Noriko Hashimoto

An exact test for linear restrictions in seemingly unrelated regressions with the same regressors

Abstract In this paper, we derive an exact test for linear restrictions on regression coefficients in seemingly unrelated regressions with the same regressors in each equation. The test statistic is distributed as the T 2 distribution, and thus critical values can be obtained from the F distribution. Since the test for symmetry in demand systems is a special case of the test for linear restrictions, our test gives an exact test for symmetry.

Small sample properties of modified Prais-Winston estimators in hypothesis testing in a linear model with ar(1) errors

Abstract This paper considers small sample properties of estimators for an autocorrelation coefficient ( p ) and of test statistics based on Prais-Winston (henceforth, P-W) estimators in a linear model with AR(1) errors. We propose two types of new modified P-W estimators (i.e., the bias-corrected P-W estimators) making use of the second-order approximation suggested by Ullah et al. (1983). It is shown by Monte Carlo experiments that one of the modified estimators performs remarkably better in hypothesis testing that the original P-W estimator especially in highly autocorrelated cases.