Stochastic volatility models are those in which the volatility of a stochastic process is itself randomly distributed. There are two random processes, one for observation, and one for the latent variables which controls specifically the volatility which is the degree of variation of a time series over time. Volatility is highly important for stocks in finance. Low volatility implies the stock will behave nearly deterministic. Large volatility means the stock price experience large spikes in pricing. In this project, Bayesian Analysis of the stochastic volatility model will be used to estimate the volatility of time series with Gibbs Sampler.

For details, please click for the poster

For details, please click for the report

For Gibbs implementation of volatility estimation, please click for the GitHub repository