Guidance on Caliper Use in School-Level PSM with psmatch2

[Sheuli Misra]

Dear Statalist users,

We are conducting a study in which we perform propensity score matching (PSM) at the school level, involving 40 treatment schools and 40 control schools. We are using the following command:

psmatch2 Treatment_control Location School_type Boundary_wall, out(Academic_score_X) neighbor(1) caliper(0.01) noreplacement

We would appreciate guidance on the use of the caliper option. Specifically, we are using a caliper of 0.01 and would like to know whether this is an appropriate choice. Are there any recommended or commonly accepted standards for selecting caliper values in such settings?

Any advice or references would be greatly appreciated.

[Felix Bittmann]

This seems like a relevant source: https://journals.plos.org/plosone/ar...l.pone.0081045

Propensity score matching is a method to reduce bias in non-randomized and observational studies. Propensity score matching is mainly applied to two treatment groups rather than multiple treatment groups, because some key issues affecting its application to multiple treatment groups remain unsolved, such as the matching distance, the assessment of balance in baseline variables, and the choice of optimal caliper width. The primary objective of this study was to compare propensity score matching methods using different calipers and to choose the optimal caliper width for use with three treatment groups. The authors used caliper widths from 0.1 to 0.8 of the pooled standard deviation of the logit of the propensity score, in increments of 0.1. The balance in baseline variables was assessed by standardized difference. The matching ratio, relative bias, and mean squared error (MSE) of the estimate between groups in different propensity score-matched samples were also reported. The results of Monte Carlo simulations indicate that matching using a caliper width of 0.2 of the pooled standard deviation of the logit of the propensity score affords superior performance in the estimation of treatment effects. This study provides practical solutions for the application of propensity score matching of three treatment groups.