The estimation of gross regional product leading indicator by temporal dissaggregation method

Abstract

Introduction. Тhe estimation of gross regional product high-frequency leading indicator is relevant for the reliable analysis of current trends in regional economy and early understanding of its changes in the periods of high uncertainty since gross regional product is published on an annual basis. One approach to receive this indicator is a temporal disaggregation method, which has proven to be reasonable in foreign literature for disaggregating gross domestic product. At the same time, temporal disaggregation of regional economic time series has been understudied. Purpose. The purpose of the study is to refer to a temporal disaggregation method to estimate an unobservable indicator with high accuracy approximation for annual GRPs. Materials and Methods. The study analyzed Rosstat data for various periods, which characterize the economic growth in the Republic of Bashkortostan, as well as Bank of Russia data of enteprises’ monitoring. X-13ARIMA-SEATS methods for seasonal adjustment, temporal disaggregation methods (Chou–Lin, Fernandez and Litterman) and ARIMA for short-term forecast were used. Results. The article presents the results of temporal disaggregation of the gross regional product of the Republic of Bashkortostan. The best specification was estimated by the Chow–Lin method and includes indicators that characterize industrial production, retail trade, as well as enterprises’ survey data about the fluctuations in the ruble exchange rate. The ARIMA model gave a short-term forecast for a gross regional product leading monthly indicator. Unlike a random walk model with a forecast of up to 2-year lead time, a combination of temporal disaggregation method and ARIMA gave a better out-of-sample annual GRP forecast. Conclusion. The study successfully tested a temporal disaggregation method for the gross regional product of the Republic of Bashkortostan. In practice, this method provides reliable forecast estimates of the gross regional product for the current economic analysis with regard to available high-frequency data. It is shown that the use of survey data can improve the quality of gross regional product forecast.