Title

Do We Reject Too Often? Small Sample Bias in Tests of Rational Expectations

Document Type

Discussion Paper

Publication Date

4-1-1985

CFDP Number

743

CFDP Pages

21

Abstract

We examine the small sample properties of tests of rational expectations models. We show using Monte Carlo experiments that these tests can be extremely biased toward rejection for sample sizes typical in applied research. These biases are important when the time series examined are highly autoregressive. We also show that these tests are even more biased with detrended data. We present correct small sample critical values for our canonical problem.

This document is currently not available here.

Share

COinS