Large-scale Factor Model Research Articles

Monetary, fiscal and oil shocks: Evidence based on mixed frequency structural FAVARs

Large scale factor models have been often adopted both for forecasting and to identify structural shocks and their transmission mechanism. Mixed frequency factor models have been also used in a reduced form context, but not for structural applications, and in this paper we close this gap. First, we adapt a simple technique developed in a small scale mixed frequency VAR and factor context to the large scale case, and compare the resulting model with existing alternatives. Second, using Monte Carlo experiments, we show that the finite sample properties of the mixed frequency factor model estimation procedure are quite good. Finally, to illustrate the method we present three empirical examples dealing with the effects of, respectively, monetary, oil, and fiscal shocks.

Keeping a Finger on the Pulse of the Economy: Nowcasting Swiss GDP in Real-Time Squared

This study evaluates forecasting performance of a large-scale factor model developed in Siliverstovs and Kholodilin (2012) in a genuine ex ante forecasting exercise. We perform our forecast of GDP growth in Switzerland in real time using real-time data vintages collected at weekly frequency. This allows us to monitor how newly released economic and financial data influence our forecasts and hence capture prevailing tendencies in current course of economic development.

How synchronized are new EU member states with the euro area? Evidence from a structural factor model

A high degree of cyclical synchronization between the new EU member states (NMS) from Central and Eastern Europe and the euro area is considered to be a prerequisite for successful enlargement of the European Monetary Union. In this paper, we establish stylized facts on economic linkages between NMS and the euro area using dynamic correlation and cohesion measures. Then, we identify the main structural common euro-area shocks and investigate their transmission to NMS by means of a large-scale factor model. Finally, we compare it to the propagation to current EMU members. Journal of Comparative Economics 34 (3) (2006) 538–563.

Common Stationary and Non-Stationary Factors in the Euro Area Analyzed in a Large-Scale Factor Model

In this paper we rely on techniques recently developed by Bai and Ng (2004a) to estimate common euro-area stationary and non-stationary factors using a large-scale dynamic factor model. We find that euro-area economies share four non-stationary factors or trends and one stationary factor. By means of rotation techniques, we estimate a euro-area business cycle which is a fairly good match to EuroCOIN, the euro-area coincident business cycle indicator published by the CEPR. Fluctuations of common euro-area factors mainly reflect variations of German and French real economic activity as well as of producer prices and financial prices (long-term interest rates and/or real effective exchange rates) in various countries. As concerns the transmission channels, macroeconomic shocks seem to proliferate in the euro area more strongly through trade, exchange rates and long-term interest rates than through stock prices. Among the external driving forces, shocks to US economic activity seem to be more strongly linked to shocks to the euro-area factors than oil price shocks. We finally find evidence of mild overall convergence; results for individual countries are mixed.

Common Stationary and Non-Stationary Factors in the Euro Area Analyzed in a Large-Scale Factor Model

In this paper we rely on techniques recently developed by Bai and Ng (2004a) to estimate common euro-area stationary and non-stationary factors using a large-scale dynamic factor model. We find that euro-area economies share four non-stationary factors or trends and one stationary factor. By means of rotation techniques, we estimate a euro-area business cycle which is a fairly good match to EuroCOIN, the euro-area coincident business cycle indicator

Estimating Large-Scale Factor Models for Economic Activity in Germany: Do They Outperform Simpler Models? / Die Schätzung von großen Faktormodellen für die deutsche Volkswirtschaft: Übertreffen sie einfachere Modelle?

Summary This paper discusses a large-scale factor model for the German economy, Following the recent literature, a data set of 121 time series is used to determine the factors by principal component analysis. The factors enter a linear dynamic model for German GDP. To evaluate its empirical properties, the model is compared with alternative univariate and multivariate models. These simpler models are based on regression techniques and considerably smaller data sets. Empirical forecast tests show that the large-scale factor model almost always encompasses its rivals. Moreover, out-of-sample forecasts of the large-scale factor model have smaller prediction errors than the forecasts of the alternative models. However, these advantages are not statistically significant, as a test for equal forecast accuracy shows. Therefore, the efficiency gains of using a large data set with this kind of factor models seem to be limited.