This module will develop students' understanding of quantitative analysis and impart the practical skills necessary for carrying out advanced statistical analysis of social data using modern statistical software.
The first term of the module begins with simple OLS regression and provides a framework for modelling strategy and variable selection. Students are then taken through extensions to the basic OLS model, with categorical predictors, interactions and non-linear terms. Next, we introduce models for categorical outcomes: binary logistic and multinomial logit. The term concludes with a discussion of practical topics in data analysis - how to deal with complex sample designs, weighting and non-response adjustments.
The second part of the module introduces students to principles of measurement and provides statistical methods for realising empirical measurement models. The first lectures cover basic classical test theory, concepts of reliability and validity, and demonstrate simple methods for developing scales and indexes to measure sociological phenomena. Latent variable models are introduced in the form of exploratory factor analysis, and then the focus switches to confirmatory factor analysis models. At this point students are introduced to the SPSS AMOS structural equation modelling software. The module concludes by integrating general linear models with measurement models in the form of full structural equation modelling. This brings together in one statistical framework the principles and techniques learned throughout the year.
Learning outcomes
By the end of course students should be able to:
The first term of the module begins with simple OLS regression and provides a framework for modelling strategy and variable selection. Students are then taken through extensions to the basic OLS model, with categorical predictors, interactions and non-linear terms. Next, we introduce models for categorical outcomes: binary logistic and multinomial logit. The term concludes with a discussion of practical topics in data analysis - how to deal with complex sample designs, weighting and non-response adjustments.
The second part of the module introduces students to principles of measurement and provides statistical methods for realising empirical measurement models. The first lectures cover basic classical test theory, concepts of reliability and validity, and demonstrate simple methods for developing scales and indexes to measure sociological phenomena. Latent variable models are introduced in the form of exploratory factor analysis, and then the focus switches to confirmatory factor analysis models. At this point students are introduced to the SPSS AMOS structural equation modelling software. The module concludes by integrating general linear models with measurement models in the form of full structural equation modelling. This brings together in one statistical framework the principles and techniques learned throughout the year.
Learning outcomes
By the end of course students should be able to:
- understand the principles and practice of statistical modelling
- critically evaluate research articles that use statistics
- understand the link between substantive theory, measurement and statistical models
- carry out intermediate and advanced statistical analysis using SPSS and AMOS S
- Module Supervisor: Nick Allum