Random effects panel data models with known heteroskedasticity

The paper introduces two estimators for the linear random effects panel data model with known heteroskedasticity. Examples where heteroskedasticity can be treated as given include panel regressions with averaged data, meta regressions and the linear probability model. While one estimator builds on the additive random effects assumption, the other, which is simpler to implement in standard software, assumes that the random effect is multiplied by the heteroskedastic standard deviation. Simulation results show that substantial efficiency gains can be realized with either of the two estimators, that they are robust against deviations from the assumed specification, and that the confidence interval coverage equals the nominal level if clustered standard errors are used. Efficiency gains are also evident in an illustrative meta-regression application estimating the effect of study design features on loss aversion coefficients.