BEX5400 Statistical theory and practice

The objective of this unit is to outline the general principles that underlie advanced methods of statistical inference. Building on the maximum likelihood estimator (MLE), the unit provides a formal treatment of quasi-MLE, generalized method of moments (GMM), non-parametric methods and the bootstrap. The discussion is motivated by reference to econometric and statistical models and data, and simple practical examples with which you should be familiar. It is shown that these methods find application in many areas of econometrics and business statistics, and may be viewed as encompassing many familiar econometric and statistical techniques. Broad topic headings are: quasi-MLE, classical method of moments and regression (OLS and IV), GMM, identification, non-parametric methods, the bootstrap, asymptotic distribution theory and optimal inference. Simulation experiments are used to reinforce the theoretical derivations.