Evaluating state revenue forecasting under a flexible loss function

This paper examines the accuracy of state revenue forecasting under a flexible loss function. Previous research has focused on whether a forecast is rational, meaning that the forecasts are unbiased and the actual forecast errors are uncorrelated with information available at the time of the forecast. These traditional tests assumed that the forecast loss function is quadratic and symmetric. The literature has found that budget forecasts often under-predict revenue and use the available information inefficiently. Using Californian data, I reach the same conclusion using similar tests. However, the rejection of forecast rationality might be the result of an asymmetric loss function. Once the asymmetry of the loss function is taken into account using a flexible loss function, I find evidence that under-forecasting is less costly than over-forecasting California’s revenues. I also find that the forecast errors that take this asymmetry into account are independent of information available at the time of the forecast. These results indicate that a failure to control for possible asymmetry in the loss function in previous work may have produced misleading results.