Breadcrumb
Functional ANOVA
Supervisor: Li Chen
Theme: Bayesian Modelling & Analysis
Analysis of Variance (ANOVA) is an extremely important method in exploratory and confirmatory data analysis. Functional ANOVA decomposes a functional response into the main effects and interactions of various factors. This project will develop a general Bayesian framework for functional ANOVA using Gaussian priors and Markov Chain Monte Carlo algorithms. This method is also applicable to numerical model evaluation. More insights about the numerical model uncertainty will be gained by decomposing the total variance into components depending on space and time. We will illustrate this method with application to environmental data sets.