WIVE

Image from CF_WIV paper

Statistical models are only focus at the estimation of the mean of a certain biomedical outcome. However, within-individual variability estimation (WIVE) can play a role in quantifying disease risk and progression. In longitudinal studies, WIV is related to the deviation from individual mean. Starting from mixed-effects scale-location models (MELSM), we have looked at strategies to dynamically evaluate WIV and include it into the classic statistical modelling for dynamic risk prediction. We have developed a multivariate Bayesian joint model with association based on WIV.

Biostatistics Longitudinal data MELSM Joint modelling Cystic fibrosis
Avatar
Marco Palma
Senior Research Fellow in Ophthalmic Biostatistics

Publications

(2025). Assessing the impact of variance heterogeneity and misspecification in mixed-effects location-scale models.

Code Project DOI

(2025). Bayesian shared parameter joint models for heterogeneous populations.

PDF Code Project DOI

(2025). Mendelian Randomization with longitudinal exposure data: simulation study and real data application.

Project DOI

(2025). A longitudinal study of the gender gap in school grades via flexible Bayesian Beta regression.

PDF Project DOI

(2025). A Bayesian location-scale joint model for time-to-event and multivariate longitudinal data with association based on within-individual variability.

PDF Code Project Video DOI

(2024). EPS6.09 Association of within-individual variability of FEV1 and BMI with mortality in women with cystic fibrosis: preliminary results from the UK Registry.

PDF Project DOI

(2024). Demographic factors associated with within-individual variability of lung function for adults with cystic fibrosis: A UK registry study.

PDF Code Project Video DOI