MathHealth Short Course
In person: Seminar Room, Buiding VII, NOVA FCT
11th December, 14:00-17:00
12th December, 14:00-17:00
14th December, 14:00-16:00
Registration is mandatory.
Please register at https://forms.gle/
Title: An Introduction to Bayesian Nonparametric Methods with Applications in Biostatistics
Speaker: Vanda Inácio, School of Mathematics, University of Edinburgh, Scotland
Abstract: Bayesian methods play a key role in modern statistical modelling. The main aim of Bayesian nonparametric methods is to avoid dependence on critical parametric assumptions, thus robustifying parametric models, and also to provide a sensitivity analysis for such models by embedding them in a broader nonparametric model. This course introduces Bayesian nonparametric methods, and particular emphasis will be placed on models based on Dirichlet processes and Polya trees, with a view towards applications and software implementation. Special attention will be given to density estimation and regression, along with application in biostatistics.
- Review of Bayesian parametric statistics and sampling methods.
- Models for density estimation based on finite mixtures, Dirichlet process mixtures and mixtures of finite Polya trees.
- Models for density regression based on dependent Dirichlet process mixtures and dependent tailfree processes.
- Biostatistical applications, with a particular focus on evaluating the accuracy of biomarkers, and software implementation.
Intermediate knowledge of statistical inference, regression techniques, and of the R programming language.
Vanda Inacio is Reader in Statistics at the School of Mathematics of the University of Edinburgh since 2016. Previously, she was an Assistant Professor at PUC Chile (2012–2016). Vanda received a PhD in Statistics from Universidade de Lisboa and a BSc in Applied Mathematics from Universidade Nova de Lisboa. Her main research interests are Bayesian (nonparametric) statistics, computational statistics, and biostatistics, with an emphasis on the statistical evaluation of medical tests. Vanda’s work has been published in some of the top-tier journals in the field, like Annals of Applied Statistics, Bayesian Analysis, Biostatistics, Biometrics, Statistics in Medicine, Statistical Science, and The American Statistician. Vanda is also a co-author of the R package ROCnReg, the only package integrating both frequentist and Bayesian methods for estimation of ROC curves (with and without covariates).