Research Methods in MIS: Experimentation Dr. Deepak Khazanchi Acknowledgment: Some of the information in this presentation is Based on Cooper and Schindler (2000) and Sproull (1996).
Variables in Experiments Independent variables Treatment or experimental variable: The independent variable that is manipulated by the researcher so that different groups of subjects receive different kinds or amounts. Dependent variables
Advantages of an Experiment? Researcher’s ability to manipulate the independent variable Contamination from extraneous variables can be controlled more efficiently Convenience Cost Replication
Disadvantages of Experiments Artificiality of the laboratory Generalization from nonprobability samples Larger budgets needed Restricted to problems of the present or immediate future Ethical limits to manipulation of people
Experimentation Process Select relevant variables Specify the treatment levels Control the experimental environment Choose the experimental design Select and assign the subjects Pilot-test, revise, and test Analyze the data
Ways to Assign Subjects Random Assignment Matching Assignment Quota matrix
Does a Measure Accomplish What it Claims? Internal validity External validity
Threats to Internal Validity History Maturation Testing Instrumentation Selection Statistical Regression Experimental Mortality
Threats to External Validity The Reactivity of Testing on X Interaction of Selection and X Other Biasing Effects on X Artificial setting of testing Respondents knowledge of testing
Experimental Designs Preexperimental designs True experimental designs Field experiments
Design Symbols X the introduction of an experimental stimulus to the respondent 0 a measure or observation activity R an indication that sample units have been randomly assigned
Preexperimental Designs One-shot case study One-group pretest-posttest design Static group comparison
True Experimental Designs Pretest-posttest control group design Posttest-only control group design
Operational Extensions of True Designs Completely randomized designs Randomized block design Latin square Factorial design Covariance analysis
Field Experiments: Quasi- or Semi-Experiments Non Equivalent Control Group Design Separate Sample Pretest-Posttest Design Group Time Series Design