PhD Project

Expert Knowledge in Latent Growth Curve Models

My PhD project focusses on providing a solution to small data problems in latent growth curve models. With few data points, it can be impossible to estimate the model of interest. Yet asking a different (simplified) question the data can answer may not be desirable. The PhD project aims to elicit information from for instance, experts-by-experience, researchers and clinicians. The elicited information from the experts can be used as prior information in a Bayesian analysis. By incorporating this prior knowledge in the analysis, a model of interest can be fitted to provide an answer to the original research question. The PhD project is part of a larger research group, more on which can be found on the website of my supervisor Rens van de Schoot.

A Five-Step Method to Elicit Expert Judgement

Duco Veen, Diederick Stoel, Mariëlle Zondervan-Zijnenburg & Rens van de Schoot

In this project we developed a Five-Step elicitation procedure. The software that we developed for this elicitation procedure can be found under the Featured Work section. The paper is currently submitted for publication. 

Using the Data Agreement Criterion to Rank Experts' Beliefs

Duco Veen, Diederick Stoel, Naomi Schalken & Rens van de Schoot

In this project we ranked experts based on prediction they had provided in the form of probability distributions. By letting experts specify their beliefs in the form of a probability distribution we can evaluate both their tacit knowledge and their uncertainty. This paper is currently submitted for publication. A pre-publication on the arXiv website can be found here.

Current Projects

Duco Veen

PhD Candidate - Utrecht University