iiw: Given a proportional hazards model for visit intensities,...

In IrregLong: Analysis of Longitudinal Data with Irregular Observation Times

Given a proportional hazards model for visit intensities, compute inverse-intensity weights.

Description

For a longitudinal dataset subject to irregular observation, use a Cox proportional hazards model for visit intensities to compute inverse intensity weights

Usage

iiw(phfit, data, id, time, first)

Arguments

phfit	coxph object for the visit process
data	The dataset featuring longitudinal data subject to irregular observation for which inverse-intensity weights are desired
id	character string indicating which column of the data identifies subjects
time	character string indicating which column of the data contains the time at which the visit occurred
first	logical variable. If TRUE, the first observation for each individual is assigned an intensity of 1. This is appropriate if the first visit is a baseline visit at which recruitment to the study occurred; in this case the baseline visit is observed with probability 1.

Value

A vector of inverse-intensity weights for each row of the dataset. The first observation for each subject is assumed to have an intensity of 1.

See Also

Other iiw: iiw.weights(), iiwgee()

Examples

library(nlme)
library(survival)
library(geepack)
library(data.table)
data(Phenobarb)
Phenobarb$event <- 1-as.numeric(is.na(Phenobarb$conc))
data <- Phenobarb
data <- data[data$event==1,]
data$id <- as.numeric(data$Subject)
data <- data[data$time<16*24,]
data <- lagfn(data, lagvars=c("time","conc"), id="Subject", time="time", lagfirst = NA)
head(data)

mph <- coxph(Surv(time.lag,time,event)~I(conc.lag>0 & conc.lag<=20) + I(conc.lag>20 & conc.lag<=30)
 + I(conc.lag>30)+ cluster(id),,data=data)
summary(mph)
data$weight <- iiw(mph,data,"id","time",TRUE)
head(data)

IrregLong documentation built on March 18, 2022, 5:45 p.m.