Philipp Gersing:
A Distributed Lag Approach to the Generalised Dynamic Factor Model

We propose a new estimator for the Generalised Dynamic Factor Model (GDFM) that simplifies estimation by avoiding frequency-domain methods. Our key theoretical insight shows that the dynamic common component can be represented by a finite number of lags of contemporaneously pervasive factors under general conditions. This result reduces GDFM estimation to a simple OLS regression of observed variables on estimated factors and their lags, with factors obtained via static principal components. The approach naturally accommodates weak (non-pervasive) factors within the dynamic common space, addressing an important limitation of existing methods. We establish consistency and asymptotic normality for both the dynamic and weak common components. An application to a large European macroeconomic dataset demonstrates strong empirical performance and uncovers a sizeable weak common component - particularly in sentiment indicators and several other variables - revealing dynamics that standard methods overlook.

Marléne Baumeister:
Multivariate and Multiple Contrast Testing in General Covariate-Adjusted Factorial Designs

Evaluating intervention effects on multiple outcomes is a central research goal in a wide range of quantitative sciences. It is thereby common to compare interventions among each other and with a control across several, potentially highly correlated, outcome variables. In this context, researchers are interested in identifying effects at both, the global level (across all outcome variables) and the local level (for specific variables). At the same time, potential confounding must be accounted for. This leads to the need for powerful multiple contrast testing procedures (MCTPs) capable of handling multivariate outcomes and covariates. Given this background, we propose an extension of MCTPs within a semiparametric MANCOVA framework that allows applicability beyond multivariate normality, homoscedasticity, or non-singular covariance structures. To realize this, we implement a generalized resampling-based method for the determination of critical values. We illustrate our approach by analysing multivariate psychological intervention data, evaluating joint physiological and psychological constructs such as heart rate variability.

Gregor Zens:
Advances in Bayesian Model Averaging for Latent Variable Regression

Latent variable models are widely used for Bayesian regression analysis with non-Gaussian outcomes. Bayesian variable selection and model averaging techniques offer principled frameworks for addressing model uncertainty in these settings. However, practical implementation is often hindered by intractable marginal likelihoods, exponentially growing model spaces, and computational bottlenecks within individual models. This talk discusses recent advances that help overcome these challenges. First, we establish a model averaging framework for a broad class of latent Gaussian models. We develop theoretical foundations - covering posterior existence and model selection consistency - and present a robust Markov chain Monte Carlo algorithm for exact probabilistic inference. Second, to make these methods scalable to large datasets, we introduce a novel approximation to marginal likelihoods based on variational inference, outlining its theoretical properties and practical implementation. Finally, we examine a computational shortcut that approximately preserves model selection behavior while substantially reducing runtimes in large-scale settings, often with negligible loss of accuracy. Throughout, we illustrate the practical benefits of the methods through simulations and a range of real-world applications.

This talk is based on joint work with Mark F. J. Steel (University of Warwick).