A Simulation Study of Effects of Multicollinearity and Autocorrelation on Estimates of Parameters

Abstract

In attempting to analytically discover or test economic relationships, econometricians have available many computational techniques by which to estimate the parameters of their models. But different solution methods may give unbiased and consistent, biased and consistent, or biased and inconsistent estimates under varying assumptions. The model builder is vitally interested in how each of these procedures reacts under varying conditions that may impinge on his model, but which are conditions not assumed by the estimation technique.