Markus Frölich

Finite-Sample Properties of Propensity-Score Matching and Weighting Estimators

The finite-sample properties of matching and weighting estimators, often used for estimating average treatment effects, are analyzed. Potential and feasible precision gains relative to pair matching are examined. Local linear matching (with and without trimming), k-nearest-neighbor matching, and particularly the weighting estimators performed worst. Ridge matching, on the other hand, leads to an approximately 25 smaller MSE than does pair matching. In addition, ridge matching is least sensitive to the design choice.The finite-sample properties of matching and weighting estimators, often used for estimating average treatment effects, are analyzed. Potential and feasible precision gains relative to pair matching are examined. Local linear matching (with and without trimming), k-nearest-neighbor matching, and particularly the weighting estimators performed worst. Ridge matching, on the other hand, leads to an approximately 25% smaller MSE than does pair matching. In addition, ridge matching is least sensitive to the design choice.

Unconditional Quantile Treatment Effects Under Endogeneity

This article develops estimators for unconditional quantile treatment effects when the treatment selection is endogenous. We use an instrumental variable (IV) to solve for the endogeneity of the binary treatment variable. Identification is based on a monotonicity assumption in the treatment choice equation and is achieved without any functional form restriction. We propose a weighting estimator that is extremely simple to implement. This estimator is root n consistent, asymptotically normally distributed, and its variance attains the semiparametric efficiency bound. We also show that including covariates in the estimation is not only necessary for consistency when the IV is itself confounded but also for efficiency when the instrument is valid unconditionally. An application of the suggested methods to the effects of fertility on the family income distribution illustrates their usefulness. Supplementary materials for this article are available online.

Non-parametric regression for binary dependent variables

Finite-sample properties of non-parametric regression for binary dependent variables are analyzed. Non parametric regression is generally considered as highly variable in small samples when the number of regressors is large. In binary choice models, however, it may be more reliable since its variance is bounded. The precision in estimating conditional means as well as marginal effects is investigated in settings with many explanatory variables (14 regressors) and small sample sizes (250 or 500 observations). The Klein-Spady estimator, Nadaraya-Watson regression and local linear regression often perform poorly in the simulations. Local likelihood logit regression, on the other hand, is 25 to 55% more precise than parametric regression in the Monte Carlo simulations. In an application to female labour supply, local logit finds heterogeneity in the effects of children on employment that is not detected by parametric or semiparametric estimation. (The semiparametric estimator actually leads to rather similar results as the parametric estimator.) Copyright Royal Economic Society 2006

A Caseworker Like Me – Does the Similarity between the Unemployed and Their Caseworkers Increase Job Placements?

This article examines whether the chances of job placements improve if the unemployed are counselled by caseworkers who belong to the same social group, defined by gender, age, education and nationality. Based on an unusually informative dataset, which links Swiss unemployed to their caseworkers, we find positive employment effects of about 3 percentage points if the caseworker and his unemployed client belong to the same social group. Coincidence in a single characteristic, e.g., same gender of caseworker and unemployed, does not lead to detectable effects on employment. These results, obtained by statistical matching methods, are confirmed by several robustness checks.

Targeting Labour Market Programmes - Results from a Randomized Experiment

SummaryWe evaluate a randomized experiment of a statistical support system developed to assist caseworkers in Swiss employment offices in choosing appropriate active labour market programmes for their unemployed clients. This statistical support system predicted the labour market outcome for each programme and thereby suggested an ‘optimal’ labour market programme for each unemployed person. The support system was piloted in several employment offices. In those pilot offices, half of the caseworkers used the system and the other half acted as control group. The allocation of the caseworkers to treatment and control group was random. The experiment was designed such that caseworkers retained full discretion about the choice of active labour market programmes, and the evaluation results showed that caseworkers largely did not follow the statistical support system. This indicates that stronger incentives are needed for caseworkers to comply with statistical profiling and targeting systems.

Matching estimators and optimal bandwidth choice

Optimal bandwidth choice for matching estimators and their finite sample properties are examined. An approximation to their MSE is derived, as a basis for a plug-in bandwidth selector. In small samples, this approximation is not very accurate, though. Alternatively, conventional cross-validation bandwidth selection is considered and performs rather well in simulation studies: Compared to standard pair-matching, kernel and ridge matching achieve reductions in MSE of about 25 to 40%. Local linear matching and weighting perform poorly. Furthermore, the scope for developing better bandwidth selectors seems to be limited for ridge matching, but non-negligible for kernel and local linear matching.

The Short- and Long-Term Effects of School Choice on Student Outcomes – Evidence from a School Choice Reform in Sweden

This paper evaluates the effects of a major Swedish school choice reform. The reform in 1992 increased school choice and competition among public schools as well as through a large-scale introduction of private schools. We estimate the effects of school choice and competition, using precise geographical information on the locations of school buildings and children’s homes for the entire Swedish population for several cohorts affected at different stages in their educational career. We can measure the long-term effects up to age 25. We find that increased school choice had very small, but positive, effects on marks at the end of compulsory schooling, but virtually zero effects on longer term outcomes such as university education, employment, criminal activity and health.

A Caseworker Like Me: Does the Similarity between Unemployed and Caseworker Increase Job Placements?

This paper examines whether the chances of job placements improve if unemployed persons are counselled by caseworkers who belong to the same social group, defined by gender, age, education, and nationality. Based on an unusually informative dataset, which links Swiss unemployed to their caseworkers, we find positive employment effects of about 4 percentage points if caseworker and unemployed belong to the same social group. Coincidence in a single characteristic, e.g. same gender of caseworker and unemployed, does not lead to detectable effects on employment. These results, obtained by statistical matching methods, are confirmed by several robustness checks.

Programme Evaluation and Treatment Choice

Lecture Notes in Economics and Mathematical Systems, Vol. 524, Heidelberg: Springer#### Policy evaluation and programme choice are important tools for informed decision-making, for the administration of active labour market programmes, training programmes, tuition subsidies, rehabilitation programmes etc. Whereas the evaluation of programmes and policies is mainly concerned with an overall assessment of impact, benefits and costs, programme choice considers an optimal allocation of individuals to the programmes. This book surveys potential evaluation strategies for policies with multiple programmes and discusses evaluation and treatment choice in a coherent framework. Recommendations for choosing appropriate evaluation estimators are derived. Furthermore, a semiparametric estimator of optimal treatment choice is developed to assist in the optimal allocation of participants. http://www.springeronline.com/sgw/cda/frontpage/0,10735,5-169-22-2272343-0,00.html

Can health-insurance help prevent child labor? An impact evaluation from Pakistan

Child labor is a common consequence of economic shocks in developing countries. We show that reducing vulnerability can affect child labor outcomes. We exploit the extension of a health and accident insurance scheme by a Pakistani microfinance institution that was set up as a randomized controlled trial and accompanied by household panel surveys. Together with increased coverage the microfinance institution offered assistance with claim procedures in treatment branches. We find lower incidence of child labor, hazardous occupations and child labor earnings caused by the innovation. Boys are more often engaged in child labor in our sample, but also seem to profit more from the insurance innovation.