Quantifying Drivers of Forecasted Returns Using Approximate Dynamic Factor Models for Mixed-Frequency Panel Data

Abstract

This article considers the estimation of Approximate Dynamic Factor Models with homoscedastic, cross-sectionally correlated errors for incomplete panel data. In contrast to existing estimation approaches, the presented estimation method comprises two expectation-maximization algorithms and uses conditional factor moments in closed form. To determine the unknown factor dimension and autoregressive order, we propose a two-step information-based model selection criterion. The performance of our estimation procedure and the model selection criterion is investigated within a Monte Carlo study. Finally, we apply the Approximate Dynamic Factor Model to real-economy vintage data to support investment decisions and risk management. For this purpose, an autoregressive model with the estimated factor span of the mixed-frequency data as exogenous variables maps the behavior of weekly S&P500 log-returns. We detect the main drivers of the index development and define two dynamic trading strategies resulting from prediction intervals for the subsequent returns.

Explaining Aggregated Recovery Rates

“…The parameters θ := (A, W, D, Q) are unknown and need to be estimated. As in Defend et al (2021), we choose A (0) = 0 q×pq for an initial estimate of A and for an initial estimate of Q we choose Q (0) = I q . The initial values D (0) and W (0) are calculated according to a probabilistic principal component analysis (see Tipping and Bishop (1999)).…”