This thesis uses hidden Markov models to analyze an asset pricing problem and to model the term structure of interest rates.;Chapter 1 reviews selected topics in mathematical finance. It discusses discrete-time and continuous-time models of financial markets and some models of interest rates.;Chapter 2 discusses hidden Markov models. In these models, a discrete-time, finite-state Markov chain is observed through a function whose values are distorted by noise.;In Chapter 3, a unit-delay model with a real-valued observation process is applied in three examples using IBM stock prices, gold prices, and United States-Canadian exchange rates.;In Chapter 4, a zero-delay model with a vector-valued observation process is applied in an analysis of the United States term structure of interest rates.;Two appendices give the computer programs written to implement the estimation procedures of Chapters 3 and 4. |