version 1.0.1

cran · Apr 25, 2018 · 0ae88d0 · 0ae88d0
1 parent 6af5740
commit 0ae88d0
Show file tree

Hide file tree

Showing 26 changed files with 164 additions and 128 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -2,19 +2,19 @@ Package: intccr
 Type: Package
 Title: Semiparametric Competing Risks Regression under Interval
         Censoring
-Version: 1.0.0
+Version: 1.0.1
 Author: Giorgos Bakoyannis <gbakogia@iu.edu>, Jun Park <jp84@iu.edu>
 Maintainer: Jun Park <jp84@iu.edu>
 Description: Semiparametric regression models for the cumulative incidence function with interval-censored competing risks data as described in Bakoyannis, Yu, & Yiannoutsos (2017) <doi:10.1002/sim.7350>. The main function fits the proportional subdistribution hazards model (Fine-Gray model), the proportional odds model, and other models that belong to the class of semiparametric generalized odds rate transformation models.
 Date: 2018-02-27
-Imports: alabama (>= 2015.3.1), doParallel, foreach, numDeriv,
-        parallel, stats, utils
+Imports: alabama (>= 2015.3.1), doParallel, foreach, parallel,
+        numDeriv, stats, utils
 Depends: R (>= 2.14.0)
 License: GPL (>= 2)
 Encoding: UTF-8
 LazyData: true
 RoxygenNote: 6.0.1
 NeedsCompilation: no
-Packaged: 2018-03-30 18:14:19 UTC; Jun
+Packaged: 2018-04-25 18:58:09 UTC; Jun
 Repository: CRAN
-Date/Publication: 2018-03-30 18:25:30 UTC
+Date/Publication: 2018-04-25 19:51:27 UTC
diff --git a/MD5 b/MD5
@@ -1,24 +1,24 @@
-eedc92998dded0147ab960a98b503ee4 *DESCRIPTION
+a84d048a02971cf5b14ddbaaa9c6caa9 *DESCRIPTION
 7f306fd33d5778a0b4de24481b0f592a *NAMESPACE
-0a0eccdd23ddcd2bc0b0887c3075ac26 *R/bssmle.R
-c608b6039dee102304601e5ed8bd78b0 *R/bssmle_se.R
-5a2699f9d04d2188502ef77899322e36 *R/ciregic.R
-428b6a52374ef25c49c7fc6acf6a541b *R/dataprep.R
-dfa3b20cdd8fb350c7c688343838afad *R/longdat.R
-fa95594e495520520d2d7511f5e5d906 *R/naive_b.R
-b48e4e01030f7fc1d79f93a9e6609060 *R/simdat.R
-8a11096b5df80935f7feedc7d4477fbd *R/surv2.R
-d550e752be05c6d10870bb075bf650d2 *data/longdat.rda
-ab9636fd019c34e85025f5782eadc451 *data/simdat.rda
-380bc899acf63cd042a9f7f572bb8cf0 *man/Surv2.Rd
-36a7909a573ee760173e2913c5653955 *man/bssmle.Rd
-69e12722ca79ef1008078c0229615bf4 *man/bssmle_se.Rd
-5eab2cea8924db7c036c65c087e74104 *man/ciregic.Rd
-d349c4977fd75880bd84b0002d577a64 *man/dataprep.Rd
-400e840e0464e1cbb9d99b8312d92753 *man/longdat.Rd
-bd3faf52ad0dca013d31b675bf5a8f52 *man/naive_b.Rd
-99229cdac13863bb33ab66968f341233 *man/predict.ciregic.Rd
-0cd4681f88c07c1e0acaef2d991bb26d *man/simdat.Rd
-6f720dd810fb9f3b64f2ba05618f1968 *man/summary.ciregic.Rd
-c6f1ef4248ee4378a14f77fada507b45 *man/vcov.ciregic.Rd
-d4f0c3b0842b631693073e969a4f1315 *man/vcov.summary.ciregic.Rd
+954185cadbbc7e4d7fa06a4de556cfe5 *R/bssmle.R
+5e723fb7e883e7e4b3e1a8bac8d87ad6 *R/bssmle_se.R
+18add2f0e1f9b205bd6806bf69e26053 *R/ciregic.R
+2fb486c72054d80529135a3017b031e1 *R/dataprep.R
+7754488688a6e5c07e92ef05e3cb494a *R/longdat.R
+1dfea5d46a5b3e7f1c5fc2e81a0b4704 *R/naive_b.R
+fb3d1a1b5b02b4a48e5ac9b93eeb2f4e *R/simdat.R
+512bacc4ce440952aab345213db32cd0 *R/surv2.R
+53cb826850deb94719d43789216bcf4d *data/longdata.rda
+78eae9bc04d386eec1aacef483a57454 *data/simdata.rda
+ed3ceca062c6d09bc223c791b5140141 *man/Surv2.Rd
+d1a6744f596ebea4c308203974c4a09a *man/bssmle.Rd
+e10553c3ae22e188de0e51b2e594384e *man/bssmle_se.Rd
+b45db60013bff08a7001662e53ed2b4d *man/ciregic.Rd
+b1888fdc4ba620f037ae47b4e9aeba98 *man/dataprep.Rd
+4fa7ccc0caedba020f87be2a9f981a21 *man/longdata.Rd
+ed5fb50ba8bb0b512f5107441e5d4dd1 *man/naive_b.Rd
+5a42b10d158320b6e91a6f5e3ac70be5 *man/predict.ciregic.Rd
+52179c149a838f1a2a35d58a6b101bb7 *man/simdata.Rd
+45edcd12505acc9c7e49895ad456038d *man/summary.ciregic.Rd
+21c0d29bd735bddc4731073e8fab16d4 *man/vcov.ciregic.Rd
+8872c82fa046cc76f576026b99b664c1 *man/vcov.summary.ciregic.Rd
diff --git a/R/bssmle.R b/R/bssmle.R
@@ -2,9 +2,9 @@
 #' @description Routine that performs B-spline sieve maximum likelihood estimation with linear and nonlinear inequality constraints
 #' @author Giorgos Bakoyannis, \email{gbakogia at iu dot edu}
 #' @author Jun Park, \email{jp84 at iu dot edu}
-#' @param formula a formula object relating survival object \code{Surv2(v, u, event)} to a set of covariates.
-#' @param data a data frame to be used.
-#' @param alpha \eqn{\alpha = (\alpha1, \alpha2)} contains parameters that define the link functions from class of generalized odds-rate transformation models. The components \eqn{\alpha1} and \eqn{\alpha2} should both be \eqn{\ge 0}. If \eqn{\alpha1 = 0}, the user assumes a proportional subdistribution hazards or Fine-Gray model for cause of failure 1. If \eqn{\alpha2 = 1}, the user assumes a proportional odds model for cause of failure 2.
+#' @param formula a formula object relating survival object \code{Surv2(v, u, event)} to a set of covariates
+#' @param data a data frame that includes the variables named in the formula argument
+#' @param alpha \eqn{\alpha = (\alpha1, \alpha2)} contains parameters that define the link functions from class of generalized odds-rate transformation models. The components \eqn{\alpha1} and \eqn{\alpha2} should both be \eqn{\ge 0}. If \eqn{\alpha1 = 0}, the user assumes a proportional subdistribution hazards model or Fine-Gray model for the cause of failure 1. If \eqn{\alpha2 = 1}, the user assumes a proportional odds model for the cause of failure 2.
 #' @keywords bssmle
 #' @import stats
 #' @importFrom alabama constrOptim.nl
@@ -19,7 +19,10 @@
 #' \item{tms}{a vector of the minimum and maximum observation times}
 #' \item{Bv}{a list containing the B-splines basis functions evaluated at \code{v}}
 #' @examples
-#' est <- intccr:::bssmle(Surv2(v, u, c) ~ z1 + z2, data = simdat, alpha = c(1, 1))
+#' est.simdata <- intccr:::bssmle(Surv2(v, u, c) ~ z1 + z2, data = simdata, alpha = c(1, 1))
+#' newdata <- intccr::dataprep(data = longdata, ID = "id", time = "t",
+#'                             event = "c", Z = c("z1", "z2"))
+#' est.longdata <- intccr:::bssmle(Surv2(v, u, c) ~ z1 + z2, data = newdata, alpha = c(1, 1))
 
 
 bssmle <- function(formula, data, alpha){

diff --git a/R/bssmle_se.R b/R/bssmle_se.R
@@ -3,10 +3,10 @@
 #' @author Giorgos Bakoyannis, \email{gbakogia at iu dot edu}
 #' @author Jun Park, \email{jp84 at iu dot edu}
 #' @param formula a formula object relating survival object \code{Surv2(v, u, event)} to a set of covariates
-#' @param data a data frame to be used
-#' @param alpha \eqn{\alpha=(\alpha1, \alpha2)} contains parameters that that define the link functions from class of generalized odds-rate transformation models. The components \eqn{\alpha1} and \eqn{\alpha2} should both be \eqn{\ge 0}. If \eqn{\alpha1 = 0}, the user assumes a proportional subdistribution hazards or Fine-Gray model for cause of failure 1. If \eqn{\alpha2 = 1}, the user assumes a proportional odds model for cause of failure 2.
-#' @param do.par using parallel computing for bootstrap. If \code{TRUE}, parallel computing will be used during the bootstrap estimation of the variance-covariance matrix for the regression parameter estimates.
-#' @param nboot a number of bootstrap samples for estimating variances and covariances of the estimated regression coefficients. If \code{nboot = 0}, \code{ciregic} does dot perform bootstrap estimation of the variance matrix of the regression parameter estimates and returns \code{NA} in the place of the estimated variance matrix of the regression parameter estimates.
+#' @param data a data frame that includes the variables named in the formula argument
+#' @param alpha \eqn{\alpha = (\alpha1, \alpha2)} contains parameters that define the link functions from class of generalized odds-rate transformation models. The components \eqn{\alpha1} and \eqn{\alpha2} should both be \eqn{\ge 0}. If \eqn{\alpha1 = 0}, the user assumes a proportional subdistribution hazards model or Fine-Gray model for the cause of failure 1. If \eqn{\alpha2 = 1}, the user assumes a proportional odds model for the cause of failure 2.
+#' @param do.par using parallel computing for bootstrap calculation. If \code{do.par = TRUE}, parallel computing will be used during the bootstrap estimation of the variance-covariance matrix for the regression parameter estimates.
+#' @param nboot a number of bootstrap samples for estimating variances and covariances of the estimated regression coefficients. If \code{nboot = 0}, the function \code{ciregic} does dot perform bootstrap estimation of the variance matrix of the regression parameter estimates and returns \code{NA} in the place of the estimated variance matrix of the regression parameter estimates.
 #' @keywords bssmle_se
 #' @import foreach parallel numDeriv
 #' @importFrom doParallel registerDoParallel
@@ -16,8 +16,8 @@
 #' \item{numboot}{a number of bootstrap converged}
 #' \item{Sigma}{an estimated bootstrap variance-covariance matrix of the estimated regression coefficients}
 #' @examples
-#' intccr:::bssmle_se(Surv2(v, u, c) ~ z1 + z2, data = simdat,
-#'                    alpha = c(1, 1), do.par = FALSE, nboot = 1)
+#' est.vcov <- intccr:::bssmle_se(Surv2(v, u, c) ~ z1 + z2, data = simdata,
+#'                                alpha = c(1, 1), do.par = FALSE, nboot = 1)
 
 bssmle_se <- function(formula, data, alpha, do.par, nboot) {
   tmp <- list()