The representativeness heuristic: is it really a misconception of probability?

Kasonga, R. A.

The reasoning behind the theory of testing of hypothesis is that if a sample does not resemble the characteristics of the population specified by the null hypothesis, then the null hypothesis is rejected. In this paper I draw a parallel between this reasoning and the 'representativeness heuristic.' I claim that the widely accepted view that this heuristic is a misconception in probability is a result of mixing-up the concepts of likelihood and probability on the part of statistics education researchers. While the concept of likelihood is very intuitive and comes naturally to people, the concept of probability is abstract and normally requires formal training.

The CAUSE Research Group is supported in part by a member initiative grant from the American Statistical Association’s Section on Statistics and Data Science Education