Sequential Variable Selection as Bayesian Pragmatism in Linear Factor Models

We examine a popular practitioner methodology used in the construction of linear factor models whereby particular factors are increased/decreased in relative importance within the model. This allows model builders to customise models and, as such, reflect those factors that the client/modeller may think important. We call this process Pragmatic Bayesianism (or prag-Bayes for short) and we provide analysis which shows when such a procedure is likely to be successful.