Moment Condition Tests for Heavy-Tailed Time Series
37 Pages Posted: 30 Jun 2011 Last revised: 17 Oct 2011
Date Written: September 9, 2011
Abstract
We develop an asymptotically chi-squared statistic for testing moment conditions E[m(b0)] = 0, where m(b) may be weakly dependent, scalar components of m(b0) may have an infinite variance, and E[m(b)] need not exist for any b under the alternative. Score tests are a natural application, and in general a variety of tests can be heavy-tail robustified by our method, including white noise, GARCH affects, omitted variables, distribution, functional form, causation, volatility spillover and over-identification. The test statistic is derived from a tail-trimmed sample version of the moments evaluated at a consistent plug-in b_hat for b0. Depending on the test in question and heaviness of tails, b_hat may be any consistent estimator including sub-root-T-convergent and/or asymptotically non-Gaussian ones, since b_hat can be assured not to affect the test statistic asymptotically. We adapt bootstrap, p-value occupation time, and covariance determinant methods for selecting the trimming fractile in any sample, and apply our statistic to tests of white noise, omitted variables and volatility spillover. We find it obtains sharp empirical size and strong power, while conventional tests exhibit size distortions.
Keywords: moment condition test, heavy tails, tail trimming, robust inference
Suggested Citation: Suggested Citation
Do you have a job opening that you would like to promote on SSRN?
Recommended Papers
-
Heavy-Tail and Plug-In Robust Consistent Conditional Moment Tests of Functional Form
-
Robust Estimation and Inference for Heavy Tailed Nonlinear GARCH
-
Least Tail-Trimmed Squares for Infinite Variance Autoregressions
-
Robust Score and Portmanteau Tests of Volatility Spillover
By Mike Aguilar and Jonathan B. Hill
-
Measuring Tail Thickness Under GARCH and an Application to Extreme Exchange Rate Changes
By Terry Marsh and Niklas Wagner