Factor-Midas for Now- and Forecasting with Ragged-Edge Data: A Model Comparison for German GDP

By Massimiliano Marcellino, Christian Schumacher. Social Science Research Network, 2010

333 citations recorded by the source corpus.

This paper compares different ways to estimate the current state of the economy using factor models that can handle unbalanced datasets. Due to the different release lags of business cycle indicators, data unbalancedness often emerges at the end of multivariate samples, which is sometimes referred to as the 'ragged edge' of the data. Using a large monthly dataset of the German economy, we compare the performance of different factor models in the presence of the ragged edge: static and dynamic principal components based on realigned data, the Expectation-Maximisation (EM) algorithm and the Kalman smoother in a state-space model context. The monthly factors are used to estimate current quarter GDP, called the 'nowcast', using different versions of what we call factor-based mixed-data sampling (Factor-MIDAS) approaches. We compare all possible combinations of factor estimation methods and Factor-MIDAS projections with respect to nowcast performance. Additionally, we compare the performance of the nowcast factor models with the performance of quarterly factor models based on time-aggregated and thus balanced data, which neglect the most timely observations of business cycle indicators at the end of the sample. Our empirical findings show that the factor estimation methods don't differ much with respect to nowcasting accuracy. Concerning the projections, the most parsimonious MIDAS projection performs best overall. Finally, quarterly models are in general outperformed by the nowcast factor models that can exploit ragged-edge data.

Subfields: Economics and Econometrics, Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/36c72e4b58ed4b60902bdbc92cda2a6b14aaf730

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Finance

In Statistics and Probability

Citations in the corpus

A Survey of Econometric Methods for Mixed-Frequency Data (2013, methodology): “Marcellino and Schumacher (2010) introduce Factor-MIDAS, an approach for now- and forecasting low-frequency variables exploiting information in large sets of higherfrequency indicators.”
High‐dimensional macroeconomic forecasting and variable selection via penalized regression (2019, methodology): “To investigate the forecasting performance of the penalized MIDAS regression model with a variety of horizons, we examine cases where h = 0, 1/3, 2/3, 1, 4/3, 5/3, 2 in the same manner as Clements and Galvao (2008) and Marcellino and Schumacher (2010).”
Short-Term GDP Forecasting With a Mixed-Frequency Dynamic Factor Model With Stochastic Volatility (2016, unknown): “…approach to short-term forecasting with mixed-frequency data is based on the MIDAS regressions introduced by Ghysels, Santa-Clara, and Valkanov (2004); see, for example, Clements and Galvão (2008), Foroni and Marcellino (2014), and Marcellino and Schumacher (2010) for macroeconomic applications.”
Macroeconomics and the Reality of Mixed Frequency Data (2016, background): “…Bernanke et al. (1997), Zadrozny (1990), Mariano and Murasawa (2003), Mittnik and Zadrozny (2004), and more recently Aruoba et al. (2009), Ghysels and Wright (2009), Kuzin et al. (2009), Marcellino and Schumacher (2010), Foroni and Marcellino (2014) and Schorfheide and Song (2013), among others.”
Unrestricted mixed data sampling (MIDAS): MIDAS regressions with unrestricted lag polynomials (2015, unknown): “Since the data set presents a ragged edge structure, to estimate the factor we adopt a procedure which combines principal component analysis and the EM algorithm, as outlined by Stock and Watson (2002); see also Marcellino and Schumacher (2010) for more details.”
Now-Casting and the Real-time Data Flow (2013, unknown): “There have been many other studies: for the United States (Lahiri and Monokroussos, 2011); for the aggregate euro area (Angelini, Bańbura, and Rünstler, 2010; Angelini, Camba-Méndez, Giannone, Reichlin, and Rünstler, 2011; Bańbura and Modugno, 2010; Bańbura and Rünstler, 2011; Camacho and Per”
Testing for Granger Causality in Large Mixed-Frequency VARs (2016, unknown): “Remark 9 Kilian (1998) and Paparoditis (1996) prove the asymptotic validity of the unrestricted VAR bootstrap under Assumption 2.”
Markov-Switching MIDAS Models (2013, background): “In particular, they extend the standard MIDAS model to include factors in a dynamic framework, along the lines of Marcellino and Schumacher (2010).”