Wednesday, November 16, 2011 - 15:00
1.5 hours (actually 80 minutes)
Advisor: Liang Peng
In 1988, Owen introduced empirical likelihood as a nonparametric method for constructing confidence intervals and regions. It is well known that empirical likelihood has several attractive advantages comparing to its competitors such as bootstrap: determining the shape of confidence regions automatically; straightforwardly incorporating side information expressed through constraints; being Bartlett correctable. In this talk, I will discuss some extensions of the empirical likelihood method to several interesting and important statistical inference situations including: the smoothed jackknife empirical likelihood method for the receiver operating characteristic (ROC) curve, the smoothed empirical likelihood method for the conditional Value-at-Risk with the volatility model being an ARCH/GARCH model and a nonparametric regression respectively. Then, I will propose a method for testing nested stochastic models with discrete and dependent observations.