STAT3004 Multivariate Data Analysis
This module will introduce some common methods for analysing data involving two or more variables per observation. In this respect, the module covers three topics: linear regression, logistic regression, and principal components analysis.
Aims and Objectives
• Demonstrate knowledge and understanding of the basic ideas behind several common statistical techniques for analysing multivariate data (linear regression analysis, logistic regression analysis and principal component analysis) • Analyse real data by applying these techniques using SPSS and interpret the resulting output • Write short statistical reports based on these analyses
Having successfully completed this module you will be able to:
- Demonstrate knowledge and understanding of the basic ideas behind several common statistical techniques for analysing multivariate data (linear regression analysis, logistic regression analysis and principal component analysis
- Analyse real data by applying these techniques using SPSS and interpret the resulting output
- Write short statistical reports based on these analyses
The module is split into three parts: Part 1: Linear regression: simple linear regression, least squares estimation, interpreting regression coefficients, checking the regression assumptions, hypothesis testing, confidence intervals, multiple linear regression, model selection, handling of categorical explanatory variables, interactions, variable transformations. Part 2: Logistic regression: modelling dichotomous outcome variables, probabilities and odds, the logistic regression model, how good is the model, model interpretation, model selection, diagnostic methods, grouped data. Part 3: Principal component analysis: definition, construction of principal components from the covariance matrix, principal components based on the correlation matrix, idea of dimension reduction, steps in a principal components analysis.
Learning and Teaching
|Total study time||150|
|Exam (2 hours)||70%|
Pre-requisites - Any equivalent modules can be accepted with permission from the Programme coordinator
To study this module, you will need to have studied the following module(s):
|STAT2009||Research Methods in The Social Sciences|