Dr Ganga Shreedhar

This course is compulsory on the MSc in Behavioural Science. This course is not available as an outside option.

The main aim is to familiarize students with the main statistical tools required to understand the myriad contextual and individual-level causes of human behaviour and to put students in a position to do their own research. The course will cover leading methods used by psychologists and economists to test behavioural science hypotheses about cause-effect questions. It will first introduce students to null hypothesis testing and regression analysis. It will then delve into quasi-experimental methods like differences-in-differences, regression discontinuity design and instrumental variables regression. Students will learn how to identify, interpret, and critically evaluate different research designs, to eventually conducting their own data analysis and writing a report of the same. They will keep abreast of contemporary methodological debates and best practices in data analysis in psychology and economics, apart from learning to critically appraise and navigate behavioural science studies from a methodological perspective. To this end, there will also be an emphasis on teaching students how the same analyses are presented in psychology and economics so students can understand how to integrate research from these two fields that constitute behavioural science. This course complements PB413: Experimental Design and Methods for the Behavioural Science, which covers experimental design and research for MSc Behavioural Science students.

The course is delivered in Michaelmas Term (MT) over 10 lectures of 1 hour and 10 weekly seminar sessions of 1 hour. Students on this course will have a reading week in MT Week 6. There will also be additional lab help sessions in collaboration with PB413.

Students will have to complete and submit weekly problem sets. Some of these will be marked to provide indicative assessment. All formative coursework is compulsory.

• Angrist, J.D. and Pischke, J.S., 2010. The credibility revolution in empirical economics: How better research design is taking the con out of econometrics. Journal of economic perspectives, 24(2), pp.3-30.
• Angrist, J.D. and Pischke, J.S., 2008. Mostly harmless econometrics: An empiricist's companion. Princeton university press.
• Wooldridge, Jeffrey M., 2015. Introductory Econometrics: A modern approach. Nelson Education.
• Gelman, A. & Hill, J., 2007. Data Analysis Using Regression and Multilevel/Hierarchical Models. Cambridge, UK: Cambridge University Press.
• Angrist, J.D. and Pischke, J.S., 2010. The credibility revolution in empirical economics: How better research design is taking the con out of econometrics. Journal of economic perspectives, 24(2), pp.3-30.
• Marinescu, I.E., Lawlor, P.N. and Kording, K.P., 2018. Quasi-experimental causality in neuroscience and behavioural research. Nature human behaviour, p.1.

Textbooks

• Stock, J.H. and Watson, M.W., 2015. Introduction to econometrics. Pearson Global Education.
• Angrist, J.D. and Pischke, J.S., 2014. Mastering metrics: The path from cause to effect. Princeton University Press.
• Firebaugh, G., 2018. Seven rules for social research. Princeton University Press.

Report (60%) and poster (20%) in the ST.
Problem sets (20%) in the MT.