IRSF (version 1.0.3)

cph.main: Main effects in a Cox-PH model

Description

Fits a Proportional Hazards Time-To-Event Regression Model saturated with first order terms. Computes p-values of significance of regression coefficients of main effects in a Cox-PH model

Usage

cph.main(X,
             main.term)

Arguments

X

data.frame or numeric matrix of input covariates. Dataset X assumes that: - all variables are in columns - the observed times to event and censoring variables are in the first two columns: "stime": numeric vector of observed times. "status": numeric vector of observed status (censoring) indicator variable. - each variable has a unique name, excluding the word "noise"

main.term

Vector of character string of each individual covariate name.

Value

List of 2 fields:

raw

Raw p-value covariates importances significance

fdr

FDR-adjusted p-value of covariates importances significance

Acknowledgments

This work made use of the High Performance Computing Resource in the Core Facility for Advanced Research Computing at Case Western Reserve University. We are thankful to Ms. Janet Schollenberger, Senior Project Coordinator, CAMACS, as well as Dr. Jeremy J. Martinson, Sudhir Penugonda, Shehnaz K. Hussain, Jay H. Bream, and Priya Duggal, for providing us the data related to the samples analyzed in the present study. Data in this manuscript were collected by the Multicenter AIDS Cohort Study (MACS) at (https://www.statepi.jhsph.edu/macs/macs.html) with centers at Baltimore, Chicago, Los Angeles, Pittsburgh, and the Data Coordinating Center: The Johns Hopkins University Bloomberg School of Public Health. The MACS is funded primarily by the National Institute of Allergy and Infectious Diseases (NIAID), with additional co-funding from the National Cancer Institute (NCI), the National Heart, Lung, and Blood Institute (NHLBI), and the National Institute on Deafness and Communication Disorders (NIDCD). MACS data collection is also supported by Johns Hopkins University CTSA. This study was supported by two grants from the National Institute of Health: NIDCR P01DE019759 (Aaron Weinberg, Peter Zimmerman, Richard J. Jurevic, Mark Chance) and NCI R01CA163739 (Hemant Ishwaran). The work was also partly supported by the National Science Foundation grant DMS 1148991 (Hemant Ishwaran) and the Center for AIDS Research grant P30AI036219 (Mark Chance).

References

• Dazard J-E., Ishwaran H., Mehlotra R.K., Weinberg A. and Zimmerman P.A. (2018). "Ensemble Survival Tree Models to Reveal Pairwise Interactions of Variables with Time-to-Events Outcomes in Low-Dimensional Setting" Statistical Applications in Genetics and Molecular Biology, 17(1):20170038.

• Ishwaran, H. and Kogalur, U.B. (2007). "Random Survival Forests for R". R News, 7(2):25-31.

• Ishwaran, H. and Kogalur, U.B. (2013). "Contributed R Package randomForestSRC: Random Forests for Survival, Regression and Classification (RF-SRC)" CRAN.

See Also

• R package randomForestSRC

Examples

# NOT RUN {
#===================================================
# Loading the library and its dependencies
#===================================================
library("IRSF")

# }
# NOT RUN {
    #===================================================
    # IRSF package news
    #===================================================
    IRSF.news()

    #================================================
    # MVR package citation
    #================================================
    citation("IRSF")

    #===================================================
    # Loading of the Synthetic and Real datasets
    # Use help for descriptions
    #===================================================
    data("MACS", package="IRSF")
    ?MACS

    head(MACS)

    #===================================================
    # Synthetic dataset
    # Continuous case:
    # All variables xj, j in {1,...,p}, are iid 
    # from a multivariate uniform distribution
    # with parmeters  a=1, b=5, i.e. on [1, 5].
    # rho = 0.50
    # Regression model: X1 + X2 + X1X2
    #===================================================
    seed <- 1234567
    set.seed(seed)
    n <- 200
    p <- 5
    x <- matrix(data=runif(n=n*p, min=1, max=5),
                nrow=n, ncol=p, byrow=FALSE,
                dimnames=list(1:n, paste("X", 1:p, sep="")))

    beta <- c(rep(1,2), rep(0,p-2), 1)
    covar <- cbind(x, "X1X2"=x[,1]*x[,2])
    eta <- covar %*% beta                   # regression function

    seed <- 1234567
    set.seed(seed)
    lambda0 <- 1
    lambda <- lambda0 * exp(eta - mean(eta))  # hazards function
    tt <- rexp(n=n, rate=lambda)              # true (uncensored) event times
    tc <- runif(n=n, min=0, max=3.9)          # true (censored) event times
    stime <- pmin(tt, tc)                     # observed event times
    status <- 1 * (tt <= tc)                  # observed event indicator
    X <- data.frame(stime, status, x)
                    
    #===================================================
    # Synthetic dataset
    # Ranking of individual and noise variables by univariate 
    # Minimal Depth of a Maximal Subtree (MDMS)
    # Serial mode
    #===================================================
    X.main.mdms <- rsf.main(X=X,
                            ntree=1000,
                            method="mdms",
                            splitrule="logrank",
                            importance="random",
                            B=1000,
                            ci=90,
                            parallel=FALSE,
                            conf=NULL,
                            verbose=TRUE,
                            seed=seed)
                            
    #===================================================
    # Synthetic dataset
    # Proportional Hazards Time-To-Event Regression Model 
    # saturated with first order terms only.
    #===================================================
    X.main.cph <- cph.main(X=X, 
                           main.term=rownames(X.main.mdms))

    #===================================================
    # Real dataset
    #===================================================
    seed <- 1234567
    data("MACS", package="IRSF")

    X <- MACS[,c("TTX","EventX","Race","Group3",
                 "DEFB.CNV3","CCR2.SNP","CCR5.SNP2",
                 "CCR5.ORF","CXCL12.SNP2")]
                 
    #===================================================
    # Real dataset
    # Ranking of individual and noise variables by univariate 
    # Minimal Depth of a Maximal Subtree (MDMS)
    # Parallel mode
    #===================================================
    MACS.main.mdms <- rsf.main(X=X,
                               ntree=1000, 
                               method="mdms", 
                               splitrule="logrank", 
                               importance="random", 
                               B=1000, 
                               ci=80,
                               parallel=TRUE, 
                               conf=conf, 
                               verbose=TRUE, 
                               seed=seed)
                               
    #===================================================
    # Real dataset
    # Proportional Hazards Time-To-Event Regression Model 
    # saturated with first order terms only.
    #===================================================
    MACS.main.cph <- cph.main(X=X, 
                              main.term=rownames(MACS.main.mdms))

    
# }
# NOT RUN {
# }