Title: | Weighted Quantile Sum Regression |
---|---|
Description: | Fits weighted quantile sum regression models, calculates weighted quantile sum index and estimated component weights. |
Authors: | Jenna Czarnota, David Wheeler |
Maintainer: | Jenna Czarnota <[email protected]> |
License: | GPL (>= 2) |
Version: | 0.0.1 |
Built: | 2024-12-23 06:18:10 UTC |
Source: | CRAN |
Fits weighted quantile sum regression models, calculates weighted quantile sum index and estimated component weights.
The DESCRIPTION file:
Package: | wqs |
Type: | Package |
Title: | Weighted Quantile Sum Regression |
Version: | 0.0.1 |
Date: | 2015-10-05 |
Author: | Jenna Czarnota, David Wheeler |
Maintainer: | Jenna Czarnota <[email protected]> |
Description: | Fits weighted quantile sum regression models, calculates weighted quantile sum index and estimated component weights. |
Depends: | R (>= 3.2.1) |
Imports: | Rsolnp, glm2 |
License: | GPL (>= 2) |
LazyLoad: | yes |
NeedsCompilation: | no |
Packaged: | 2015-10-05 19:29:59 UTC; Jenna |
Repository: | CRAN |
Date/Publication: | 2015-10-05 22:13:29 |
Index of help topics:
WQSdata Simulated data to test WQS wqs-package Weighted Quantile Sum Regression wqs.est Weighted Quantile Sum Regression
This package performs weighted quantile sum (WQS) regression, by fitting a WQS regression model for a continuous outcome variable. The components (e.g. chemicals) to be combined into an index are scored into quantiles and then used in the estimation of empirically derived weights and a final WQS index through bootstrap sampling. The weights are constrained to sum to 1 and be between 0 and 1, and can be used to identify important (highly weighted) components and those with no association with outcome (components recieving zero or negligable weight). Inference is constrained in a single direction and the index is interpretable as a measure of the mixture effect.
Jenna Czarnota, David Wheeler
Maintainer: Jenna Czarnota <[email protected]>
Carrico C, Gennings C, Wheeler D, Factor-Litvak P. Characterization of a weighted quantile sum regression for highly correlated data in a risk analysis setting. J Biol Agricul Environ Stat. 2014:1-21. ISSN: 1085-7117. DOI: 10.1007/ s13253-014-0180-3. http://dx.doi.org/10.1007/s13253-014-0180-3.
Czarnota J, Gennings C, Colt JS, De Roos AJ, Cerhan JR, Severson RK, Hartge P, Ward MH, Wheeler D. 2015. Analysis of environmental chemical mixtures and non-Hodgkin lymphoma risk in the NCI-SEER NHL study. Environmental Health Perspectives, DOI:10.1289/ehp.1408630.
Czarnota J, Gennings C, Wheeler D. 2015. Assessment of weighted quantile sum regression for modeling chemical mixtures and cancer risk. Cancer Informatics, 2015:14(S2) 159-171 DOI: 10.4137/CIN.S17295
data(WQSdata) y.train <- WQSdata[,'y'] x.train <- WQSdata[,-10] output <- wqs.est(y.train, x.train, B = 10)
data(WQSdata) y.train <- WQSdata[,'y'] x.train <- WQSdata[,-10] output <- wqs.est(y.train, x.train, B = 10)
This function fits a weighted quantile sum regression model.
wqs.est(y.train, x.train, z.train = NULL, y.valid = y.train, x.valid = x.train, z.valid = z.train, n.quantiles = 4, B = 100, b1.pos = TRUE)
wqs.est(y.train, x.train, z.train = NULL, y.valid = y.train, x.valid = x.train, z.valid = z.train, n.quantiles = 4, B = 100, b1.pos = TRUE)
y.train |
vector of the continuous explanatory variable from training data |
x.train |
matrix of explanatory variables (to be combined into an index) from training data |
z.train |
vector or matrix of covariates from training data |
y.valid |
vector of the continuous explanatory variable from validation data |
x.valid |
matrix of explanatory variables (to be combined into an index) from validation data |
z.valid |
vector or matrix of covariates from validation data |
n.quantiles |
number of quantiles to be used (needs to be between 2 and 10) |
B |
number of bootstrap samples to be used in estimation (needs to be greater than 1) |
b1.pos |
TRUE if the index is expected to be positively related to the outcome |
A list with the following items:
q.train |
matrix of quantiles for training data |
q.valid |
matrix of quantiles for validation data |
wts.matrix |
matrix of estimated weights; each row corresponds to a bootstrap sample |
weights |
final estimated weights used in calculating the WQS index |
WQS |
weighted quantile sum estimate based on calculated weights |
fit |
WQS model fit to validation data |
Jenna Czarnota, David Wheeler
Carrico C, Gennings C, Wheeler D, Factor-Litvak P. Characterization of a weighted quantile sum regression for highly correlated data in a risk analysis setting. J Biol Agricul Environ Stat. 2014:1-21. ISSN: 1085-7117. DOI: 10.1007/ s13253-014-0180-3. http://dx.doi.org/10.1007/s13253-014-0180-3.
Czarnota J, Gennings C, Colt JS, De Roos AJ, Cerhan JR, Severson RK, Hartge P, Ward MH, Wheeler D. 2015. Analysis of environmental chemical mixtures and non-Hodgkin lymphoma risk in the NCI-SEER NHL study. Environmental Health Perspectives, DOI:10.1289/ehp.1408630.
Czarnota J, Gennings C, Wheeler D. 2015. Assessment of weighted quantile sum regression for modeling chemical mixtures and cancer risk. Cancer Informatics, 2015:14(S2) 159-171 DOI: 10.4137/CIN.S17295
data(WQSdata) y.train <- WQSdata[,'y'] x.train <- WQSdata[,-10] output <- wqs.est(y.train, x.train, B = 10)
data(WQSdata) y.train <- WQSdata[,'y'] x.train <- WQSdata[,-10] output <- wqs.est(y.train, x.train, B = 10)
Correlation and concentration patterns were loosely based on NHL data.
data("WQSdata")
data("WQSdata")
A data frame with 1000 observations on the following 10 variables.
X1
a numeric vector
X2
a numeric vector
X3
a numeric vector
X4
a numeric vector
X5
a numeric vector
X6
a numeric vector
X7
a numeric vector
X8
a numeric vector
X9
a numeric vector
y
a numeric vector; the outcome variable
Correlation and concentration patterns were loosely based on NHL data.
Carrico C, Gennings C, Wheeler D, Factor-Litvak P. Characterization of a weighted quantile sum regression for highly correlated data in a risk analysis setting. J Biol Agricul Environ Stat. 2014:1-21. ISSN: 1085-7117. DOI: 10.1007/ s13253-014-0180-3. http://dx.doi.org/10.1007/s13253-014-0180-3.
Czarnota J, Gennings C, Colt JS, De Roos AJ, Cerhan JR, Severson RK, Hartge P, Ward MH, Wheeler D. 2015. Analysis of environmental chemical mixtures and non-Hodgkin lymphoma risk in the NCI-SEER NHL study. Environmental Health Perspectives, DOI:10.1289/ehp.1408630.
Czarnota J, Gennings C, Wheeler D. 2015. Assessment of weighted quantile sum regression for modeling chemical mixtures and cancer risk. Cancer Informatics, 2015:14(S2) 159-171 DOI: 10.4137/CIN.S17295
data(WQSdata)
data(WQSdata)