The social is made up of categories. Age, gender, ethnicity, citizenship, social class, political affiliation, partnership status, educational level, grade on a exam, occupational level, happiness level, city area, you name it! Our lives are sequences of social categories that are as much the product of our choices, as an imposition from outside; the result of contextual and historical processes embodied in our ability to perceive and choose. The study of categorical data of this kind has a long standing tradition in statistics. This course offers an introduction to data analysis methods for the study of the social through the categorical lens. It will make use of R, a free software environment for statistical analysis and graphics to introduce methods used in the study of categorical data. Some of the topics that will be covered by this course involve:
1. Introduction to using R: functions and packages for categorical data (e.g. data cleaning and management)
2. What is a categorical variable? Latent versus observed variables
3. Uni-dimensional measures of association
4. Multivariate methods: the general linear regression model and friends
5. Ordinal data is everywhere
6. Prediction problems: supervised and unsupervised context
7. Summarizing results: statistics and in Tables or in Figures (plots with ggplot2) |