We are a group of researchers working on discrete latent variable models tailored to analyze longitudinal data. We focus mainly on models formulated through a Markov chain latent process or similar latent processes. These are of interest in many fields from the methodological and applicative point of view, even for causal inference.

Concerning the analysis of longitudinal data, latent Markov and related models allow us to:

• account for unobserved heterogeneity

• account for measurements errors

• summarize several outcomes observed at the same occasion into a single variable (e.g., quality of life), the evolution of which on time may be studied even depending on individual covariates

• provide dynamic model-based clustering

• In the following, we list:

  • researchers currently working on these models and their web pages;

  • some relevant articles, books, technical reports, and software in the field;

  • conferences and events that may be of interest for presenting papers in the field.

Please contact us by email to be added among researchers working on the field, list relevant papers, or advertise to international conferences and events and advice about research projects.

Researchers

Francesco Bartolucci Department of Economics, University of Perugia (IT), email: francesco.bartolucci@unipg.it

Silvia Pandolfi Department of Economics, University of Perugia (IT), email: silvia.pandolfi@unipg.it

Fulvia Pennoni Department of Statistics and Quantitative Methods, University of Milano-Bicocca (IT), email: fulvia.pennoni@unimib.it

Recent presentations

Pennoni, F., Bartolucci, F., Pandolfi, S. (2021). Variable selection in hidden Markov models with missing data. Book of Abstracts 14th International Conference of the ERCIM WG on Computational and Methodological Statistics, 15th International Conference on Computational and Financial Econometrics, King’s College London, 18-20 December, pp. 41- 42.