Policy impact estimation

IFS is involved in assessing the effectiveness of a number of labour market programmes, tax and transfer programmes and social programmes in a variety of fields, from education and training, to labour supply, childcare, health and welfare. Determining whether such policy interventions work and whether their cost is justified is of crucial importance in the presence of limited public resources, and allows policy decisions to be guided by evidence on programme effectiveness.

Estimating the causal impact of a programme is difficult because one can never observe the outcome that programme participants would have experienced had they not participated. Constructing this unobserved counterfactual for programme participants is the central issue that evaluation methods need to overcome. In addition to the evaluation of specific government interventions, our research contributes to the development of econometric and statistical methods to address the evaluation problem.

Information redundancy neglect versus overconfidence: a social learning experiment

| Working Paper

We study social learning in a continuous action space experiment.

Find out more

Binarization for panel models with fixed effects

| Working Paper

In nonlinear panel models with fixed effects and fixed-T, the incidental parameter problem poses identification difficulties for structural parameters and partial effects. Existing solutions are model-specific, likelihood-based, impose time homogeneity, or restrict the distribution of unobserved heterogeneity. We provide new identification results for the large class of Fixed Effects Linear Transformation (FELT) models with unknown, time-varying, weakly monotone transformation functions.

Find out more

Semiparametric efficient empirical higher order influence function estimators

| Working Paper

Robins et al. (2008, 2016b) applied the theory of higher order infuence functions (HOIFs) to derive an estimator of the mean of an outcome Y in a missing data model with Y missing at random conditional on a vector X of continuous covariates; their estimator, in contrast to previous estimators, is semiparametric efficient under minimal conditions. However the Robins et al. (2008, 2016b) estimator depends on a non-parametric estimate of the density of X. In this paper, we introduce a new HOIF estimator that has the same asymptotic properties as their estimator but does not require non-parametric estimation of a multivariate density, which is important because accurate estimation of a high dimensional density is not feasible at the moderate sample sizes often encountered in applications. We also show that our estimator can be generalized to the entire class of functionals considered by Robins et al. (2008) which include the average effect of a treatment on a response Y when a vector X suffices to control confounding and the expected conditional variance of a response Y given a vector X.

Find out more