When: Thursday 23rd November 2017, 13:00-14:00.
Included in meeting:
The fortnightly BRAG meeting will be held Thursday (23/11/2017) at 1 pm in the room Y801, GP.
This week we have presentations by Jagath and Insha
Insha’s talk: “Title: Dirichlet process mixture models
Dirichlet process Mixture Models (non-parametric Bayesian mixture models, infinite mixture models) are widely used to identify latent clusters in data. In this meeting, I will be presenting how to simulate data from a mixture model and then will try to model the simulated data using Dirichlet process Mixture Models. Everything is coded explicitly in R, so I will be demonstrating mainly R codes.
Jagath’s talk: “Title: How to fit a Copula model in R?
Copula models are multivariate distributions whose marginal distributions follow a standard uniform distribution. There are different families of Copulas, derived using Sklar’s theorem, which have been introduced in the literature. In this talk, I’ll be discussing the way of constructing multivariate distributions using Copula models. In particular, I will demonstrate how these models can be implemented in R using available R-packages such as copula and vinecopula packages.”
We look forward to seeing you all there!
Matt and Shovanur