Monash University
Browse
wp2-10.pdf (389.86 kB)
Download file

A Quasi-locally Most powerful Test for Correlation in the conditional Variance of Positive Data

Download (389.86 kB)
journal contribution
posted on 2022-11-01, 04:11 authored by Brendan P.M. McCabe, Gael Martin, Keith Freeland
A test is derived for short-memory correlation in the conditional variance of strictly positive, skewed data. The test is quasi-locally most powerful (QLMP) under the assumption of conditionally gamma data. Analytical asymptotic relative efficiency calculations show that an alternative test, based on the first-order autocorrelation coefficient of the squared data, has negligible relative power to detect correlation in the conditional variance. Finite sample simulation results con.rm the poor performance of the squares-based test for fixed alternatives, as well as demonstrating the poor performance of the test based on the first-order autocorrelation coefficient of the raw (levels) data. Robustness of the QLMP test, both to misspecification of the conditional distribution and misspecification of the dynamics is also demonstrated using simulation. The test is illustrated using financial trade durations data.

History

Classification-JEL

C12, C16, C22

Creation date

2010-02-09

Working Paper Series Number

2/10

Length

26 pages

File-Format

application/pdf

Handle

RePEc:msh:ebswps:2010-2