This paper describes an empirical evaluation of a Bayesian procedure for equating scores on test forms taken by small numbers of examinees, using collateral information from the equating of other test forms. In this procedure, a separate Bayesian estimate is derived for the equated score at each raw-score level, making it unnecessary to specify a parametric model for the equating function. Collateral information can come either from other forms of the same test or, possibly, from other tests having a similar structure. Our evaluation consisted of two resampling studies. Each study applied the Bayesian procedure to small samples drawn from large-sample data collected for an anchor equating. The large-sample equating function served as the criterion. The results of the two studies were somewhat inconsistent, leading to different conclusions regarding the use of the empirical Bayesian procedure with small samples.