Do Surveys Help in Macroeconomic Variables Disaggregation and Estimation?

This paper explores the potential of Business Survey data for the estimation and disaggregation of macroeconomic variables at higher frequency. We propose a multivariate approach which is an extension of the Stock and Watson (1991) dynamic factor model, considering more than one common factor and low-frequency cycles. The multivariate model is cast in State Space Form and the temporal aggregation constraint is converted into a problem of missing values. An application in real time for the value added of the Industry sector in the Euro area is presented.