Econometrica: Mar 1974, Volume 42, Issue 2
Bounds on the Variance of Regression Coefficients Due to Heteroscedastic or Autoregressive Errors
H. D. Vinod, S. T. SatheIn applications of linear regression analysis, the unknown error covariance matrix has to be somehow estimated. This can lead to biased estimates of the covariance matrix of the regression coefficients. Since such bias is difficult to eliminate completely, its sensitivity to alternatives estimates of error covariances is studies by Watson, Theil, Malinvaud, and others with the help of bounds on the bias derived under certain assumptions. This paper gives similar bounds under less restrictive assumptions, and illustrates them context of heteroscedasticity and autocorrelation problems. In particular, for the first order error autocorrelation coefficient of @r the upper bound on proportionate bias is shown to be reasonably approximated by (1 + pr)/(1 - @r) - 1.
Log In To View Full Content