MARK 302 Chapter Notes - Chapter 10: Root Mean Square, Complete Control, Extreme Behavior
24 Oct 2016
School
Department
Course
Professor
Document Summary
10) primary data collection: experimentation and test marketing. Experiment - research approach where one variable is manipulated and e(cid:125)ect on another variable is observed. Causal research - designed to determine whether a change in one variable likely caused an observed change in another: concomitant variation (correlation, appropriate time order of occurrence, elimination of other possible causal factors. Can never prove that x causes y but can infer that relationship exists. Causal relationships are always inferred and never demonstrated conclusively beyond shadow of doubt. Concomitant variation - statistical relationship between two variables. Appropriate time order of occurrence - change in independent variable occurring before observed change in dependent var. Most di(cid:126)cult thing to demonstrate in marketing experiments is that change in b wasn"t caused by some factor other than a. Laboratory experiment - conducted in controlled setting. Can deal with third element of proving causation and focus on (cid:128)rst two elements.
