-------------------------------------------------------------------------------
help for imbalance
-------------------------------------------------------------------------------
  
Check covariate imbalance before and after matching
---------------------------------------------------
 

Syntax ------ imbalance dataname varname treatname blockname savfile

Description ----------- imbalance calculates absolute standardized difference in covariate means (ASAM) before matching (dx) and after matching (dxm), as described by Haviland, Nagin, and Rosenbaum (2007). It allows the analyst to evaluate whether matching balances an observed covariate between treated and control observations. dataname specifies the name of data file containing covariates to be checked. varname is the name of a covariate on which the analyst wants to check its balance between treated and control observations. treatname specifies the name of the dichotomous variable identifying treatment conditions. For imbalance to run properly, treatname must be coded treatname = 1 if the observation receives treatment, and treatname = 0 if the observation is a control. blockname specifies the variable name that identifies matched sets. Output and Return Values ------------------------ After running imbalance, Stata returns dx ¨C the absolute standardized difference in covariate means before matching, dxm - the absolute standardized difference in covariate means after matching, and the name of the covariate along with the blockname. Both dx and dxm are similar to CohenĄ¯s d. After running imbalance, Stata saves the results in a file named savfile. The analyst can use return list immediately after running imbalance to see statistics saved for further analysis. Examples --------

. imbalance cds black kuse fm results . imbalance "D:\PSA\cds.dta" black kuse fm "C:\tmp\results" . return list . use "C:\tmp\results", clear . list References ---------- Guo, S., & Fraser, M. (2009). Propensity score analysis: Statistical methods and applications. Thousand Oaks, CA: Sage Publications Inc. Haviland, A., Nagin, D. S., & Rosenbaum, P. R. (2007). Combining propensity score matching and group-based trajectory analysis in an observational study. Psychological Methods, 12, 247-267. Author ------ Shenyang Guo University of North Carolina at Chapel Hill sguo@email.unc.edu

Also see: ---------