Econometrica: Jan 1978, Volume 46, Issue 1

Testing for Autocorrelation with Missing Observations<59:TFAWMO>2.0.CO;2-N
p. 59-67

Kenneth J. White, N. E. Savin

This paper considers procedures for testing for autocorrelation when there are missing observations on both the dependent and explanatory variables. These procedures include Durbin-Watson type tests given the vector of residuals, tests based on a set of uncorrelated residuals, and large sample likelihood ratio and Wald tests.

Log In To View Full Content