| Title: | Variable Selection for Optimal Treatment Decision |
|---|---|
| Description: | A penalized regression framework that can simultaneously estimate the optimal treatment strategy and identify important variables. Appropriate for either censored or uncensored continuous response. |
| Authors: | Wenbin Lu, Hao Helen Zhang, Donglin Zeng, Yuan Geng, and Shannon T. Holloway |
| Maintainer: | Shannon T. Holloway <[email protected]> |
| License: | GPL-2 |
| Version: | 1.2 |
| Built: | 2024-12-19 05:07:45 UTC |
| Source: | https://github.com/cran/OTRselect |
A penalized regression framework that can simultaneously estimate the optimal treatment strategy and identify important variables. Appropriate for either censored or uncensored continuous response.
The DESCRIPTION file:
| Package: | OTRselect |
| Type: | Package |
| Title: | Variable Selection for Optimal Treatment Decision |
| Version: | 1.2 |
| Date: | 2023-11-24 |
| Author: | Wenbin Lu, Hao Helen Zhang, Donglin Zeng, Yuan Geng, and Shannon T. Holloway |
| Maintainer: | Shannon T. Holloway <[email protected]> |
| Description: | A penalized regression framework that can simultaneously estimate the optimal treatment strategy and identify important variables. Appropriate for either censored or uncensored continuous response. |
| License: | GPL-2 |
| Depends: | stats, lars, survival, methods |
| NeedsCompilation: | no |
| Packaged: | 2023-11-24 17:24:43 UTC; 19194 |
| Date/Publication: | 2023-11-24 17:50:02 UTC |
| Repository: | https://sth1402.r-universe.dev |
| RemoteUrl: | https://github.com/cran/OTRselect |
| RemoteRef: | HEAD |
| RemoteSha: | 18f05e6571e65bae065574d56bd1d3c042733967 |
Index of help topics:
OTRselect-package Variable Selection for Optimal Treatment
Decision
Qhat Mean Response or Restricted Mean Response Given
a Treatment Regime
censored Variable Selection for Optimal Treatment
Decision with Censored Survival Times
uncensored Variable Selection for Optimal Treatment
Decision with Uncensored Continuous Response
Function censored performs variable selection for censored continuous response. Function uncensored performs variable selection for uncensored continuous response. Function Qhat estimates the restricted mean response given a treatment regime for censored data or the mean response given a treatment regime for uncensored data.
Wenbin Lu, Hao Helen Zhang, Donglin Zeng, Yuan Geng, and Shannon T. Holloway
Maintainer: Shannon T. Holloway <[email protected]>
Lu, W., Zhang, H. H., and Zeng. D. (2013). Variable selection for optimal treatment decision. Statistical Methods in Medical Research, 22, 493–504. PMCID: PMC3303960.
Geng, Y., Lu, W., and Zhang, H. H. (2015). On optimal treatment regimes selection for mean survival time. Statistics in Medicine, 34, 1169–1184. PMCID: PMC4355217.
A penalized regression framework that can simultaneously estimate the optimal treatment strategy and identify important variables when the response is continuous and censored. This method uses an inverse probability weighted least squares estimation with adaptive LASSO penalty for variable selection.
censored(x, y, a, delta, propen, phi, logY = TRUE, intercept = TRUE)censored(x, y, a, delta, propen, phi, logY = TRUE, intercept = TRUE)
x |
Matrix or data.frame of model covariates. |
y |
Vector of response. Note that this data is used to estimate the Kaplan-Meier Curve and should not be log(T). |
a |
Vector of treatment received. Treatments must be coded as integers or numerics that can be recast as integers without loss of information. |
delta |
Event indicator vector. The indicator must be coded as 0/1 where 0=no event and 1=event. |
propen |
Vector or matrix of propensity scores for each treatment. If a vector, the propensity is assumed to be the same for all samples. Column or element order must correspond to the sort order of the treatment variable, i.e., 0,1,2,3,... If the number of columns/elements in propen is one fewer than the total number of treatment options, it is assumed that the base or lowest valued treatment has not been provided. |
phi |
A character {'c' or 'l'} indicating if the constant ('c') or linear ('l') baseline mean function is to be used. |
logY |
TRUE/FALSE indicating if log(y) is to be used for regression. |
intercept |
TRUE/FALSE indicating if an intercept is to be included in phi model. |
A list object containing
beta |
A vector of the estimated regression coefficients after variable selection. |
optTx |
The estimated optimal treatment for each sample. |
Wenbin Lu, Hao Helen Zhang, Yuan Geng, and Shannon T. Holloway
Geng, Y., Lu, W., and Zhang, H. H. (2015). On optimal treatment regimes selection for mean survival time. Statistics in Medicine, 34, 1169–1184. PMCID: PMC4355217.
sigma <- diag(10) ct <- 0.5^{1L:9L} rst <- unlist(sapply(1L:9L,function(x){ct[1L:{10L-x}]})) sigma[lower.tri(sigma)] <- rst sigma[upper.tri(sigma)] <- t(sigma)[upper.tri(sigma)] M <- t(chol(sigma)) Z <- matrix(rnorm(1000),10,100) X <- t(M%*%Z) A <- rbinom(100,1,0.5) Y <- rweibull(100,shape=0.5,scale=1) C <- rweibull(100,shape=0.5,scale=1.5) delta <- as.integer(C <= Y) Y[delta > 0.5] <- C[delta>0.5] dat <- data.frame(X,A,exp(Y),delta) colnames(dat) <- c(paste("X",1:10,sep=""),"a","y","del") censored(x = X, y = Y, a = A, delta = delta, propen = 0.5, phi = "c", logY = TRUE, intercept = TRUE)sigma <- diag(10) ct <- 0.5^{1L:9L} rst <- unlist(sapply(1L:9L,function(x){ct[1L:{10L-x}]})) sigma[lower.tri(sigma)] <- rst sigma[upper.tri(sigma)] <- t(sigma)[upper.tri(sigma)] M <- t(chol(sigma)) Z <- matrix(rnorm(1000),10,100) X <- t(M%*%Z) A <- rbinom(100,1,0.5) Y <- rweibull(100,shape=0.5,scale=1) C <- rweibull(100,shape=0.5,scale=1.5) delta <- as.integer(C <= Y) Y[delta > 0.5] <- C[delta>0.5] dat <- data.frame(X,A,exp(Y),delta) colnames(dat) <- c(paste("X",1:10,sep=""),"a","y","del") censored(x = X, y = Y, a = A, delta = delta, propen = 0.5, phi = "c", logY = TRUE, intercept = TRUE)
Estimates the mean response given a treatment regime if data is uncensored. If data is censored, estimates the restricted mean response given a treatment regime.
Qhat(y, a, g, wgt = NULL)Qhat(y, a, g, wgt = NULL)
y |
vector of responses. Note if logY = TRUE in censored, this value should also be the logarithm. |
a |
vector of treatments received. |
g |
vector of the given treatment regime. |
wgt |
weights to be used if response is censored. |
Returns the estimated mean response or restricted mean response.
Wenbin Lu, Hao Helen Zhang, Donglin Zeng, Yuan Geng, and Shannon T. Holloway
Lu, W., Zhang, H. H., and Zeng. D. (2013). Variable selection for optimal treatment decision. Statistical Methods in Medical Research, 22, 493–504. PMCID: PMC3303960.
Geng, Y., Lu, W., and Zhang, H. H. (2015). On optimal treatment regimes selection for mean survival time. Statistics in Medicine, 34, 1169–1184. PMCID: PMC4355217.
y <- rnorm(100) a <- rbinom(100,1,0.5) g <- integer(100) Qhat(y = y, a = a, g = g)y <- rnorm(100) a <- rbinom(100,1,0.5) g <- integer(100) Qhat(y = y, a = a, g = g)
A penalized regression framework that can simultaneously estimate the optimal treatment strategy and identify important variables when the response is continuous and not censored. This method uses an inverse probability weighted least squares estimation with adaptive LASSO penalty for variable selection.
uncensored(x, y, a, propen, phi, intercept = TRUE)uncensored(x, y, a, propen, phi, intercept = TRUE)
x |
Matrix or data.frame of model covariates. |
y |
Vector of response. Note that this data is used to estimate the Kaplan-Meier Curve and should not be log(T). |
a |
Vector of treatment received. Treatments must be coded as integers or numerics that can be recast as integers without loss of information. |
propen |
Vector or matrix of propensity scores for each treatment. If a vector, the propensity is assumed to be the same for all samples. Column or element order must correspond to the sort order of the treatment variable, i.e., 0,1,2,3,... If the number of columns/elements in propen is one fewer than the total number of treatment options, it is assumed that the base or lowest valued treatment has not been provided. |
phi |
A character {'c' or 'l'} indicating if the constant ('c') or linear ('l') baseline mean function is to be used. |
intercept |
TRUE/FALSE indicating if an intercept is to be included in phi model. |
A list object containing
beta |
A vector of the estimated regression coefficients after variable selection. |
optTx |
The estimated optimal treatment for each sample. |
Wenbin Lu, Hao Helen Zhang, Donglin Zeng, and Shannon T. Holloway
Lu, W., Zhang, H. H., and Zeng. D. (2013). Variable selection for optimal treatment decision. Statistical Methods in Medical Research, 22, 493–504. PMCID: PMC3303960.
sigma <- diag(10) ct <- 0.5^{1L:9L} rst <- unlist(sapply(1L:9L,function(x){ct[1L:{10L-x}]})) sigma[lower.tri(sigma)] <- rst sigma[upper.tri(sigma)] <- t(sigma)[upper.tri(sigma)] M <- t(chol(sigma)) Z <- matrix(rnorm(1000),10,100) X <- t(M %*% Z) gamma1 <- c(1, -1, rep(0,8)) beta <- c(1,1,rep(0,7), -0.9, 0.8) A <- rbinom(100,1,0.5) Y <- 1.0 + X %*% gamma1 + A*{cbind(1.0,X)%*%beta} + rnorm(100,0,.25) dat <- data.frame(X,A,Y) uncensored(x=X, y = Y, a = A, propen = 0.5, phi = "c", intercept = TRUE)sigma <- diag(10) ct <- 0.5^{1L:9L} rst <- unlist(sapply(1L:9L,function(x){ct[1L:{10L-x}]})) sigma[lower.tri(sigma)] <- rst sigma[upper.tri(sigma)] <- t(sigma)[upper.tri(sigma)] M <- t(chol(sigma)) Z <- matrix(rnorm(1000),10,100) X <- t(M %*% Z) gamma1 <- c(1, -1, rep(0,8)) beta <- c(1,1,rep(0,7), -0.9, 0.8) A <- rbinom(100,1,0.5) Y <- 1.0 + X %*% gamma1 + A*{cbind(1.0,X)%*%beta} + rnorm(100,0,.25) dat <- data.frame(X,A,Y) uncensored(x=X, y = Y, a = A, propen = 0.5, phi = "c", intercept = TRUE)