Professor Pedro Carneiro: all content

    Showing 1 – 20 of 77 results

    Publication graphic

    The long shadow of deprivation: Differences in opportunities across England

    Report

    A socially mobile country provides equal opportunities for everyone, across big cities and small towns, and regardless of whether your parents are rich or poor. This report makes use of newly linked administrative data on all state-educated pupils born between 1986 and 1988 to follow a group of sons from where they grew up, looking at their family circumstances and their educational achievement, through to the labour market.

    15 September 2020

    Working paper graphic

    Optimal Data Collection for Randomized Control Trials

    Working Paper

    In a randomized control trial, the precision of an average treatment effect estimator and the power of the corresponding t-test can be improved either by collecting data on additional individuals, or by collecting additional covariates that predict the outcome variable. To design the experiment, a researcher needs to solve this tradeoff subject to her budget constraint. We show that this optimization problem is equivalent to optimally predicting outcomes by the covariates, which in turn can be solved using existing machine learning techniques using pre-experimental data such as other similar studies, a census, or a household survey. In two empirical applications, we show that our procedure can lead to reductions of up to 58% in the costs of data collection, or improvements of the same magnitude in the precision of the treatment effect estimator.

    2 May 2019

    Working paper graphic

    Optimal data collection for randomized control trials

    Working Paper

    In a randomized control trial, the precision of an average treatment effect estimator and the power of the corresponding t-test can be improved either by collecting data on additional individuals, or by collecting additional covariates that predict the outcome variable. We propose the use of pre-experimental data such as other similar studies, a census, or a household survey, to inform the choice of both the sample size and the covariates to be collected.

    23 October 2017