In wal615/prime.total.effect: Total effect estimation of the environmental mixtures

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = ""
)

NHANCE PCBs data

Hemoglobin.PCB data

Intorduction

1. pops_hormones.sas7bdat is the original and raw NHANCE data.

2. nhance_hemoglobin_PCB.csv is a subset data based Hemoglobin hypothesis. which is Are POPs associated with hemoglobin A1c in non-diabetics. More details about the hypothesis are in here. Further details of its variables can be found in the information table.

3. hemoglobin.PCB is a cleaned dataset based on nhance_hemoglobin_PCB.csv, which can be accessed directly from the prime.total.effect package. The specific procedure are following:

   • Remove all observations if the response is missing
   • Remove all observations if all the PCBs and PCB_LC (below limit of detection (LOD)) are missing
   • Replace all the $\sqrt{\text{LOD}}$ with LOD (for data imputation)
   • The R script for cleanning can be found in here

Usage

library(prime.total.effect)
dim(hemoglobin.PCB)

# there are still many NAs in the data set, to remove the all the NAs, you could use na.omit

PCB.no.missing <- na.omit(hemoglobin.PCB)

# response is LBXGH
head(PCB.no.missing)

# covariates are PCBs
head(PCB.no.missing)

dim(hemoglobin.PCB)

dim(PCB.no.missing)

wal615/prime.total.effect documentation built on April 29, 2020, 2:05 p.m.