Silvestrini, AndreaMoulin, LaurentSalto, MatteoVeredas, David2017-12-022017-12-02200810.2139/ssrn.795327http://hdl.handle.net/20.500.12127/5245This paper presents and evaluates a new approach, temporal aggregation of models, to forecast annual budget deficits using montly information. Using French monthly data on central government revenues and expenditures, the method we propose consists of: 1) estimating monthly ARIMA models for all items of central government revenues and expenditures; 2)inferring the annual ARIMA models from the monthly models; 3) using the inferred annual ARIMA models to perform one-step-ahead forecasts for each item; 4) compounding the annual forecasts of all revenues and expenditures to obtain an annual budget deficit forecast. The major empirical benefit of this technique is that as soon as new monthly data becomes available, annual deficit forecasts are updated. This allows us to detect in advance possible slippages in central government finances. For years 2002, 2003 and 2004, forecasts obtained following the proposed approach are compared with a benchmark method and with official predictions published by the French government. An evaluation of their relative performance is provided.enAccounting & FinanceEmpirical Economics1924991925001924981818746494