•   •   •   •

Download the Paper (800 K, PDF file) - October 1, 2003 Tell a colleague about it. Printing Tips: Select 'print as image' in the Acrobat print dialog if you have trouble printing.

ABSTRACT:
Let f(y|x,z) (resp. f(y|x) be the conditional density of Y given (X,Z) (resp. X). We construct a class of `smoothed` empirical likelihood-based tests for the conditional independence hypothesis: Pr[f(Y|X,Z)=f(Y|X)]=1. We show that the test statistics are asymptotically normal under the null hypothesis and derive their asymptotic distributions under a sequence of local alternatives. The tests are shown to possess a weak optimality property in large samples. Simulation results suggest that the tests behave well in finite samples. Applications to some economic and financial time series indicate that our tests reveal some interesting nonlinear causal relations which the traditional linear Granger causality test fails to detect.

SUGGESTED CITATION:
Liangjun Su and Halbert White, "Testing Conditional Independence Via Empirical Likelihood" (October 1, 2003). Department of Economics, UCSD. Paper 2003-14.
http://repositories.cdlib.org/ucsdecon/2003-14