Dr Benjamin Lauderdale COL.8.10

This course is available to all research students.

The course is also available to taught masters students with different assessment, as MY454.

Students must have taken Applied Regression Analysis (MY452) or an equivalent intermediate regression course.

This course will cover basic statistical programming for social science research as well as several associated data analysis methods. Programming topics include basic programming, data structures, optimisation, and simulation. Applied statistical topics include nonparametric density estimation and regression, additive models, cross-validation, the bootstrap, and permutation/randomisation inference. Lectures, class exercises and homework will be based on the use of the R statistical software package but will assume no background knowledge of that language.

20 hours of lectures and 10 hours of computer workshops in the LT. 2 hours of lectures in the ST.

Students will be expected to produce 5 problem sets in the LT.

Each problem set is associated with a computer classes, and may be submitted for marking and feedback.

Keele, L. Semiparametric Regression for the Social Sciences

Matloff, N. The Art of R Programming

Shalizi, CR. Advanced Data Analysis from an Elementary Point of View.

Coursework (100%) in the ST.

A single piece of coursework (100%) in the ST applying the methods covered in the course to a topic in the area of the student’s research.  The topic and scope of the assignment will be developed in discussion with the teacher responsible for the course during LT.