My
research interests are many, however, the focus and central theme has been modeling the correlation between observations. I am particularly interested in Bayesian stochastic computation methods such as Markov chain Monte Carlo (MCMC) and sequential Monte Carlo (SMC).
In my masters thesis, I focused on modeling the correlation between observations of binary variables using the multivariate probit class of models.
In my PhD I will attempt to solve a more complex problem where the correlation extends through time and space and is dynamic (time-varying).
Some areas where my research is applicable include:
- Finance: Modeling the correlation between financial assets and stocks, while taking into account external variables is essential for many financial applications, such as asset pricing, optimal portfolio risk management and asset allocation.
- Marketing: Studying consumers choices between brands over time given certain demographic information (age, gender, etc.) is useful for market segmentation.
- Health Research: Modeling the evolving association of multiple health markers as a function of some external factor such as pollution. This can also be a function of time and space.