Methods for behavioural economics & psychology research

We use our expertise to share measures and analysis code employed by our team that cut across economics and psychology disciplines. We host a repository on how-to guides on measurements, as well as analysis code tips from CSAE's Coder's Corner series, and a glossary of behavioural and psychological constructs we measure in our research. 

Welcome to our Measures Matter series!

How can you measure a person's beliefs? What about their risk attitudes? What methods could we use to minimise reporting bias?

In our Measures Matter series, we unpack measurement tools used to study psychology and behaviour in research evaluations. The goal of the series is to share knowledge from our research and learnings from our experiences in the field with researchers interested in behavioural economics, psychology and psychiatry. We provide step-by-step instructions on how to replicate or build on our measurement approaches.

Behavioural researcher in need of coding tips?

The Centre for the Study of African Economies runs a popular Coder's Corner series providing advice on managing data and code used in analysis. Below are links to a few of their posts which might be particularly useful for researchers in behavioural economics, psychology and psychiatry.

Methods matter NCS graphic (1)
Generic Machine Learning for Heterogeneous Treatment Effects

The interests of researchers and policymakers often extend beyond a simple average treatment effect when evaluating interventions in randomised experiments. Exploring heterogeneous treatment effects, or average treatment effects by subgroups and covariates, can provide useful answers to a variety of important questions. This post explores using machine learning methods for inference on heterogeneous treatment effects. 

Methods matter NCS graphic (1)
Endogenous Stratification

When we analyse the results of an experiment, we are often interested in understanding what the treatment effects are on sub-groups. This type of sub-group analysis is usually estimated using in-sample information on the relationship between the outcome of interest and the covariates in the control group to predict outcome for all groups without treatment. However, this procedure generates substantial bias due to overfitting. This post discusses a method for overmining this bias.

Methods matter NCS graphic (1)
Regularisation in Stata

Including control variables in regressions can substantially increase the statistical power of your analysis. However, deciding which control variables to select is arbitrary. Pre-analysis plans allow researchers to credibly commit to a set of controls, yet these controls might turn out to be suboptimal ex-post. Regularisation techniques deal with this problem and ensure that you make the most of your existing data.