Banks in non-metropolitan areas compete in a spatially differentiated environment. Non-metro community banks have been insulated from increasing competition from metro banks due to their reliance on soft information in relationship lending. Proximity to borrowers, therefore, may be an important source of market power for non-metro community banks. This paper estimates a structural model of the ...

The objective of this paper is to estimate the impacts of medium and long term participation in microfinance programs. It utilises a new, large and unique panel dataset collected from treatment and control households from 1997 to 2005. The data enables us to identify continuing participants in the program as well as newcomers and leavers. We employ different estimation strategies including trip...

We explore the finite sample properties of several semiparametric estimators of average treatment effects, including propensity score reweighting, matching, double robust, and control function estimators. When there is good overlap in the distribution of propensity scores for treatment and control units, reweighting estimators are preferred on bias grounds and attain the semiparametric efficien...

Heterogeneous Impacts in PROGRESA The “common effect” model in program evaluation assumes that all treated individuals have the same impact from a program. Our paper contributes to the recent literature that tests and goes beyond the common effect model by investigating impact heterogeneity using data from the experimental evaluation of the Mexican conditional cash transfer program PROGRESA. Ou...

This paper considers nonstandard hypothesis testing problems that involve a nuisance parameter. We establish an upper bound on the weighted average power of all valid tests, and develop a numerical algorithm that determines a feasible test with power close to the bound. The approach is illustrated in six applications: inference about a linear regression coefficient when the sign of a control co...

The standard LM tests for spatial dependence in linear and panel regressions are derived under the normality and homoskedasticity assumptions of the regression disturbances. Hence, they may not be robust against non-normality or heteroskedasticity of the disturbances. Following Born and Breitung (2011), we introduce general methods to modify the standard LM tests so that they become robust agai...

We use a linked employer-employee data set from Germany to estimate the wage effect of foreignaffiliates in (the former) East and West Germany. In addition, the wage effects of the large number of West German affiliates which are located in East Germany are also considered. The implemented techniques allow us to control both for workerand plant-level unobserved components of earnings. We find l...

Decomposing the Composition Effect This paper proposes a decomposition of the composition effect, i.e. the part of the observed between-group difference in the distribution of some economic outcome that can be explained by differences in the distribution of covariates. Our decomposition contains three types of components: (i) the “direct contributions” of each covariate due to between-group dif...

The Evaluation of Immigration Policies This chapter summarizes the literature on the evaluation of immigration policies. It brings together two strands of the literature dealing with the evaluation of labor market programs and with the economic integration of immigrants. Next to immigrant selection and settlement policies, there are four types of interventions that aim at improving the economic...

Article history: Received 4 October 2007 Received in revised form 11 August 2008 Accepted 11 November 2008 Available online 24 November 2008 This paper develops a count data model for credit scoring which allows the estimation of default probabilities using incomplete contracts data. The main advantage of the proposed approach is that it permits a more efficient use of the data, including that ...