey back to us by Monday, June 4, and feel free to call if you have any questions. Thank you for your assistance.
 
 
 

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Mailed Surveys
Advantages
Self administered
Usually highly structured
One respondent at a time
Low cost
Concerns
Maximizing response rates
Low response rate hurts representativeness


Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Five different survey designs

Mailed survey
Group survey
Phone survey
In-person interview
Electronic survey
Mixed Mode combines them to improve strength


Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

PRETEST!

Pilot study of questionnaire

Prepare questionnaire, complete it yourself and revise

Try revision on friends and colleagues and revise

Draw a small sample from population and administer revision and revise
Add interpretive questions, where respondents are asked to explain what
they mean by their responses

Extremely important if questionnaire has not been thoroughly pretested
Code what has been said


Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

PRETEST!
Refine and test questions in pretests to make sure respondents will understand the questions
Ask colleagues to review questions
Review prior research on topic
Have a panel of experts review questions
Conduct a focus group of potential respondents in which they are asked to explain their responses

Conduct cognitive interviews: The researcher asks a question and then probes with follow-up questions to learn how the question was understood
Behavior coding: A researcher observers several interviews or listens to taped interviews and codes according to strict rules the number of times that difficulties occur with each question

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Sensitive Questions
Topics that participants may consider too sensitive to discuss
Mental health issues
Drug use
One way to lessen embarrassment is to phrase the question
in such a way that agreement seems more acceptable





Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.


Scales
Have been demonstrated to be reliable
Types of scales include
Likert
Semantic Differential
Guttman

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Closed-ended Questions and Response Questions
Avoid making either disagreement or agreement disagreeable
Acquiescence or Agreement Bias
Subjects tend to agree just to avoid disagreeing
Social Desirability
Occurs more in interviews
Minimize fence-sitting or floaters
Use filter questions
Skip patterns
Contingent questions

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Closed-ended Questions and Open-ended Questions
Closed-ended questions
Explicit response categories
Used when surveying large groups of people
Open-ended questions
No explicit response choices
Require careful consideration


Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Tips for Questionnaire Design
Maintain consistent focus
Build on existing instruments
Attention to order of questions
Make sure questionnaire is attractive

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Secondary Data Surveys
Data are obtained from
Publically available data archives
Another researcher
One’s own previous projects that were designed to address some other research question



Survey Research

In-person Interviews
Face-to-face
Advantages
Response rates are higher
Can be much longer
Can be much more complex
Respondents’ interpretations can be clarified
Disadvantages
Careful training and supervision required
Potential for less reliable and less valid findings

Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Writing Questions
Reduce the risk of bias
Words should not trigger biased responses (leading questions)
Don’t use biased or loaded words
Phrasing may make questions more or less attractive
Make sure response choices reflect full range of possible sentiment If responses fall on a continuum, it is important that the number of
positive and negative categories are balanced


Survey Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Survey Research in Social Work
What is survey research?
Collects information from a sample of individuals through their responses to standardized questions

Why use survey research?
Three advantages
Versatility
Efficiency
Generalizability

Survey Research

Quantitative Data Analysis
Preparing Data for Analysis
Agenda
Roll Call Chapter 14
Prezi Time
Class Activity
SLU Core Values: Community & Respect
Learning Objectives:
1. Learn About Measure of Central Tendency
Explore Relationships Among Variables
3. Discuss How to Avoid Misleading Findings

Evidence-based Practice: The evidence of a particular intervention is tested with statistical methods for statistical significance which goes beyond the ones we have discussed.

Statistical significance means that an association is not likely due to chance. It answers the question does the treatment work? It is used to test the null hypothesis of no relationship versus the predicted relationship found in the alternative hypothesis.

There are many different types of statistical test: bivariate (chi-square, paired t-test, independent sample t-tests) or multivariate tests used when the researcher test several IV and DV.

Quantitative Data Analysis

Summarizing Univariate Distributions

Mode: The most frequent value in a distribution

Median: The position average or the point that divides the distribution in half (the 50th percentile)

Mean: The arithmetic average

Range: The difference between the lowest and highest number values in the set.

Quantitative Data Analysis

All graphs have:

Frequency polygons have Two axes:
The vertical axis (the y axis) represents frequencies/percentages
The horizontal axis (the x axis) displays bivariables being graphed

Labels to identify variables and values

Tick marks that show where indicated values fall on axes

Quantitative Data Analysis

Preparing Data for Analysis
Coding open-ended questions
Creating a codebook
Set of instructions
Data entry
Spreadsheet
Computer software



Quantitative Data Analysis

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Quantitative Data Analysis

CHAPTER 12

Analyzing Ethically: First and Foremost being honest and open.

When we summarize a distribution into a single number, we lose much information.

Choosing summary statistics that accentuate a particular feature of a distribution would be unethical.


Quantitative Data Analysis

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Statistical Significance: Occurs when an analyst can demonstrate at least 95% confidence that an association was not due to chance, reported as p<.05

Association is less likely to appear by chance in a larger sample

Weak associations can be significant in large populations; just because something is significant doesn’t mean it’s important.

Quantitative Data Analysis

Evaluating Association: Avoid concluding that an association exists in the population from which the sample was drawn unless the probability that the association was due to chance is less than 5 percent.

Measures of association: A type of descriptive statistic used to summarize the strength of an association.
Lambda- is a measure of association used for nominal variables it may range from 0.0 to 1.0. It provides us with an indication of the strength between the relationship between ithe IV and DV.

Gamma: A measure for ordinal level variables that ranges from -1 to +1 with zero indicating no relationship between the IV and DV..

Chi square: An inferential statistic used to estimate the probability of association in a population, based on comparing the actual number of cases in each cell with the predicted number of cases in each cell


Quantitative Data Analysis

Crosstabulation:Displays the distribution of one variable to each category of another variable

Bivariate distribution:
Display the distribution of two variables at the same time

Crosstab reveals:
Existence of association
Strength
Direction
Pattern

Quantitative Data Analysis

Measures of Variation

Range: The highest value in a distribution minus the lowest value plus one

Interquartile range: Difference between the first quartile and the third
quartile plus one

Variance: The average squared deviation of each case from the mean, mainly useful for calculating the standard deviation

Standard deviation: The distance from the mean that covers a clear majority of the cases (about two-thirds)

Normal distribution (bell-shaped)

Quantitative Data Analysis

Deciding whether to use the median or the mean?

Consider the level of measurement, shape of distribution, and purpose
of statistical summary.

In a symmetric distribution, median and mean are the same
If the purpose is to report the middle point, use median

Mean is most commonly used quantitative variable

Median is not affected by extreme values

Means are sometimes inappropriate for ordinal variables
Mean and median are never appropriate at nominal level

Median is most suited to ordinal variables
Mean is most suited for variables at the interval and ratio level

Quantitative Data Analysis

Summarizing Univariate Distributions

Central tendency: The most common value (for nominal measures) or the value around which other cases tend to cluster (for quantitative measures)

Selecting a measure of central tendency choose mode, median, mean, or range as one or more levels of measurement

Skewness of distribution demonstrate the spread or variability responses the shape of the responses.

Purpose for which a statistic will be used to determine right skew the positive numbers of cases or left skew the negative number of cases taper in either direction.

Quantitative Data Analysis

Combined and Compressed Distributions to present large groups of data
Combined frequency display, a frequency distribution in which a set of conceptually similar variables having the same response categories are presented together.

Also a compressed frequency displays a frequency distribution that can be used to present cross tabular data, and summarize statistics more effectively by eliminating unnecessary percentages and by reducing the need for repetitive labels.

Combined and compressed frequency displays to facilitate the presentation of a large amount of data in a relatively small space, which may confuse people otherwise.

Quantitative Data Analysis

When to us Frequency Distribution:

Grouping data: Reasons for grouping data
More than 15-20 potential values on a variable

Distribution of variable will be clearer or more meaningful if some values are combined

Guidelines for grouping data
Categories should be logically defensible and preserve the shape of the distribution

A frequency group of data should be mutually exclusive and exhaustive categories so that every case is classifiable in one and only one category.




Quantitative Data Analysis

Frequency Distribution
Display the number, percentage (relative frequency), or both for cases
corresponding to each variable’s values or group of values.

A title that clearly labels variables
A stub: Labels for the values of a variable
A caption: Identifies whether the distribution includes frequencies, percentages, or both

Number of missing cases
If table is based on percentages, the total number of cases in the distribution (the base number N) should be indicated

Quantitative Data Analysis

Guidelines for graph representativeness

Graphs should never distort the shape of the distribution
Begin a graph of a quantitative variable at zero on both axes and, if not, mark the break clearly on axis

Always use bars of equal width
The two axes should be of approximately equal length

Avoid chart junk, such as excessive marks, lines, words, etc.

Quantitative Data Analysis

Bar charts
Contain solid bars separated by spaces
Good for displaying distribution in discrete categories

Histograms
Contain adjacent bars
Good for displaying the distribution of quantitative variables
that vary along a continuum that has no necessary gaps

Frequency polygons
A continuous line connects the points representing the number or percentage of cases with each value

Quantitative Data Analysis

Displaying Univariate Distributions

Univariate distributions: Displaying variation in each variable of interest,
showing shape of distribution

Level of measurement is most important determinant of the appropriateness of a particular statistic

Graphs: Bar chart (solid bars separated by spaces) and histograms (bars with no gaps in the displays) pg. 270

Advantages
Easy to read
Highlights shapes of distribution

Quantitative Data Analysis

Displaying Univariate Distributions: Simplist form of quantitative analysis describes a single variable in terms of the unit of analysis. Ex. If the variable is age, the researcher looks at how many subjects fall into a given age category.

Primary concern to accurately display shape of distribution in 2 ways:

Central Tendency
Most common value or values around which cases center around variability
Extent to which cases are spread out or clustered

Skewness
Extent to which cases are clustered more at one end
Positive (right skew)
Negative (left skew)

Quantitative Data Analysis

Preparing Data for Analysis: Generally involves assigning a number to a particular response to a question, observation, or a case record response.

Assign a unique Identification number to each form, questionnaire, survey, transcript. You would include the identifier as a variable in the data and helps you link responses.

Reviewing the forms for mistakes and have rules to follow when you find mistakes. Document the rules for consistent means of correction. Ex: Pg 266

Precoding: Every response choice on a questionnaire is represented by a
number and respondents are instructed to indicate their response to a question by checking a number
Questions to consider
Are the responses open-ended,clearly indicated?
Misread instructions?
Incomplete questionnaires
Unexpected responses

Quantitative Data Analysis

Introducing Statistics:

DO NOT FEAR STATISTICS!!

Descriptive statistics (inductive) describe the distribution of and relationships
among variables, they are used to describe clients, agencies, & communities, monitor practice, assess effectiveness of social work interventions.

Inferential statistics (deductive) estimate the degree of confidence that can be placed in generalizations from a sample to the population from which the sample was drawn, uses central tendency (mean, median ,mode), measures of variability or dispersion (standard deviation or skewness.

Quantitative Data Analysis

Preparing Data for Analysis

Data cleaning: Carefully checking for errors in data after data entry into a computer

Check responses before entry

Check that no invalid codes are entered (check coding)

Once data is entered, compute frequencies; may discover invalid code

Use of database management program helps dfine variables to computer if necessary

Quantitative Data Analysis

Reporting Research
Writing A Research Report
Agenda
Roll Call
Chapter 15 Review
Prezi Time
Class Activity
SLU Core Values: Community & Respect
Learning Objectives:
1. Explore How To Report Results
2. Learn to Make Poster Presentations
Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Poster Presentations

Effective way to communicate results

Often posters at conferences are melded into publications

Text is best presented bulleted

Use of graphs and tables is important

Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Reporting Research

CHAPTER 14

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Ethics, Politics, and Research Reports Continued:

Use the popular media with discretion

Focus on issues of national concern or that are high on the public agenda

Develop creative and thoughtful arguments that are clearly presented and devoid of technical language


Present the big picture whereby the arguments are organized and presented so that readers can see how the various parts are interrelated



Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Reporting Qualitative Research

Diverges a bit from quantitative reporting

Use elements that reflect holistic and reflexive approach

Include how researcher gained access and selected participants

Include quotes from participants and observational notes

Provide commentary on how researcher reacted in setting


Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.


Peer-reviewed journals

Methods section includes:
Research design
Setting
Participants/sample
Measures
Data collection
Statistical methods


Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.


To facilitate writing
Draw on the research proposal and project notes

Use a word processing program

Seek criticism from others before turning in a final draft

Reverse outlining
After you have written a first complete draft, outline it on a paragraph-by-paragraph basis, ignoring the actual section heads used to determine if the paper fits the planned outline


Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.


Writing research
The goal of research is not just to discover something, but to communicate
that discovery to a larger audience

Successful research reporting must have good writing
Don’t expect to write a polished draft in a linear fashion

Leave time for revisions and accept that much of what you write will be discarded

Write as fast as you can; spelling and grammar should be left for revisions
Ask for reactions from other people you trust

Draft segments as you go; don’t write it all at once

Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Social Work Research Proposals

Six sections
Introductory statement of the research problem
A literature review
A methodological plan
A budget
An ethics statement
A statement of limitations

IMPORTANT
Have others review a proposal before you submit it

Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Standards for Ethics, Politics, and Research Reports

Guidelines
Provide an honest accounting of how research was carried out and where the initial research design had to be changed

Maintain a full record of the research project so that questions can be answered if they arise

Avoid lying with statistics or using graphs to mislead

Acknowledge the sponsors of the research

Thank staff who made major contributions

Be sure that the order of authorship for coauthored reports is discussed in advance and reflects agreed-upon principles

Reporting Research

Engel and Schutt: Fundamentals of Social Work Research © 2015 SAGE Publications, Inc.

Applied Research Reports

Written for a different/wider audience
Serve multiple purposes
More information than a journal article
Must anticipate the needs of the audience

Sections:

Front matter:
Executive summary: A summary list of the study’s main findings, often with bullet points

Introduction with lead in to,
Findings and Recommendations should be engaging and clear to a general audience

Back matter:
Appendices: Tables, copies of the instrument, etc.





Reporting Research

Chapter 5
Chapter 8
Chapter 9
Chapter 14
Chapter 15
Chapter 7
Agenda
Roll Call
Chapter 7 Review
Prezi time
Class Activity
SLU Core Values: Community & Respect
Chapter 7
Chapter 1: Science, Society, and Social Work Research
Journal Article 1.1 Miller, P.M. (2011). A critical analysis of the research on student homelessness. Review of Educational Research, 81. 308-337.
Questions that apply to this article:
1. Discuss the various definitions of homelessness as it pertains to children.
2. What are the causes of homelessness as it pertains to children?
3. According to the author, what can serve as supports for homeless children?


Video Resources
o
Evidenced-Based Practice in the Real World-Part 1
This 9-minute 31-second video is the first part of a series that discusses the importance of innovative evidence-based practice with children and families.
o
Evidenced-Based Practice in the Real World-Part 2
This 9-minute 49-second video is the second part of a series that discusses the importance of innovative evidence-based practice with adults.
o
The New Homeless
The 4-minute 16-second video clip discusses the “new homeless” and who resides in the tent city of Pinellas Hope, Florida.

Web Exercises
o Prepare a 5- to 10-minute class presentation on the U.S. Department of Housing and Urban Development (HUD) report, Homelessness: Programs and the People They Serve. Go to the Web site, http://www.hudhre.info/documents/2010HomelessAssessmentReport.pdf. Write up a brief outline for your presentation, including information on study design, questions asked, and major findings.

Chapter 2: The Process and Problems of Social Work Research
Journal Article 2.1 Anderson, M.L. & Leigh, I.W. (2011). Intimate partner violence against Deaf female college students. Violence Against Women,7(7). 822-834.
Questions that apply to this article:
1. What were the questions that researchers were attempting to answer in this study?
2. What was the hypothesis tested?
3. Discuss the implications of the findings for diverse populations.


Video Resources
o
QUT Faculty of Law and Justice - Crime and Justice Research
This 3-minute 27-second video is about a man interested in researching intimate partner violence and same-sex couples. He explains how this subject is not well understood and his interest in researching this topic.

o
Low-income African American Mothers' Food Insecurity Management Strategies: Qualitative Insights
This video discusses the coping mechanisms of low-income, African American parents who experienced food insecurity.

Web Exercises
o Prepare a 5-10 minute class presentation on the US Department of Housing and Urban Development report Homelessness: Programs and the and the People They Serve (www.huduser.org/portal/publications/homeless/homelessness/contents.html). Write up a brief outline for your presentation, including information on study design, questions asked, and major findings.



Chapter 3: Ethical and Scientific Guidelines for Social Work Research
Journal Article 3.1: Neutel, C. I. (2004). The dilemma of using humans as research subjects: An assessment of risks and benefits. Drug Information Journal, 38(2), 113-126.
Questions that apply to this article:
1. What are the four ethical principles The Belmont Report outlines?
2. There are various types of risks to which a participant may be exposed because of the research project. Name some of these risks.
3. Discuss possible benefits for participants of research studies.
4. List and describe a few of the potential risks to society.
Journal Article 3.2: Lind, C., Anderson, B., Oberle, K. (2003). Ethical issues in adolescent consent for research. Nursing Ethics, 10(5), 504-511.
Questions that apply to this article:
1. What are some of the barriers to adolescents’ full involvement in research?
2. Describe what it means when adolescent research participants are referred to as “captive subjects.”
3. Discuss the debate of whether or not children and adolescents should be involved in research.
4. What is the Nuremberg Code?

o
Stanford Prison Experiment Obedience to Authority Experiment
This video discusses the Standford Prison experiment.
Nuremberg War Crime Trials
This 10-minute video discusses the Nuremberg War Crime Trials.
o
Tuskegee Syphilis Experiment
University of Maryland Associate Professor of Philosophy, Dr. Sam Kerstein, explains the Tuskegee Syphilis Experiment and how it influenced medical ethics and the treatment of patients.
o http://mentalfloss.com/article/52787/10-famous-psychological-experiments-could-never-happen-today
Ten Experiments that Could Not Happen Today
Explores through text and video ten famous psychological experiments that would not be possible today due to stricter federal regulations on the use of human subjects. Includes videos on Milgram and Tuskegee experiments

Web Exercises
o The Collaborative Institutional Training Initiative (CITI) offers an extensive online training course in the basics of human subjects protections issues. Go to the CITI public access site at https://www.citiprogram.org/rcrpage.asp?la nguage=english&affiliation=100 and complete the course in social and behavioral research. Write a short summary of what you learn.

o The U.S. Department of Health and Human Services maintains extensive resources concerning the protection of human subjects in research. Read several documents that you find on its website (www.hhs.gov/ohrp) and write a short report about them.
o Go to your university or another university and review recommendations regarding ethical conduct in internet research.

Chapter 4: Conceptualization and Measurement
Journal Article 4.1: Hox, J. J., de Leeuw, D., & Chang, H. (2012). Nonresponse versus measurement error: Are reluctant respondents worth pursing? Bulletin of Sociological Methodology, 113(1), 5-19.
Questions that apply to this article:
1. What is measurement error?
2. Discuss sample composition bias and provide an example.
3. The common cause model states that there is indeed a relationship between reluctance to respond and data quality. Two different mechanisms can be posed for this common cause relationship between response propensity and measurement error. What are these two mechanisms?

4. Discuss the recent trend in survey participation.
Journal Article 4.2: Hogan, T. P., & Agnello, J. (2004). An empirical study of reporting practices concerning measurement validity. Educational and Psychological Measurement, 64(5), 802-812.
Questions that apply to this article:
1. Discuss validity and its role in testing and measurements.
2. What are types of validity evidence?
3. Discuss journal editorial policies and their influence on reporting validity.
4. Describe the findings of this article. Which one is reported more frequently—validity or reliability?

Journal Article 4.3: Carlson, K. D., & Herdman, A. O. (2012). Understanding the impact of convergent validity on research results. Organizational Research Methods, 15(1), 17-32.
Questions that apply to this article:
1. Define convergent validity.
2. Define proxies.
3. Discuss the use of proxies in research design.
4. Describe convergent validity’s impact on research findings.



Video Resources
o
Different Levels of Measurement
A clear and engaging description and illustration of the different levels of measurement (Nominal, Ordinal and Interval/Ratio).
o
Reliability and Validity
A discussion of reliability and validity and their interrelationship.
o
Chronbach Alpha Coefficient and Reliability
A discussion regarding Cronbach's Alpha Coefficient and Reliability.


Web Exercises
o How would you define alcoholism? Write a brief definition. Based on this conceptualization, describe a method of measurement that would be valid for a study of alcoholism.
o Now go to the American Council for Drug Education and read some facts about alcohol (www.acde.org/common/alcohol2.pdf). Is this information consistent with the definition you developed for Question 1?

Chapter 5: Sampling
Journal Article 5.1: Cohen, N., & Arieli, T. (2011). Field research in conflict environments: Methodological challenges and snowball sampling. Journal of Peace Research, 28(4), 423-435.
Questions that apply to this article:
1. Discuss the snowball sampling methodology.
2. What are the advantages of snowball sampling?
3. What are the limitations of snowball sampling?

4. Discuss conflict environments. How can snowball sampling help?
Journal Article 5.2: Wyse, J. J. B. (2013). Rehabilitating Criminal Selves: Gendered Strategies in Community Corrections. Gender & Society, 27(2), 231-255.
Questions that apply to this article:
1. Discuss the multiple forms of sampling the author uses.
2. How do these qualitative and quantitative sampling strategies aid both the research aims and internal validity?
3. Discuss the author’s claim that her quantitative sampling technique is a means for controlling her regression analysis.

4. What are the strengths and weaknesses of this sampling practice?.
Journal Article 5.3: Fitzner, K., & Heckinger, E. (2010). Sample size calculation and power analysis: A quick review. The Diabetes Educator, 36(5), 701-707.
Questions that apply to this article:
1. What is statistical significance?
2. Discuss effect size. When should it be calculated?
3. What is a confidence interval?
4. Outline the sample size checklist presented in this article.


Video Resources
o
Stratified Sampling
An example of stratified sampling.
o
Cluster Sampling
An example of cluster sampling.
o
Sample Size
How to determine sample size.

Web Exercises
o Research on health care concerns has increased in recent years as health care costs have risen. Search the Web for sites that include the words medically uninsured and see what you find. You might try limiting your search to those that also contain the word census. Pick a site and write a paragraph about what you learned from it.
o Check out the people section of the U.S. Bureau of the Census Web site: www.census.gov. Based on some of the data you find there, write a brief summary of some aspect of the current characteristics of the American population.

Chapter 6: Group Experimental Designs
Journal Article 6.1: Ployhart, R. E., & Vandenberg, R. J. (2010). Longitudinal research: The theory, design,
and analysis of change. Journal of Management, 36(1), 94-120.
Questions that apply to this article:
1. What is longitudinal research?
2. Describe the numerous theoretical issues that must be considered when conceptualizing a longitudinal study.
3. What are the various analytical issues and approaches that are unique to longitudinal research?
4. Is there a minimum number of repeated measures for a longitudinal design?

Journal Article 6.2: Wagner, T. D. (2005). The neural bases of placebo effects in pain. Current Directions in
Psychological Science, 14(4), 175-179.
Questions that apply to this article:
1. What is a placebo effect?
2. Describe the effects of placebo on pain.
3. Discuss the process of placebo treatment.
4. Discuss the benefits of studying placebos.

Journal Article 6.3: Green, J. (2010). Points of intersection between randomized experiments and quasi-experiments.
The ANNALS of the American Academy of Political and Social Science, 628(1), 97-111.
Questions that apply to this article:
1. What are quasi-experiments?
2. Discuss the threats to internal validity using quasi-experiments.
3. Discuss the threats to external validity using true experiments.
4. Compare/contrast quasi-experiments and true experiments.

Video Resources
o
Internal Validity
This video discusses nine threats to internal validity.
o
External Validity
This video discusses threats to external validity.
o
Pre-Test and Post-Test Measures
This video covers a variety of types of pre- and post-tests for measuring program outcomes, including written
surveys/questionnaires as well as participatory methods. You will learn about ways to increase the validity of your
pre- and post-test measures, how to use your program objectives to develop good survey questions, tips for effective
question ordering, and the use of retrospective pre- and post-tests.

Web Exercises
o Try out the process of randomization. Go to the Web site http://www.randomizer.org. Type numbers into the randomizer
for an experiment with 2 groups and 20 individu¬als per group. Repeat the process for an experiment with 4 groups and
10 individuals per group. Plot the numbers corresponding to each individual in each group. Does the distribution of numbers
within each group truly seem to be random?

o Participate in a social psychology experiment on the Web. Go to http://www.socialpsychology.org/expts.htm. Pick an experiment
in which to participate and follow the instructions. After you finish, write up a description of the experiment and evaluate it using
the criteria discussed in the chapter.

Chapter 7: Single-Subject Design
Journal Article 7.1: Tankersley, M., Harjusola-Webb, S., & Landrum, T. J. (2008). Using single-subject research to establish the evidence base of special education. Intervention in School and Clinic, 44(2), 83-90.
Questions that apply to this article:
1. Discuss the essential features of single subject research design.
2. Discuss repeated measurement of target behaviors. Why is this important in single subject design?
3. Discuss systematic introduction of the intervention.
4. Describe reversal and multiple-baseline designs.

Journal Article 7.2: Foster, L. H. (2010). A best kept secret: Single-subject research design in counseling. Counseling Outcome Research and Evaluation 1(2), 30-39.
Questions that apply to this article:
1. What are A-B designs?
2. What are A-B-A designs?
3. What are A-B-A-B designs?
4. Discuss multiple-baseline designs.

Journal Article 7.3: Orosco, M. J. (2014). Word Problem Strategy for Latino English Language Learners at Risk for Math Disabilities. Learning Disability Quarterly, 37(1), 45-53.
Questions that apply to this article:
1. What was the goal of this research study?
2. Outline the stages of this research study from how students were selected to the end of the experiment?
3. Discuss some strengths and weaknesses of using single subject design for educational research.
4. How did the researcher manage reactivity during the study?


Video Resources
o
Single Case Research Designs
This video discusses single case designs, specifically, multiple baseline design.
o
Single Case Research Designs
This video discusses single case designs, specifically, AB, ABA, and ABAB design.
o
Internal Validity
This video discusses internal validity.


Web Exercises
o Visit the Northwest Regional Education Laboratory’s archives and read Close Up #9, School wide and Classroom Discipline (http://www.nwrel.org/archive/sirs/5/cu9.html). Select three of the techniques that educators use to minimize disruption in educational settings and then suggest a single-subject design that could be used to evaluate the effectiveness of each technique. Bear in mind the nature of the misbehavior and the treatment.

Which of the designs seems most appropriate? How would you go about conducting your research? Think about things such as operationalizing the target behavior, determining how it will be measured (frequency, duration, magnitude, etc.), deciding on the length of the baseline and treatment periods, and accounting for threats to internal validity.

o Access the PsycINFO database through your university library’s website. Perform a search using the words comparative single-subject research. Click on the link to the full text version of the article by Holcombe, Wolery, and Gast (1994). Review the description of the designs used and then the discussion of the problems faced in each of these. Can you think of any other issues the authors may have neglected? Which of these methods would you employ? Why?

Chapter 8: Survey Research
Journal Article 8.1: Lavi, I., & Slone, M. (2011). Resilience and Political Violence: A Cross-Cultural Study of Moderating Effects Among Jewish- and Arab-Israeli Youth. Youth & Society, 43(3), 845-872.
Questions that apply to this article:
1. How did the researchers construct their survey instrument?
2. Analyze the questionnaire given typical design considerations.
3. Why was it important for interviewers to read the survey out loud?
4. What was the rationale behind interviewing both mother and child?

Journal Article 8.2: Holtgraves, T. (2004). Social desirability and self-reports: Testing models of socially desirable responding. Personality and Social Psychology Bulletin, 30(2), 161-172.
Questions that apply to this article:
1. What is social desirability and how does it impact self-report measures?
2. Discuss the retrieval and evaluation stages of self-report.
3. What is response faking?
4. How does self-deception relate to social desirability?

Journal Article 8.3: Ziegler, S. J. (2006). Increasing response rates in mail surveys without increasing error: A research note. Criminal Justice Policy Review, 17(1), 22-31.
Questions that apply to this article:
1. Discuss how researchers can increase response rates in mail surveys.
2. Describe the Tailored Design Method.
3. What was found to be more effective than any other technique for increasing response to surveys by mail?
4. Discuss the potential for error when engaging in multiple contacts with potential respondents.


Video Resources
o
Open-ended vs. Closed-ended Research Questions
This video discusses the importance of open-ended research questions.
o
Survey Research
This video introduces the research method of survey research.
o http://wn.com/Survey_methodology
Survey Methodology
This video discusses introduction to survey methodology.

Web Exercises
o Go to the Research Triangle Institute Web site at http://www.rti.org; click on “Survey Research & Services” and then “Innovations.” Read about their methods for computer-assisted interviewing and their cognitive laboratory methods for refining. What does this add to the treatment of these topics in this chapter?
o Go to the Survey Resources Network at http://surveynet.ac.uk/sqb/. Click on the “Surveys” link and then click on one of the listed surveys or survey sections that interest you. Review 10 questions used in the survey, and critique them in terms of the principles for question writing that you have learned. Do you find any question features that might be attributed to the use of British English? How might you change those features?

Check out this amazing website from USAID
http://www.povertytools.org/povertypres/index.html

1. Then develop 10 survey questions about beliefs of social work students about poverty. Did you use open-ended questions or both? What demographic information did you query? Did you attend to attractiveness? Is the instrument user-friendly?
Chapter 12: Quantitative Data Analysis
Journal Article 12.1: Pryjmachuk, S., & Richards, D. A. (2007). Look before you leap and don’t put all your eggs in one basket: The need for caution and prudence in quantitative data analysis. Journal of Research in Nursing, 12(1), 43-54.
Questions that apply to this article:
1. Discuss data cleaning, data screening, and exploratory data analysis.
2. Describe the assumptions underlying parametric test of comparison.
3. What are confidence intervals, effect sizes, and the meaning of significance?
4. Why are effect size statistics important?
Journal Article 12.2: Kandel, S., Heer, J., Plaisant, C., Kennedy, J., van Ham, F., Riche, N. H., Weaver, C., Lee, B., Brodbeck, D., & Buono, P. (2011). Research directions in data wrangling:

Visualizations and transformations for usable and credible data. Information Visualization, 10(4), 271-288.
Questions that apply to this article:
1. Discuss the process of transforming data.
2. How are multiple data sets integrated?
3. How can visualizing raw data help researchers gain insight about data errors?
4. How are erroneous values corrected?

Journal Article 12.3: Magis, D., & De Boeck, P. (2012). A robust outlier approach to prevent type I error inflation in differential item functioning. Educational and Psychological Measurement, 72(2), 291-311.
Questions that apply to this article:
1. Discuss the outlier detection approach.
2. Describe type I errors and power.
3. What are robust statistics?
4. What is the Type I error inflation effect?

Video Resources
o
Qualitative Data
David Silverman giving an interview on qualitative data sources and the benefits of natural data.
o http://vimeo.com/2216855
Ethnography
In this video, Aviva Rosenstein, Ph.D., discusses the difference between the competing claims to the title of "ethnography" (is it a methodology? a discipline? a literary genre?) and how ethnography relates to user research.
o
Qualitative Interviewing
After a short introduction looking at Steinar Kvale's ten criteria of a good interviewer, this video examines two interviews: one a short and rather poor attempt, the other a longer and much improved version. It is designed to help anyone learning how to undertake research interviews in the social sciences.

Video Resources
o http://videolectures.net/ssmt09_onwuegbuzie_mmr/
Mixed Methods Research
This video provides new and seasoned researchers with a framework in a step-by-step manner for using quantitative and qualitative research approaches within the same study.
o
Mixed Methods Research
Dr. John W. Creswell provides a look into mixed methods research.
o
Mixed Methods Research
Robert Walker of Oxford University gives an introduction to mixed methods evaluation.


Video Resources
o
Central Tendency
This video introduces measures of central tendency as used in basic statistical analysis.
o
Range and Interquartile Range
This video illustrates how to calculate the range and the interquartile range (IR) of a block of data, and explains the difference between the two terms.
o
Standard Deviation and Variance
The tutorial provides a step-by-step guide on calculating the standard deviation and variance for statistics class.


Web Exercises
o Using the data found at: http://www.oas.samhsa.gov/ statesList.cfm locate the state in which you live (listed alphabetically). How did the researchers decide to group the data? Why do you believe they chose to do so in this manner? Would you have made the same choice? Why or why not?

o Using the same table as referenced in Exercise 1, examine the distribution of substance use by age. Graph the results for the past month of cigarette use by age. What does the frequency distribution look like? What would you say with regard to skew¬ness? Does the above referenced table give you enough informa¬tion to make comparisons between variables? Why or why not?

Chapter 14: Reporting Research
Journal Article 14.1: Caulley, D. N. (2008). Making qualitative research reports less boring: The techniques of writing creative nonfiction. Qualitative Inquiry, 14(3), 424-449.
Questions that apply to this article:
1. What is creative nonfiction?
2. Discuss the difference between dramatic and summary methods of writing.
3. Should the researcher write in the first or third person?
4. Can the creative nonfiction writer report a person’s thoughts?

Journal Article 14.2: Oppenheim, C., & Bence, V. (2004). The influence of peer review on the research assessment exercise. Journal of Information Science, 30(4), 347-368.
Questions that apply to this article:
1. Discuss the peer-review process.
2. What are the four main functions of scholarly communication?
3. Discuss the advantages and disadvantages of the peer-review process.
4. Has electronic publishing changed peer review?

Journal Article 14.3: Davis, L. (2011). Arresting student plagiarism: Are we investigators or educators? Business Communication Quarterly, 74(2), 160-163.
Questions that apply to this article:
1. Discuss tips and techniques for preventing plagiarism without using technology.
2. Define plagiarism.
3. At what point in the class should professors discuss plagiarism?
4. Discuss strategies for hindering plagiarism using technology.

Video Resources
o
Research Paper Proposal
This video discusses writing a research paper proposal, including the thesis of the paper, at least three important points in the paper, and at least three primary and secondary sources.
o
Research Proposals
This video discusses guidelines for writing successful research proposals in the sciences.
o
Plagiarism
This second in a series on Ethics of Research and Publishing discusses a number of serious questions involving plagiarism: Can I reuse text I wrote for a previous publication? Can I use the same methods section over again? Who is responsible for plagiari
Full transcript