Weighted-average least squares: Beyond the classical linear regression model

Abstract

Abstract

In this article, we introduce four new commands for the weighted- average least-squares approach to model uncertainty. The hetwals command fits linear models with multiplicative forms of heteroskedasticity; the arlwals command fits linear models with stationary first-order autoregressive errors; the xtwals command fits fixed-effects and random-effects panel-data models with either independent and identically distributed or first-order autoregressive idiosyncratic errors; and the glmwals command fits univariate generalized linear models. These commands extend the new functionalities of the wals command (version 3.0), introduced by De Luca and Magnus (2025, Stata Journal 25: 587-626), and enlarge the classes of models that can be fit by this model-averaging method. We also illustrate the hetwals and glmwals commands via real-data applications.