| Abstract: | ABSTRACT. This paper proposes a new method for estimating a monthly regional production model. The technique involves treating the region's monthly industrial output as a latent variable, which is in turn a function of capital (prosed by energy usage) and labor inputs. Annual observations on regional value added correspond to the summation of the unobservable monthly series over the 12 months, while changes in the national Industrial Production index help infer the series' month-to-month fluctuations. The model is estimated using the Kalman filter and the method of maximum likelihood. The estimates are used to compute monthly indices of regional value added for 15 individual 2-digit industries, and for the aggregate manufacturing sector in the Seventh Federal Reserve District. In a comparison of out-of-sample forecasting accuracy, the mixed-frequency model outperforms both the traditional parametric Cobb-Douglas and nonparametric Atlanta methods over the 1988–89 forecasting horizon. |
