Abstract

In continuous norming, (psychological) test scores are typically estimated in relation to predictor variables (e.g., age). To estimate this relationship properly, large normative samples may be needed. In this talk, we will discuss to what extent this burden can be alleviated by using prior information in the estimation of new norms. In a simulation study, we investigated using Bayesian Gaussian distributional regression to what extent this norm estimation is more efficient and how robust it is to prior model deviations. We varied the prior type, prior misspecification, and sample size. In the simulated conditions, using a fixed effects prior resulted in more efficient norm estimation than a weakly informative prior as long as the prior misspecification was not age dependent. With the proposed method and reasonable prior information, the same norm precision can be achieved with a smaller normative sample, at least in empirical problems similar to the simulated conditions. This may help test developers to achieve cost-efficient high-quality norms. We illustrate the method using empirical normative data from the IDS-2 intelligence test, and we discuss the general implications of this proof of concept for using prior norm information.