Hello
I'm a postdoctoral research fellow in statistics at Bordeaux Population Health, developing predictive models from longitudinal data using random forests and functional data methods. Previously, I worked on causal inference in London and Paris, and my PhD, defended in december 2019, focused on random changepoint models for cognitive ageing. Find my full resume here.
Research interests
- Mixed models for complex longitudinal data
- Sparse and irregular functional data analysis
- Dynamic prediction with machine learning
- Causal inference and missing data
Selected publications
- ✨ Segalas C, Helmer C, Genuer R, Proust-Lima C. Functional principal component analysis as an alternative to mixed-effect models for describing sparse repeated measures in presence of missing data, Statistics in Medicine, 2024.
- Segalas C, Leyrat C, Carpenter JR, Williamson E. Propensity score matching after multiple imputation when a confounder has missing data, Statistics in Medicine, 2023.
- Segalas C, Helmer C, Jacqmin-Gadda H. A curvilinear bivariate random changepoint model to assess temporal order of markers, Statistical Methods in Medical Research, 2020.
- Segalas C, Amieva H, Jacqmin-Gadda H. A hypothesis testing procedure for random changepoint mixed models, Statistics in Medicine, 2019.
Selected talks
- Dynamic random survival forests using functional principal component analysis for the prediction of survival outcomes from time-varying predictors, ISCB Conference, Thessaloniki, July 2024.
- Robustness to missing data: comparison between mixed-effects model and functional principal component analysis, French Biometrics Societies Conference, Toulouse, November 2023.
- Multiple imputation in propensity score matching: obtaining correct confidence intervals, ISCB Conference, Lyon, July 2021.
- Inference for random changepoint models: application to the pre-dementia cognitive decline, Daniel Schwartz PhD Award talk, Paris, October 2020.
- Inferential methods for random changepoint models, ISCB Conference, Leuven, July 2019.