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

Chp 02

description
by

Psyc-Lecture Notes

on 6 September 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Chp 02

Research in Psychology
?
Formulate a Testable Hypothesis
While asking questions, scientists formulate their questions as testable statements or hypotheses.
Hypothesis is derived from a theory.
Psychologists construct a theory, system of interrelated ideas to explain a set of observations.
Hypotheses are predictions, tentative statements about the relationship between two or more variables.
Variables are any measurable conditions, events, characteristics, or behaviours that are controlled or observed in a study.
Example from Bandura's study:
Social Learning Theory
Hyp:Children that observe or watch aggressive adult models would reproduce aggressive acts.
Here, ‘watching aggressive adults’ and ‘aggressive acts’ are the variables. Bandura can control exposure to aggressive models and he can observe aggressive act of children.
Select Research Method and Design of the Study
Collect Data
Experimental
Correlational
Descriptive
The investigator manipulates a variable under carefully controlled conditions and observes whether any change occur in a second variable as a result.
Researcher has no control over variables, and tries to understand how variables are related to each other.
Researcher tries to understand an event, behaviour and tries to describe and categorize it.
Independent variable: Variable that the experimenter controls or manipulates.
Dependent variable: Variable that is thought to be affected by manipulation of the independent variable.
Experimental group receives some special treatment in regard to the independent variable.
Control group does not receive the special treatment given to the experimental group.
Random assignment: Randomly assigning subjects to each group and assuming that all subjects (participants) will have an equal chance of being assigned to any group.
Extraneous variables: Variables other than our independent variable that might affect dependent variable. A confounding of variables occur when two variables are linked together and making it difficult to sort out their individual effects.
Researchers define the operational definitions. Operational definition might be different than the dictionary definition and it tells how researcher measures or controls a variable.
We cannot draw causal conclusions.
We can never know the causal direction of the relation.
We can never know if our variables are actually related. Their relation might be as a result of a third variable.
Survey studies are a well-known example for correlational studies
These studies might be especially valuable in the early stages of research.
The importance of descriptive studies should not be underestimated.
Observation and case studies are well-known examples for descriptive studies.
Observation
Self-Report
Physiological Recording
Examination of Archival Data
Analyze and Evaluate Data
Report Findings
Inferential
Correlational
Descriptive
Descriptive Stat provide summary.
The most useful measure of central tendency is the mean.

Mean is the arithmetic average of a set of numbers.
You need additional information. That’s why there are other central tendency measures.
Median: the score that falls exactly in the centre of a distribution.
Mode: the most frequent score in a distribution.
Ex: 20 , 20 , 25 , 35 , 200

Mean: 60
Median: 25
Mode: 20
It is also useful to know variability of the scores. Variability tells us how much the scores in a data set vary from each other and from the mean.
Standard Deviation tells us how far away each value is from mean on average.
Correlations Describe the Relationships between Variables
An index known as correlation coefficient is calculated. This coefficient provides a numerical value (between -1 and +1). This coefficient gives us two important pieces of information:

1)The direction of the relation (positive or negative): If the correlation coefficient is positive, it means that the two variables increase or decrease together.

2)The strength of the relation: When the coefficient value is close to -/+ 1, the relationship is stronger. If the coefficient is 1, this means there is perfect relation. If there is no relation at all, the coefficient will be zero.
Inferential Statistics Predict Chance Results
Psychological Test
Systematic assessment and coding of behaviour
While using observational techniques you should decide on three things depending on your study’s requirements.
Should it be in the lab or in the natural environment?
Observation in lab environment might cause artificial behavior.
Should you collect data as written descriptions or as grouping in categories of behaviour?
You can write each behaviour down or you can run a list of behaviour categories
Should the observer be visible?
In general, observation should be as unnoticeable as possible
Interactive ways of collecting data
Questionnaires, surveys, and interviews are all aimed to get people give information about themselves- their demographic facts (age, religious affiliation and etc), personal attitudes, beliefs, past behaviour and so on.
Questionnaires and surveys can be used to gather data from a large number of people. They are easy to administer, cost-efficient and time efficient.
Interviews can be used to reach limited number of people. Interviews are face-to-face dialogues
and they give the researcher the opportunity to explore more about a particular subject.
Standardized measures (such as intelligence test) to assess mental abilities or personal traits.
They can also be used in measuring response performance. How participants response to a stimulus can inform us about the processing in the brain.
These tests can be a relatively simple way to study cognition and perception.
Researchers examine how changes in bodily functions are associated with behaviour and mental state by using physiological recording techniques.
They monitor and record a specific physiological process in a subject, such as heart rate, muscle tension, brain activity.
We should be aware of the fact that the relation between physical functioning and mental/emotional states are not perfectly understood.
Institutional records (the archives) such as census, economic, medical, legal, educational, and business records, can provide information for researchers.
Archival data can be used in correlational and descriptive studies.
The final step in a scientific investigation is to write up a summary of the study and findings.
Scientific progress can be achieved only if researchers share their findings with one another and with the general public.
Researchers deliver their reports at scientific meetings and submit them to journals for publication.
The process of publishing allows other experts to evaluate and critique new research.
Researchers need to decide whether their data support their hypotheses. They evaluate the possibility that their results might be due to the chance.
Control Group
Mean: 6.3
Sd: 1.4
Experimental group:
Mean: 6.8
Sd: 2.4
Is this observed difference between the two groups large enough to support our hypothesis? Or could a difference of this size have occurred by chance?
When statistical calculations indicate that research results are not likely to be due to chance, the results are said to be statistically significant. The probability that results are due to chance is very low, such as fewer than 5 chances in 100, (also shown as <.05)
Is research error free?
Does researcher have
ultimate power?
NO
There is always a probability that our result
may not be true.

That's why there are replication of studies.
We are all human beings. Both researchers and the participants are human beings who have personal biases, expectations and worries that can affect the results of the study.
Our expectations affect us more than we think
We want to leave a positive impression on other people
Placebo effect
Experimenter bias
Socially desirable responding
Other flaws include sampling bias and response set.
Solution: Double-blind process (not knowing the condition)
Solution: Being anonymous
NO
Milgram's Experiment
Hawthorne Effect
To ensure the well being of participants and protect their rights, ethical guideliness are created.

These guidelines are set out by Canadian Psychological Association and research practices are followed and approved by variety of committees and boards.

Accordingly, participants have to be informed about the study, potential risks and benefits. Participant are free to withdraw from the study and to contact researcher after the study. Their information is confidential. Researcher has to debrief them about the aim of the study.
Interconnected ideas (..............) yield testable predictions (....................), which are tested in a systematic way (..................) by collecting and evaluating evidence (.....................).
Interconnected ideas (theory) yield testable predictions (hypotheses), which are tested in a systematic way (research) by collecting and evaluating evidence (data).
A hypothesis states that television violence causes children to be violent. A researcher tests this hypothesis by using a television-viewing behaviour questionnaire and then observing how children behave during recess at school. This type of study is:

a) correlational and therefore cannot establish if TV causes violence, because of a potential third variable.

b) experimental because the researcher has control over the setting in which the behaviour is observed.

c) descriptive, only because there is observation involved.

d) able to clearly establish that viewing violence on television causes violence at school.
It is a correlational study.

Variables: Viewing violence on TV and violence behaviour

Correlational studies use questionnaires or surveys mostly.

We cannot draw casual conclusions in correlational or descriptive studies.
An experimenter tests the hypothesis that physical exercise helps people's mood (makes them happier). Subjects in the experimental group participate on Monday and Tuesday and those in control group on Wednesday and Thursday.

What is the independent variable?

a) the hypothesis
b) the day of the week
c) the exercise
d) the mood (degree of happiness)

What is the dependent variable?

a) the hypothesis
b) the day of the week
c) the exercise
d) the mood (degree of happiness)

What is a confounding variable?

a) the hypothesis
b) the day of the week
c) the exercise
d) the mood (degree of happiness)
Hypothesis: Physical exercise makes people happier.

Independent variable: Physical exercise (Under researchers control)

Dependent variable: Degree of happiness

Confounding variable: the day of the week (people might be less happy on Monday and Tuesday)
1) Dr. Smith is measuring electrical activity of her participants' brains to understand how people recognize faces.

2) July is investigating traffic accident reports to understand how drinking and accidents are related.

3) A researcher is studying aggressive behaviour of monkeys by watching them in their natural environment.

4) Micheal is administering Five-factor personality test to his subjects to investigate personality differences in stress experience.

5) Dr. Hall is interviewing people with frontal brain damage to understand the changes in patients' lives after the injury.
Data Collection Techniques


Self-report


Examination of Archival Data


Psychological Testing


Physiological Testing


Observation
1-Physiological Testing
2-Examination of Archival Data
3-Observation
4-Psychological Testing
5-Self-report
Researchers find a negative relationship between alcohol consumption and speed of response. Which of the following fictitious statistics could possibly represent that correlation?

a) -4.57
b) -.87
c) .91
d) .05
Correlation coeffcient changes between -1 and +1

If there is no relation between two variables the coefficient value is equal to zero.

If two variables are positively related, they move the the same direction. They both increase or decrease.

If the relation is negative, the variables move in opposite directions.

Since response rate decrease as alcohol consumption increases, they move in opposite directions. The answer is -.87
Masali conducted a study in which she measured the response time for males and females to complete a spatial task. She found that the mean response time was 1.48 minutes for males and 1.63 minutes for females. For Masali to be confident that an actual difference exists between males and females, what must she do?

a.calculate a correlation coefficient
b.redo the experiment
c.obtain a larger sample
d.calculate an inferential statistic
Infrential stat tells us if there is an actual difference between our groups. If a difference is statistically significant, it means that the difference is due to manipulation (independent variable) not due to chance factors.
Non-experimental
In looking through some medical records, you find there is a strong relationship between depression and chronic pain: The stronger the physical pain that people report, the higher their scores on an inventory that measures depression. Which of the following conclusion is justified?

a. Depression tends to produce chronic pain.
b. Chronic pain tends to produce depression.
c. Both chronic pain and depression result from some unknown third factor.
d. Any of the above.
Any of the statements is a possible causal explanation of the relationship, but we do not know which one may be correct because the study is correlational. Therefore, no causal conclusions are justified.
Full transcript