摘要：Hierarchical Bayes models provide a natural way of incorporating
covariate information into the inferential process through the elaboration of re-
gression equations for one or more of the model parameters, with errors that are
often assumed to be i.i.d. Gaussian. Unfortunately, building adequate regression
models is a complicated art form that requires the practitioner to make numerous
decisions along the way. Assessing the validity of the modeling decisions is often
dicult.
In this article I develop a simple and e
ective device for ascertaining the quality
of the modeling choices and detecting lack-of- t. I specify an arti cial autoregres-
sive structure (AAR) in the probability model for the errors that incorporates
the i.i.d. model as a special case. Lack-of- t can be detected by examining the
posterior distribution of AAR parameters. In general, posterior distributions that
assign considerable mass to a region of the AAR parameter space away from zero
provide evidence that apparent dependencies in the errors are compensating for
misspeci cations of some other aspects (typically conditional means) of the model.
I illustrate the methodology through several examples including its application to
the analysis of data on brain and body weights of mammalian species and response
time data.
关键词：Allometry, Asymptotic normality, Autocorrelation, Hierarchical mod-
els, Response times
