MARK 302 Study Guide - Final Guide: Design Of Experiments, Causal Inference, Internal Validity
8 Dec 2016
School
Department
Course
Professor
Document Summary
Chapter 10: primary data collection: experimentation and test marketing. Experiment: a research approach which one variable is manipulated and the effect on another variable is observed. Only type of research potential to demonstrate causation. Must be able to show 3 things: concomitant variation (correlation, appropriate time order of occurrence, elimination of other possible factors. Implies a probabilistic relationship: x can be a cause of y if the presence of x makes the occurrence of y more predictable, or more likely. Can never definitively prove that x causes y but only infer that a relationship exists. Concomitant variation: a statistical relationship between two variables. A and b must vary together in some predictable way. This might be a positive or an inverse (negative) relationship. Appropriate time order of occurrence: a change in an independent variable occurring before an observed change in the dependent variable.
