MY552 Half Unit
Applied Regression Analysis
This information is for the 2012/13 session.
Dr Jouni Kuha and Professor Kenneth Benoit
Research students where programme regulations allow. Students are required to have completed MY451, MY551 or an equivalent level statistics course.
10 x two-hour lectures and nine x one-hour computer classes. Weekly assignments are required. This course is given twice per session, starting in the second week of each of the MT and LT. Students must either register for MY552M which is taught in Michaelmas Term, or MY552L which is taught in Lent Term.
The course is designed for students with a good working knowledge of elementary descriptive statistics; sampling distributions; one and two sample tests for means and proportions; correlation and the least squares regression model with one or more predictor variables. The course is concerned with deepening the understanding of the generalized linear model and its application to social science data. The main topics covered are linear regression modelling and binary, multinomial and ordinal logistic regression. Class exercises and homework will be carried out using the Stata or SPSS package, according to the student's choice.
A Agresti & B Finlay, Statistical Methods for the Social Sciences; M Lewis-Beck, Applied Regression: An Introduction; J Aldrich & F D Nelson, Linear Probability, Logit, and Probit Models. A course pack will be provided at the beginning of the course and additional reading will be recommended.
A two-hour open book unseen examination in ST.