A study of effect sizes in consumer behaviour experiments.

Abstract

An investigation was undertaken to empirically document effect sizes, which describes the magnitude or strength of a relationship among two or more variables, in consumer behaviour experiments reported in marketing journals from the period 1985 to 1995. Using omega-wquared, Pearson's r and Cohen's d as measures of effect size, the results of 269 experiments, yeilding a total of 1,399 experimental effects, were analysed for their proportion of explained variance.