Intermediate Quantitative Methods

Course Provider: Prof John Ermisch

Aims

The application of standard statistical models to social science data and their interpretation.

This course follows on from Statistical Methods in Michaelmas Term with the aim of developing a number of more advanced techniques that are particularly relevant to sociologists. It is primarily an “applied” course and emphasizes the application of standard statistical models to typical social science data. Most emphasis is placed on the correct and useful interpretation of parameter estimates rather than on the derivation of the models themselves. The statistical software used in the practical classes is Stata.

On successfully completing this course, students should have an appreciation of the advantages and pitfalls of different methods and experience of the practical use of the methods taught. To gain any benefit from this course, it is necessary to have demonstrated mastery of the material taught in the Statistical Methods course in Michaelmas Term. A poor or even average performance in that course should suggest to you that you are unprepared for this course.

Eight two-hour lectures (weeks 1–8) and four practical classes (weeks 5–8) in which students are introduced to and gain hands-on experience with software for estimating and testing the statistical models outlined in the lectures.

The course is assessed by a take home exam consisting of three research questions/problems. The candidates will analyze data using some of the methods covered and write a short report on two of the three questions. The exam will be made available at noon Monday 1st week of Trinity Term and the deadline for submission will be noon Monday 2nd week of Trinity Term.

The following texts are indicative, students will receive suggestions for readings in the lectures.

  • Joshua D. Angrist and Jorn-Steffen Pischke, Mostly Harmless Econometrics. Princeton University Press, 2009 [e-book, available from Bodleian through SOLO].
  • Carina Mood. (2010) Logistic Regression: Why We Cannot Do What We Think We Can Do, and What We Can Do About It, European Sociological Review 26 : 67–82.
  • Paul D. Allison, Fixed Effect Regression Models. Sage, 2009 [e-book, available from Bodleian through SOLO].
  • Charles N. Halaby, Panel models in sociological research: theory into practice, Annual Review of Sociology, 30:507-544, 2009.

Stata-related texts:

  • Long, J. Scott, & Freese, Jeremy. (2014). Regression Models for Categorical Dependent Variables Using Stata (3rd ed.). College Station, TX: Stata Press.
  • Rabe-Hesketh, Sophia, & Skrondal, Anders. (2012). Multilevel and Longitudinal Modeling Using Stata. Volume I: Continuous Responses (3rd ed.). College Station, TX: Stata Press.
  • Rabe-Hesketh, Sophia, & Skrondal, Anders. (2012). Multilevel and Longitudinal Modeling Using Stata. Volume II: Categorical Responses, Counts, and Survival (3rd ed.). College Station, TX: Stata Press.

Other useful reading:

  • Paul D. Allison (2004). Using panel data to estimate the effects of events, Sociological Methods and Research, 23(2):174-199.
  • Douglas C. Montgomery, Elizabeth A. Peck and G Geoffrey Vining. (2012). Introduction to Linear Regression Analysis. John Wiley & Sons [e-book, available from Bodleian through SOLO].
  • Richard Breen et. al. (2014). Correlations and Nonlinear Probability Models, Sociological Methods & Research 43: 571-605.
  • Mark L. Bryan and Stephen P. Jenkins. (2016). Multilevel Modelling of Country Effects: A Cautionary Tale. European Sociological Review, 32(1): 3–22.