Kyle Hickman, Ph.D.

Research Interests

My research interests lie in the propagation of uncertainty through large-scale stochastic simulations. In the context of disease models this involves finding efficient methods to calculate probabilities of events in an epidemic simulation while accounting for uncertainty in the defining parameters of the model. Techniques I have applied in this aspect are Bayesian Gaussian process regression, quasi-random sampling methods, and non-intrusive spectral projection.

This research also relates to the inverse problem of model parameter identification using epidemic data. Parameter identification in this context must allow for imprecision of the model and uncertainty in the collected data. Estimates for parameters will then be in the form of probability distributions that describe the extent to which the data determines the parameter.