Although conceptually straightforward, model averaging is rarely used in applied research, possibly due to the lack of easily accessible software. These drawbacks can be overcome by model averaging, a technique that retains all models for inference, weighting each model’s contribution by its posterior probability. However, such second-stage inference ignores the model uncertainty from the first stage, resulting in overconfident parameter estimates that generalize poorly.
In the first stage, a single ‘best’ model is defined by a specific selection of relevant predictors in the second stage, the regression coefficients of the winning model are used for prediction and for inference concerning the importance of the predictors. Linear regression analyses commonly involve two consecutive stages of statistical inquiry.
