After reviewing the simulation performance of general-to-specific automatic regression model selection, as embodied in PcGets, we show how model selection can be non-distortionary: approximately unbiased selection estimates are derived, with reported standard errors close to the sampling...

We suggest an alternative use of disaggregate information to forecast the aggregate variable of interest, that is to include disaggregate information or disaggregate variables in the aggregate model as opposed to first forecasting the disaggregate variables separately and then aggregating those...