ps.strata.regression: Evaluate a regression model

Description Usage Arguments Details Value Examples

View source: R/psStrata.R

Description

Evaluate a regression outcome model for the stratified dataset.

Usage

1
2
ps.strata.regression(data, strata, outcome, estimand = "ATT",
  covariates = character(), family = binomial())

Arguments

data

Data Frame - containing the stratified dataset. The data frame must contain a treatment indicator variable called 'treat' and a propensity score value called 'ps_values'.

strata

Vector - containing the stratum that each subject is assigned to

outcome

The outcome variable name

estimand

String, the desired estimand ("ATT" or "ATE"), default (ATT).

covariates

Vector, containing the names of the additional covariates to include in the outcome analysis

family

- Model family, passed through to glm

Details

This function evaluates an outcome model for each strata and then pools the models to evaluate the overall treatment effect

Value

An object of type "strata.model". This object contains the model information for each strata in object$models, as well as the pooled treatment effect information in object$treatment.effect.

Examples

1
2
3
4
## Not run: 
ps.strata.regression(myData, strata, "outcome")

## End(Not run)

OHDSI/Centaur documentation built on May 9, 2017, 3:24 p.m.