Almost unbiased variance estimation in simultaneous equation models

While a good deal of research in simultaneous equation models has been conducted to examine the small sample properties of coe¢ cient estimators there has not been a corresponding interest in the properties of esimators for the associated variances. In this paper we build on Kiviet and Phillips (2000) and explore the biases in variance estimators. This is done for the 2SLS and the MLIML estimators together with an estimator which is a combination of k-class estimators with k<1. The approximations to the bias are then used to develop less biased estimators whose properties are examined and compared in a number of simulation experiments. Also included are two bootstrap estimators one of which is found to perform especially well. [/vc_column_text][vc_empty_space height="20px"][dt_button link="https://www.dropbox.com/s/ga7s0wlzaq73s7x/SEM%20Bias%20in%20Variance2%20%284%29.pdf?dl=0" target_blank="true"]Baixar pdf[/dt_button][/vc_column][/vc_row]