Bayesian Matrix Factor Models for Demographic Analysis across Age and Time

Gregor Zens , IIASA

Analyzing demographic data collected across multiple populations, time periods, and age groups is challenging due to the interplay of high dimensionality, demographic heterogeneity among groups, and stochastic variability within smaller groups. This paper proposes a Bayesian matrix factor model to address these challenges. By factorizing count data matrices as the product of low-dimensional latent age and time factors, the model achieves a parsimonious representation that mitigates overfitting and remains computationally feasible even when hundreds of subpopulations are involved. Smoothness in age factors and a dynamic evolution of time factors are achieved through informative priors, and a Markov chain Monte Carlo algorithm is developed for posterior inference. Applying the model to Austrian district-level emigration data from 2002 to 2023 demonstrates its ability to reconstruct demographic processes using only a fraction of the parameters required by conventional demographic models. Extensive cross-validation and out-of-sample forecasting exercises show that the proposed matrix factor model consistently outperforms standard demographic benchmarks.

See extended abstract

 Presented in Session 2. Bayesian Demographic Modeling