UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Using randomized experiments and structural models for 'scaling up': evidence from the PROGRESA evaluation

Attanasio, O.; Meghir, C.; Szekely, M.; (2003) Using randomized experiments and structural models for 'scaling up': evidence from the PROGRESA evaluation. (IFS Working Papers WP04/0). Institute for Fiscal Studies: London, UK. Green open access

[thumbnail of 14753.pdf]

Download (252kB)


The evaluation of welfare programs and more generally government or international organisms interventions is often posed as a one off question, in that evaluators ask whether a specific intervention achieves a specific objective in a specific situation. However,recently, the more general question of whether results from a given studies can be used to predict the effect of different interventions in,possibly,different contexts has received a considerable amount of attention. The usefulness of such an exercise, if successful, is obvious. The ability to extrapolate success stories and avoid failures in different situations would obviously be highly desirable. Unfortunately, a rigorous and successful extrapolation is extremely difficult. Perhaps such difficulties should not be unexpected,given the problems that often one encounters in establishing the effects of social programs in non experimental settings. In this paper we discuss at length the issues involved with the evaluation of social interventions and with the attempts at 'scaling them up'. In particular, we discuss the relative merits of non- parametric evaluation strategies that rely on (possibly experimental) exogenous variation to estimate the impact effects and of more structural approaches. The difference between the two approaches is particularly relevant when one comes to the issue of 'extrapolation' and 'scaling up'. In principle one could consider two types of extrapolation and scaling up. First, one might want to predict the effects of a program that is different from the one that was evaluated or the effect of changing some aspects of the program evaluated. Second, one might want to predict the effect of exporting an existing program from a population where its effects were evaluated (evaluation population) to a different population (implementation population). In what follow we focus on the latter problem and discuss the former only marginally. After considering extensively the conceptual and technical issues involved with this type of exercises, we apply the ideas we discuss to the results from the evaluation of PROGRESA , a large welfare program in Mexico, for which a randomized evaluation sample is available and has been extensively studied. In particular, we divide the seven Mexican states in which the evaluation was carried out in two groups and check to what extent the results in one group can be extrapolated to the other. The advantage of such a strategy is that one can compare the extrapolation results (based on a structural model) with the actual 'ex-post' evaluation that can be carried out either by simple comparison of means or by structural methods.

Type: Working / discussion paper
Title: Using randomized experiments and structural models for 'scaling up': evidence from the PROGRESA evaluation
Open access status: An open access version is available from UCL Discovery
Publisher version: http://www.ifs.org.uk/publications/2084
Language: English
UCL classification: UCL > Provost and Vice Provost Offices > UCL SLASH > Faculty of S&HS > Dept of Economics
URI: https://discovery.ucl.ac.uk/id/eprint/14753
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item