A GMM estimator asymptotically more efficient than OLS and WLS in the presence of heteroskedasticity of unknown form

We propose a generalized method of moments (GMM) estimator, where our specific moment conditions, where our specific moment conditions ensure that the GMM estimator is asymptotically at least as efficient as ordinary least squares (OLS) and whatever competing weighted least squares (WLS) we wish to consider. With a popular exponential model of heteroskedasticity, our new GMM estimator performs significantly better than OLS or WLS. In an empirical application to a financial wealth equation, we show that the efficiency gains can be nontrivial with real data.