Pre-Experimental, True-Experimental, and Quasi-Experimental

Pre-Experimental, True-Experimental, and Quasi-Experimental Research Designs

Inference:

- is a conclusion that can be logically drawn in light of our research design and our findings

Casual Inference:

- is one derived from a research design and findings that logically imply that the IV really has a Casual on the DV

Research Design:

- refers to all the decision made in planning and conducting research including decision about, research question, appropriate design, measurement, sampling, data

collection, logical arrangements designed to permit

certain kind of inferences

Validity:

- Refers to the extent to which an empirical measure adequately measures the real meaning of concept under consideration

- the extent to which a test measures what it claims to measure

- a measurement (operationalization) accurately captures the construct

Construct Operationalization Assessment (Measures)

Gender M/F… self-report

Poverty annual income payroll slips, self-report,

Karun K. Karki

Threats to Internal Validity

Pre-Experimental, True-Experimental, and Quasi-Experimental Research Designs

Pre-Experimental, True-Experimental, and Quasi-Experimental Research Designs

External Validity:

-refers to the extent to which we can generalize the findings of a study to setting and populations beyond the study conditions

can be addressed through randomization

Internal Validity:

-refers to the confidence we have that the result of a study accurately depict whether one variable is or is not a cause of another.

-is a degree of confidence which we can claim causality

Pre-Experimental Designs (Passive Observation - Survey Research)

• One Short Case Study
• One Group Pretest-Posttest Design
• Static Group Comparison (Posttest Only Nonequivalent Group)

True-Experimental Designs (Randomized Experimental Designs)

• Pretest-Posttest Control Group
• Posttest Only Control Group
• Solomon Four-Group Design

Quasi- Experiential Designs

• Simple Time-Series Experiment Design
• Multiple Time Series Design
• Nonequivalent Control Group Design
• Participant Observation (Field Study, Ethnography)

History: anything that happens in between pretest and post test(more external), can influence the outcomes. Researcher collects gross sales data before and after a 5 day 50% off sales. During the sale hurricane occurs and result of the study may be affected because of the hurricane, not the sale.

Maturation: change in individual over time causes a gradual change (more internal). Subjects become tired after completing a training session, and their responses on the post test are affected.

Selection Bias: the groups being compared must truly be comparable. How are the participant selected? How is volunteering for the study?

Mortality: Drop outs, loss of participants. Loss of subjects from comparison group could greatly affect the comparison because of unique characteristics of those subjects.

Testing: participants become familiar with items (pre and Post)

Instrumentation: differences in the calibration of the measuring instrument.

Statistical Regression: Regression to the mean. Groups with extreme score

Ambiguity of direction of influence: when it is unknown whether X caused Y or Y caused X

Campbell & Stanley (1963). Experimental and quasi-experimental

designs for research.