Professor Nicholas Biddle is Associate Director of the Australian National University (ANU) Centre for Social Research and Methods and Director of the newly created Policy Experiments Lab (http://csrm.cass.anu.edu.au/pelab). He has a Bachelor of Economics (Hons.) from the University of Sydney and a Master of Education from Monash University. He also has a PhD in Public Policy from the ANU where he wrote his thesis on the benefits of and participation in education of Indigenous Australians. He previously held a Senior Research Officer and Assistant Director position in the Methodology Division of the Australian Bureau of Statistics. He is currently a Fellow of the Tax and Transfer Policy Institute, a member of the National Data Advisory Council, and a member of the Behavioural Economics Team for Australia (BETA) Academic Advisory Panel

Course Content
Building on students’ knowledge in simple linear regression, this course introduces more advanced statistical techniques with a particular focus on drawing out policy insights. We will focus on the following topics:

1. Non-linear dependent variables and the generalized linear model;
2. Specification and interpretation of interactions and non-linear effects;
3. Using weights in regression analyses;
4. Causal inference from the analysis of experimental data (including intention to treat and average treatment effects);
5. Causal inference from quasi-experimental analysis (including difference-in-difference, instrumental variables, and regression discontinuity);
6. Introduction to panel data analysis, and the estimation of fixed and random effects models; and
7. Controlling for clustering when estimating parameters of interest (including robust standard errors).

For each topic, the course will be structured into four parts:

a) A theoretical introduction to each topic;
b) Examples from the literature;
c) Lab sessions in which students perform replications of published work in Economics and Political Science using STATA; and
d) Identification of future research ideas and the application to policy discussion

Students are encouraged to bring their own data sets and present their research projects and empirical analyses throughout the course.

Course Objectives
Upon successful completion of this course, students will be able to undertake relatively advanced and robust quantitative analysis that contributes to policy insights and advances theoretical knowledge. They will have the knowledge and skills to:

1. Identify the appropriate functional form and estimation technique for the data being used;
2. Precisely state the assumptions on which estimates are based;
3. Conduct sensible, robust inferences and interpret their estimates accurately; and
4. Utilise different types of data to control for unobserved heterogeneity for robust causal inference.

Course Prerequisites
This course is targeted at social and political scientists with a strong interest in applied empirical research and data analysis. Participants must be familiar with STATA and its command structure and be able to write their own do-files. R users are also welcome. The course is designed for students with basic training in statistics including linear regression and hypothesis testing. It is also essential that students have basic knowledge of matrix algebra, calculus, and probability theory to follow the lectures

Representative Background Reading
Kennedy, S., Kidd, M.P., McDonald, J.T. and Biddle, N., 2015. The healthy immigrant effect: patterns and evidence from four countries. Journal of International Migration and Integration, 16(2), pp.317-332.

Required texts
Angrist, J.D. and Pischke, J.S., 2014. Mastering ‘metrics: The path from cause to effect. Princeton University Press.

Background knowledge required
Statistics
OLS = elementary

Computer Background
Stata = moderate

Day 1 – Revision, introduction to the course, and Topic 1 (Non-linear dependent variables and the generalized linear model)

Day 2 – Topic 1 cont’d.

Day 3 – Topics 2 and 3 (Specification and interpretation of interactions and non-linear effects; Using weights in regression analyses)

Day 4 – Topic 4 (Causal inference from the analysis of experimental data (including intention to treat and average treatment effects);

Day 5 – Topic 4 cont’d

Day 6 – Topic 5 (Causal inference from quasi-experimental analysis)

Day 7 – Topic 5 cont’d; Topic 6 (Introduction to panel data analysis, and the estimation of fixed and random effects models)

Day 8 – Topic 6 cont’d

Day 9 – Topic 7 (Controlling for clustering when estimating parameters of interest)

Day 10 – Revision of course content, extensions

Each topic will follow a similar structure:

a. A theoretical introduction to each topic;
b. Examples from the literature;
c. Lab sessions in which students perform replications of published work in Economics and Political Science using STATA
d. Identification of future research ideas and the application to policy discussion