From noreply at r-forge.r-project.org  Sun Aug 10 21:26:12 2014
From: noreply at r-forge.r-project.org (noreply at r-forge.r-project.org)
Date: Sun, 10 Aug 2014 21:26:12 +0200 (CEST)
Subject: [Gsdesign-commits] r373 - pkg/gsDesign/man
Message-ID: <20140810192612.419EC187323@r-forge.r-project.org>

Author: keaven
Date: 2014-08-10 21:26:11 +0200 (Sun, 10 Aug 2014)
New Revision: 373

Modified:
   pkg/gsDesign/man/gsCP.Rd
Log:
gsCP update and documentation update

Modified: pkg/gsDesign/man/gsCP.Rd
===================================================================
--- pkg/gsDesign/man/gsCP.Rd	2014-06-23 18:57:22 UTC (rev 372)
+++ pkg/gsDesign/man/gsCP.Rd	2014-08-10 19:26:11 UTC (rev 373)
@@ -8,6 +8,7 @@
 \title{2.4: Conditional and Predictive Power, Overall and Conditional Probability of Success}
 \description{
 \code{gsCP()} computes conditional boundary crossing probabilities at future planned analyses for a given group sequential design assuming an interim z-statistic at a specified interim analysis.
+While \code{gsCP()} is designed toward computing conditional power for a variety of underlying parameter values, \code{\link{condpower}} is built to compute conditional power for a variety of interim test statistic values which is useful for sample size adaptation (see \code{\link{ssrCP}}).
 \code{gsPP()} averages conditional power across a posterior distribution to compute predictive power.
 \code{gsPI()} computes Bayesian prediction intervals for future analyses corresponding to results produced by \code{gsPP()}. 
 \code{gsPosterior()} computes the posterior density for the group sequential design parameter of interest given a prior density and an interim outcome that is exact or in an interval.
@@ -73,7 +74,7 @@
 }
 \note{The manual is not linked to this help file, but is available in library/gsdesign/doc/gsDesignManual.pdf in the directory where R is installed.}
 
-\seealso{\code{\link{normalGrid}}, \code{\link{gsDesign}}, \code{\link{gsProbability}}, \code{\link{gsBoundCP}}}
+\seealso{\code{\link{normalGrid}}, \code{\link{gsDesign}}, \code{\link{gsProbability}}, \code{\link{gsBoundCP}}, \code{\link{ssrCP}}, \code{\link{condPower}}}
 
 \author{Keaven Anderson \email{keaven\_anderson at merck.}}
 \references{


From noreply at r-forge.r-project.org  Sun Aug 10 21:27:14 2014
From: noreply at r-forge.r-project.org (noreply at r-forge.r-project.org)
Date: Sun, 10 Aug 2014 21:27:14 +0200 (CEST)
Subject: [Gsdesign-commits] r374 - in pkg/gsDesign: . R
Message-ID: <20140810192714.72528187323@r-forge.r-project.org>

Author: keaven
Date: 2014-08-10 21:27:14 +0200 (Sun, 10 Aug 2014)
New Revision: 374

Modified:
   pkg/gsDesign/DESCRIPTION
   pkg/gsDesign/R/ssrCP.R
Log:
gsCP update and documentation update

Modified: pkg/gsDesign/DESCRIPTION
===================================================================
--- pkg/gsDesign/DESCRIPTION	2014-08-10 19:26:11 UTC (rev 373)
+++ pkg/gsDesign/DESCRIPTION	2014-08-10 19:27:14 UTC (rev 374)
@@ -1,5 +1,5 @@
 Package: gsDesign
-Version: 2.9-1
+Version: 2.9-2
 Title: Group Sequential Design
 Author: Keaven Anderson 
 Maintainer: Keaven Anderson <keaven_anderson at merck.com>

Modified: pkg/gsDesign/R/ssrCP.R
===================================================================
--- pkg/gsDesign/R/ssrCP.R	2014-08-10 19:26:11 UTC (rev 373)
+++ pkg/gsDesign/R/ssrCP.R	2014-08-10 19:27:14 UTC (rev 374)
@@ -244,12 +244,13 @@
                             target=1-x$beta, x=x$x, 
                             n2=x$maxinc*x$x$n.I[2]-x$x$n.I[1],
                             z2=x$z2fn, theta=x$theta)$root
+  
     if (changepoint3 >= changepoint2){
       en <- en + x$maxinc*x$x$n.I[2]*(pnorm(changepoint2-mu)-
                                         pnorm(changepoint-mu))
       a <- changepoint
       b <- changepoint2
-      n2 <- x$x$n.I[2]-x$x$n.I[1]
+      n2 <- x$maxinc*x$x$n.I[2]-x$x$n.I[1]
       grid <- normalGrid(mu=(a+b)/2,bounds=c(a,b),r=r)
       for(i in 1:length(theta)) Power[i] <-  Power[i] +
         sum(dnorm(grid$z-sqrt(x$x$n.I[1])*theta[i]) * 


From noreply at r-forge.r-project.org  Fri Aug 22 23:41:57 2014
From: noreply at r-forge.r-project.org (noreply at r-forge.r-project.org)
Date: Fri, 22 Aug 2014 23:41:57 +0200 (CEST)
Subject: [Gsdesign-commits] r375 - pkg/gsDesign/man
Message-ID: <20140822214157.2AE231855D5@r-forge.r-project.org>

Author: keaven
Date: 2014-08-22 23:41:56 +0200 (Fri, 22 Aug 2014)
New Revision: 375

Modified:
   pkg/gsDesign/man/gsCP.Rd
Log:
Minor error in gsCP.rd documentation file.

Modified: pkg/gsDesign/man/gsCP.Rd
===================================================================
--- pkg/gsDesign/man/gsCP.Rd	2014-08-10 19:27:14 UTC (rev 374)
+++ pkg/gsDesign/man/gsCP.Rd	2014-08-22 21:41:56 UTC (rev 375)
@@ -8,7 +8,7 @@
 \title{2.4: Conditional and Predictive Power, Overall and Conditional Probability of Success}
 \description{
 \code{gsCP()} computes conditional boundary crossing probabilities at future planned analyses for a given group sequential design assuming an interim z-statistic at a specified interim analysis.
-While \code{gsCP()} is designed toward computing conditional power for a variety of underlying parameter values, \code{\link{condpower}} is built to compute conditional power for a variety of interim test statistic values which is useful for sample size adaptation (see \code{\link{ssrCP}}).
+While \code{gsCP()} is designed toward computing conditional power for a variety of underlying parameter values, \code{\link{condPower}} is built to compute conditional power for a variety of interim test statistic values which is useful for sample size adaptation (see \code{\link{ssrCP}}).
 \code{gsPP()} averages conditional power across a posterior distribution to compute predictive power.
 \code{gsPI()} computes Bayesian prediction intervals for future analyses corresponding to results produced by \code{gsPP()}. 
 \code{gsPosterior()} computes the posterior density for the group sequential design parameter of interest given a prior density and an interim outcome that is exact or in an interval.