pm3 {pm3}

pm3

Description

Propensity score matching for unordered 3-group data

Arguments

data

need a dataframe

x

Enter the 3 categorical variables to be matched.If x is a number, it must be of type 1,2,3.

y

Enter the outcome variable for your study.

covs

Covariates. Usually the other fitted variables of the model.This is also usually the baseline variable you need to match.

factor

Define the categorical variables in your data.

CALIP

The number used to match. Usually you don't need to change it. The default is 0.5.

Details

You can use this program for 3 sets of categorical data for propensity score matching. Assume that the data has 3 different categorical variables. You can use it to perform propensity matching of baseline indicator groupings. The matching will make the differences in the baseline data smaller.

Value

A list with data.

Examples

bc<-prematurity
#####Generate data lists and extract data
g<-pm3(data=bc,x="race",y="low",covs=c("age","lwt","ptl"),
factor=c("ui","low","smoke"))
mbc<-g[["mbc"]]
####Compare before and after matching
library(tableone)
allVars <-c("age", "lwt", "ptl")
fvars<-c("ht")
tab2 <- CreateTableOne(vars = allVars, strata = "race" ,
data = bc, factorVars=fvars,addOverall = TRUE )
print(tab2,smd = TRUE)
tab1 <- CreateTableOne(vars = allVars, strata = "race" ,
data = mbc, factorVars=fvars,addOverall = TRUE )
print(tab1,smd = TRUE)