PhD in Methodolgy and Statistics

PhD in Methodolgy and Statistics (23934)

Tilburg University | Tilburg School of Social and Behavioral Sciences

is looking for a PHD candidate

PhD candidate in Methodology & Statistics

Topic:
Dynamic Mixture Modeling for Intensive Longitudinal Data

Department:
Methodology and Statistics

Location:

Tilburg

Contract size: 1.0 fte (40 hours per week)

Contract duration: 12 months with a possible extension of 36 months.

Desired starting date:
September 2026

Do you want to contribute to the development of innovative statistical methods for intensive longitudinal data, such as experience sampling data? Tilburg University is looking for a motivated PhD candidate to advance methodological research on dynamic mixture models for intensive longitudinal data.

This PhD project focuses on methodological developments in dynamic mixture models for intensive longitudinal data. The project will be embedded within the Department of Methodology and Statistics and linked to the methods branch of the Tilburg Experience Sampling Center (TESC), an interdisciplinary research center focused on intensive longitudinal research.

The overarching aim of the project is to develop and extend statistical models that allow latent structures to evolve over time to better understand, predict, and measure complex within‑person processes. The precise methodological direction will partly depend on the interests and background of the PhD candidate. One possible research direction concerns how statistical models can adapt as new data become available, for example, by improving individualized prediction or updating latent‑state estimates in evolving data streams.

Another possible direction concerns adaptive and personalised measurement, where questionnaire content or measurement structures dynamically adapt based on estimated latent states. The project combines methodological innovation with substantive applications in intensive longitudinal research and experience sampling methodology. An important component of the project also involves the implementation of the newly developed methods in statistical software.

The Department of Methodology and Statistics and TESC foster an open and collaborative working culture, emphasizing intellectual exchange, teamwork, and methodological innovation. The project will be supervised by Dr. Leonie Vogelsmeier, Dr. Mihai Constantin, and Prof. Dr. Jeroen Vermunt.

• Your research work includes literature reviews, developing and extending statistical methods, analyzing empirical data, developing statistical software, and writing research reports.
• You will prepare scientific articles to be published in international journals, present key findings at national and international scientific conferences, and write a dissertation.
• You will actively participate in the Department of Methodology and Statistics and TESC.
• You will contribute to Open Science and Team Science.
• You will contribute to education and supervision (e.g., supervising bachelor’s theses and research skills groups, with roughly 10% of your time being devoted to such tasks).

Researchers increasingly use intensive longitudinal data, such as experience sampling data, to study psychological, behavioural, and social processes as they unfold over time in daily life. These data offer unique opportunities to investigate within‑person dynamics in, for example, emotions, behaviours, and cognition. At the same time, intensive longitudinal data pose substantial methodological challenges. Psychological and behavioural processes are often dynamic, heterogeneous, and context‑dependent.

Dynamic mixture models, including Latent Markov Models, provide a flexible framework for modelling such complex processes by unraveling unobserved clusters of occasions and/or individuals in a data‑driven manner. These models can contribute to improved personalised prediction, adaptive assessment, and a better understanding of individual differences in dynamic psychological and behavioural processes. This project aims to advance methodological developments in dynamic mixture modelling for intensive longitudinal data.

We are looking for a…