Experimental Design 264a Marketing Research
Criteria for Establishing a Causal Relationship Concomitant variation Temporal variation Control over other possible causal factors 264a Marketing Research
Concomitant Variation 264a Marketing Research
Concomitant Variation
264a Marketing Research Concomitant Variation
Temporal Ordering Causes must precede effects. 264a Marketing Research
Control over other possible causal factors Randomization: Randomly assign respondents to treatment conditions. Physical control: Hold possible extraneous factors constant. Design control: Experimental design. Statistical control: Analysis of covariance. 264a Marketing Research
Threats to Validity Internal to the experiment External -- The relation of the experiment to real life 264a Marketing Research
Internal Threats History: Events occurring simultaneously with the experiment Maturation: Biological and/or psychological changes in the respondents Testing: Measuring changes the objects measured. Instrumentation: The yardstick can change. Selection Bias: Improper assignment Mortality: Differential loss of respondents 264a Marketing Research
External Threats Reactive/Interactive Effects of Testing: Sensitizing respondents to the topic Interactive Effects of Selection Bias: Improper assignment to groups Surrogate Situations: The laboratory is not like the real world. 264a Marketing Research