Paul Kabaila, Rheanna Mainzer, Davide Farchione
Abstract
We assess the impact of a Hausman pretest, applied to panel data, on a confidence interval for the slope, conditional on the observed values of the time-varying covariate. This assessment has the advantages that it (a) relates to the values of this covariate at hand, (b) is valid irrespective of how this covariate is generated, (c) uses finite sample results and (d) results in an assessment that is determined by the values of this covariate and only 2 unknown parameters. Our conditional analysis shows that the confidence interval constructed after a Hausman pretest should not be used.