Authorised by Academic Registrar, April 1996
Objectives On completion of this subject students should understand the situations in which the linear regression model is not an appropriate way to model the behaviour of interest; be familiar with a range of alternative models which may be used in such situations; have an understanding of the practical skills required to model data as recorded in either surveys or panels.
Synopsis This subject considers the specification, estimation and evaluation of statistical models for a variety of situations in economics, finance and marketing, where the linear regression model is inappropriate. These include the modelling of discrete data on individual choice behaviour, censored and truncated data and panel data. The models are illustrated by considering examples from the economics and marketing literature. Students will make use of the software package LIMDEP to gain practical experience in the application of these models.
Assessment Written (one assignment [computing and report]): 40% + Examination (3 hours): 60%