Estimation of discretely sampled continuous diffusion processes with application to short-term interest rate models

摘要: Stochastic Differential Equations (SDE’s) are commonly found in most of the modern finance used today. In this dissertation we use SDE’s to model a random phenomenon known as short-term interest rate where explanatory power particular is largely dependent on description SDE real data. The challenge face that cases transition density functions these models unknown and therefore, need find reliable accurate alternative estimation techniques. dissertation, discuss estimating techniques for discretely sampled continuous diffusion processes do not require true function be known. Moreover, reader introduced following techniques: (i) time maximum likelihood estimation; (ii) discrete (iii) functions. We show through Monte Carlo simulation study parameter estimates obtained from provide good approximation density. also bias mean reversion can reduced by implementing jackknife reduction technique. Furthermore, data analysis carried out South-African indicate strongly single factor explain variability rate. This may possibility distinct jumps market. Therefore, leave with notion incorporating into framework.