imphdaft {autohd}R Documentation

High dimensional missing data imputation and performing mediation analysis with univariate accelerated failure time model using Weibull distribution.

Description

Given the dimension of variables and survival information the function performs imputations using missForest function and filters significant variables, allowing the user to fit AFT model. Further, it performs mediation analysis among the signifiant variables and provides handful variables with their alpha.a values which are mediator model exposure coefficients and beta.a coefficients.

Usage

imphdaft(m, n, survdur, event, time, sig, ths, b, d, data)

Arguments

m

Starting column number from where high dimensional variates to be selected.

n

Ending column number till where high dimensional variates to be selected.

survdur

"Column/Variable name" consisting duration of survival.

event

"Column/Variable name" consisting survival event.

time

"Column/Variable name" consisting time of repeated observations.

sig

Level of significance pre-determined by the user

ths

A numeric between 0 to 100.

b

Number of MCMC iterations to burn.

d

Number of draws for the iterations.

data

High dimensional data containing survival observations with multiple covariates.

Value

Data frame containing the beta and alpha values of active variables among the significant variables.

Examples

##
## Not run: 
imphdaft(m=6,n=25,survdur="OS",event="event",time="Visit",sig=0.5,ths=0.02,b=10,d=10,data=srdata)

## End(Not run)
##

[Package autohd version 0.1.0 Index]