Group Lending with Heterogeneous Types

50 Pages Posted: 18 May 2017

See all articles by Li Gan

Li Gan

Texas A&M University - Department of Economics; National Bureau of Economic Research (NBER)

Manuel A. Hernandez

International Food Policy Research Institute (IFPRI)

Yanyan Liu

International Food Policy Research Institute (IFPRI)

Multiple version iconThere are 4 versions of this paper

Date Written: Feb 2, 2017

Abstract

This paper proposes and implements a mixture model to account for the unobserved group heterogeneity when modeling repayment behavior in group lending. We discuss the model properties and identification. We estimate the model using a rich dataset from a group lending program in India. The estimation results support the existence of two different group types: “responsible” and “irresponsible” groups. We find that the effects of the factors driving the repayment behavior differ across types. The model also shows a higher predictive performance than standard probabilistic models, particularly in identifying potential defaulters. We provide evidence supporting the robustness of the estimations.

Keywords: Group lending, heterogeneous types, repayment behavior, mixture model

JEL Classification: O16, C35

Suggested Citation

Gan, Li and Hernandez, Manuel A. and Liu, Yanyan, Group Lending with Heterogeneous Types (Feb 2, 2017). Available at SSRN: https://ssrn.com/abstract=2970040 or http://dx.doi.org/10.2139/ssrn.2970040

Li Gan

Texas A&M University - Department of Economics ( email )

5201 University Blvd.
College Station, TX 77843-4228
United States

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Manuel A. Hernandez (Contact Author)

International Food Policy Research Institute (IFPRI) ( email )

1201 Eye St, NW,
Washington, DC 20005
United States

Yanyan Liu

International Food Policy Research Institute (IFPRI) ( email )

1201 Eye St, NW,
Washington, DC 20005
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
10
Abstract Views
246
PlumX Metrics