Courses / Module

LINEAR MODELS

Module code: ST303
Credits: 5
Semester: 1
Department: MATHEMATICS AND STATISTICS
International:

	Overview
	Scatterplots and regression. The multiple regression model and its applications. Matrix notation, mean vectors and covariance matrices. Least-squares estimation. The multivariate normal distribution. Hypothesis testing and confidence intervals, prediction. Simple linear regression as a special case. Analysis of variance, R2, sequential sums of squares, general F-tests. Added variable plots. Model checking via testing for lack of fit and residual plots. Regression diagnostics: residuals, leverage, outliers, influence and Cook's Distance. Polynomials and factors in regression. Weighted least squares.

Overview

Scatterplots and regression. The multiple regression model and its applications. Matrix notation, mean vectors and covariance matrices. Least-squares estimation. The multivariate normal distribution. Hypothesis testing and confidence intervals, prediction. Simple linear regression as a special case. Analysis of variance, R2, sequential sums of squares, general F-tests. Added variable plots. Model checking via testing for lack of fit and residual plots. Regression diagnostics: residuals, leverage, outliers, influence and Cook's Distance. Polynomials and factors in regression. Weighted least squares.

	Learning Outcomes
	On successful completion of the module, students should be able to: Fit and interpret multiple regression models. Understand the theory of multiple regression. Assess model assumptions. Use model diagnostics.

Teaching & Learning methods

Assessment

	Autumn Supplementals/Resits
	Are supplemental/resit registrations permitted? Yes University scheduled written examination (Autumn): 120 minutes, On-campus

	Pre-Requisites
	(ST122/ST221 or ST361) and (MT216C/MT212A or MT243P). Equivalent modules would also suffice.

Timetable

Search form

Courses / Module

LINEAR MODELS

Semester 1

Semester 2