Small Sample Bias Due to Misspecification in the “Partial Adjustment” and “Adaptive Expectations” Models

Abstract

The “partial adjustment” and “adaptive expectations” models are simply special cases of a more general model. This fact has not been commonly recognized by investigators who have used one or the other of these two models in empirical economic research. An examination of the results of small sample experiments shows that the bias in the estimated regression coefficients and the estimated mean lag which occurs when either one of the models is fitted by least squares to data generated by the more general model is quite serious. Also it is found that the spread of the distribution of these estimates is very sensitive to this misspecification. The departures from normality of these distributions are notable for the smallest sample sizes examined, but perhaps less significant in view of the severity of the other problems noted.