Ch7. Experimental, Quasi-Experimental, and Ex Post Facto Designs exam with 100% correct answers

Confounding Variable A variable that directly or indirectly correlates with both the dependent and the independent variables Strategies for controlling confounding variables 1. keep some things constant 2. include a control group 3. randomly assign people to groups 4. use one or more pre-tests to assess equivalence before treatment/experiment 5. expose participants to all experimental treatments 6. statistically control for confounding variables Types of experimental designs >Pre-Experimental Designs >True Experimental Designs >Quasi-Experimental Designs >Ex Post Facto Designs >Factorial Designs Pre-Experimental Design -the independent variable doesn't vary -experimental and control groups are not composed of equivalent or randomly selected individuals -not possible to show cause-and-effect relationship Examples: *Static Group Comparison *One-shot experimental case study True Experimental Design -groups are randomly assigned -presentation of different treatments Examples: *Within-subjects design *Solomon Four-group design Quasi-Experimental Design -randomness is not possible or practical -can't control all confounding variables Examples: *Multiple-Baseline design *Reversal time-series design Ex Post Facto Design -researcher identifies events that have already occurred -the variable _cause of the effect_ has already occurred Example: *Simple Ex Post Facto design Factorial Design -more independent variables in one study Example: *Two-factor experimental design Meta-Analyses A meta analysis is an analysis of the analyses of the researcher. The researcher combines the results of many experimental studies to determine whether they lead to consistent conclusions