Matchit April 2009

matchit@lists.gking.harvard.edu

7 participants
5 discussions

by Manuela Exp�sito Ruiz

Hi, I have a basic question for the use and interpretation of propensity score (ps) When I add de ps lika an independent variable for the multivariate regression model, when can I translate its contribution? Must I use the treatment and the ps in the same model and the rest coavariables using for the ps estimation? If ps is significative in all model of multivariate regression, it´s ps a confounding variable? Thanks Manuela

15 years, 1 month

explaining weighting with full matching

by Casey Klofstad

Hey all- I've been having some trouble explaining, in plain English, where the weight in full matching comes from and how it incorporates the matching process into the final regression analysis. Any advice on language would be greatly appreciated. Thanks much, -c -- Casey A. Klofstad University of Miami Department of Political Science Coral Gables, FL klofstad(a)gmail.com http://www.as.miami.edu/personal/cklofstad/ -- MatchIt mailing list served by Harvard-MIT Data Center List Address: matchit(a)lists.gking.harvard.edu Subscribe/Unsubscribe: http://lists.gking.harvard.edu/?info=matchit MatchIt Software and Documentation: http://gking.harvard.edu/matchit/

15 years, 1 month

can you analyze two treatment variables at once?

by Casey Klofstad

Hey all- I have two variables that I want to match on. Ideally, I'd like to combine both treatment variables in the same model. Is there anyway to do this? Perhaps by multiplying the weights from each match to get a single summary weight? Best, -c -- Casey A. Klofstad University of Miami Department of Political Science Coral Gables, FL klofstad(a)gmail.com http://www.as.miami.edu/personal/cklofstad/ -- MatchIt mailing list served by Harvard-MIT Data Center List Address: matchit(a)lists.gking.harvard.edu Subscribe/Unsubscribe: http://lists.gking.harvard.edu/?info=matchit MatchIt Software and Documentation: http://gking.harvard.edu/matchit/

15 years, 1 month

Error in weights.matrix(match.matrix, treat, discarded)

by Beth Gifford

Dear colleagues, I am using MatchIt for my project. Cfst_std is a treatment variable. We want to use “exact” matching in gender and use “nearest” matching for other variables. However, I got the error message: Error in weights.matrix(match.matrix, treat, discarded). What does this mean? And how do I fix this issue? Thanks so much, > cfst_std <-yu$cfst_std > table (cfst_std) cfst_std 0=no 1=yes 25034 3074 > summary (yu$boy) 0=no 1=yes 14042 14066 > >m.out <- matchit(cfst_std~math_s+old_grade, data=yu, exact=c("boy"), method="nearest") Error in weights.matrix(match.matrix, treat, discarded) : No units were matched In addition: Warning messages: 1: In max(pscore[treat == 0]) : no non-missing arguments to max; returning -Inf 2: In max(pscore[treat == 1]) : no non-missing arguments to max; returning -Inf 3: In min(pscore[treat == 0]) : no non-missing arguments to min; returning Inf 4: In min(pscore[treat == 1]) : no non-missing arguments to min; returning Inf Yu

15 years, 2 months

error in Matchit - caliper matching using mahalanobis distances?

by Lugtig, P. (Peter)

Dear colleagues, I encountered a problem in using matchit; more particular in the combination of matching using propensity scores including a caliper score based on the mahalanobis distance. Below you find a fragment of my R-output: Problem: > panel <- read.table("G:/data 25-03-09 na norm alleen catiwapi.dat", header=T, quote="", dec=".") > dim(panel) [1] 4032 19 > tevredenm.out.cal <- matchit(catiwapi~ inkomen+stedelijk+V66+V63+V61+job+livalone + +zorgen+V44+V61*V63+V61*livalone+V66*job+ + V61*job+V63*V61,data=panel,distance="mahalanobis", + mahvars = c("V61", "V66", "zorgen"), caliper=0.0005) Error: subscript out of bounds I found this error, despite many efforts to solve it. Apparantly, R cannot extract the individual variables from the data matrix (despite the fact I atta In the end I found one workaround which didn't produce the error, but I have no clue why this is. Did anyone else encounter this particular error? Solved by: > panels <- read.table("G:/data 25-03-09 na norm alleen catiwapi.dat", header=T, quote="", dec=".") > panel <- panels[1:4032,1:19] > tevredenm.out.cal <- matchit(catiwapi~ inkomen+stedelijk+V66+V63+V61+job+livalone + +zorgen+V44+V61*V63+V61*livalone+V66*job+ + V61*job+V63*V61,data=panel,distance="mahalanobis", + mahvars = c("V61", "V66", "zorgen"), caliper=0.0005) works as I want it warm greeting from the Netherlands, Peter Lugtig Methoden en technieken/ methods and statistics Utrecht University

15 years, 2 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Matchit April 2009