version 0.78

cran · Sep 3, 2011 · 354e6a2 · 354e6a2
1 parent d6a2296
commit 354e6a2
Show file tree

Hide file tree

Showing 7 changed files with 30 additions and 19 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,13 +1,13 @@
 Package: SKAT
 Type: Package
 Title: SNP-set (Sequence) Kernel Association Test
-Version: 0.77
-Date: 2011-07-24
+Version: 0.78
+Date: 2011-09-03
 Author: Seunggeun Lee, Larisa Miropolsky and Micheal Wu
 Maintainer: Seunggeun (Shawn) Lee <phila78@gmail.com>
 Description: Kernel based SNP set test
 License: GPL (>= 2)
 Depends: R (>= 2.13.0)
-Packaged: 2012-07-24 16:45:24 UTC; sglee
+Packaged: 2012-09-06 16:57:54 UTC; sglee
 Repository: CRAN
-Date/Publication: 2012-07-24 18:37:16
+Date/Publication: 2012-09-06 19:33:45
diff --git a/MD5 b/MD5
@@ -1,11 +1,11 @@
-aebfad68e398a03b265a6a92150613d7 *DESCRIPTION
+d397c335c64d24259c74da9213b9ee57 *DESCRIPTION
 91200fad1a7abf0bd2a6288f33694ee3 *NAMESPACE
-1d71c5f98b8afed87f2c55f4f1e62190 *R/Function.R
+180e0ec5e99043829aea1fff22cc43fa *R/Function.R
 1dfb97d6d0ed6d4e023825ed0b22627a *R/Function_Power_Resampling.R
 ecee6a0f727be4fe62d5a6494bf1e11b *R/KMTest_Linear.R
 aeb01912fa7696ed7dae5b8012f1249a *R/KMTest_Logistic.R
-33f8c08f2ccd000b7cd2e89e6e7312da *R/KMTest_Logistic_VarMatching.R
-81009ecb31e01e1f9ad7753dbd135254 *R/KMTest_Optimal.R
+81f9f70109fa2dc8eb37fcb35bc0889c *R/KMTest_Logistic_VarMatching.R
+8caaada8528885ea14d159b18c88038e *R/KMTest_Optimal.R
 5ff61f1e2188ea06c83a4b5f9b3345c8 *R/KMTest_Optimal_VarMatching.R
 a270d1f8802d88edb99d9e9ed343d164 *R/Kernel.R
 a7d14a52e9b3e106898d232a34a95ff1 *R/Main.R
@@ -23,7 +23,7 @@ ba60f2917612cca53407a1933d988f39 *inst/doc/Example1.SetID
 e3b99ed0a36686c879c840e293e7687d *inst/doc/Example1.bim
 9a8d91e7b3c8d88b3d465b2c5ee5e614 *inst/doc/Example1.fam
 40344d9daf587ad38eda15074535dbc5 *inst/doc/SKAT.Rnw
-7ab9d0482742037b617a20b0a15595c9 *inst/doc/SKAT.pdf
+0dbff698c6987f6b7624cc5ae2712b55 *inst/doc/SKAT.pdf
 c15e095daf297308d467f36902f60e62 *man/Close_SSD.rd
 d49220922e600dfd17ba774ebcab9aae *man/Generate_SSD_SetID.rd
 f9800e7e2bc262cf021d87dd53df0876 *man/Get_Genotypes_SSD.rd
@@ -38,7 +38,7 @@ b277bfda9f567a5c01ac8e28432ab457 *man/Open_SSD.rd
 3aba9ec25d378071cedfcb7fc8bb7554 *man/SKAT.SSD.All.rd
 8d815f91cd850341802b9ecc334a1569 *man/SKAT.example.rd
 32db14db92e122e11566931363c6ded8 *man/SKAT.haplotypes.rd
-37acc83a37176b7163e1201ae08b04e1 *man/SKAT.rd
+a78603ed8536b6fbaf2a917d6414691a *man/SKAT.rd
 d8b382740ac36d34123e8d634119df14 *man/SKAT_Null_Model.rd
 e28440439fe71f4e6500ad5b642b2d96 *man/SKAT_Null_Model_MomentAdjust.rd
 6abae0d1663d5a07b8e6cf01898f810c *man/SSD_FILE_OPEN.rd

diff --git a/R/Function.R b/R/Function.R
@@ -212,12 +212,16 @@ Get_Lambda_U_From_Z<-function(Z1){
 		return(list( lambda = lambda, U = cbind(U)))
 	}
 
-	try1<-try(svd(Z1, LINPACK = TRUE),silent = TRUE)
-	if(class(try1) == "try-error"){
-		# try LAPACK
-		try1<-try(svd(Z1, LINPACK = FALSE),silent = TRUE)
-	}
-
+	#########################################
+	#try1<-try(svd(Z1, LINPACK = TRUE),silent = TRUE)
+	#
+	#if(class(try1) == "try-error"){
+	#	# try LAPACK
+	#	try1<-try(svd(Z1, LINPACK = FALSE),silent = TRUE)
+	#}
+
+	try1<-try(svd(Z1),silent = TRUE)
+
 	if(class(try1) == "try-error"){
 		stop("SVD error!");
 	} else {

diff --git a/R/KMTest_Logistic_VarMatching.R b/R/KMTest_Logistic_VarMatching.R
@@ -275,6 +275,10 @@ SKAT_Get_Cov_Param<-function(lambda,p_all,U){
 				Cov_Mat[i,j]<-Cov_Mat[i,j]* lambda[i]* lambda[j]
 			}
 		}
+	} else{
+		msg<-sprintf("Error SKAT_Get_Cov_Param: p.m=%d \n", p.m)
+		stop(msg)
+
 	}
 
 	Cov_Mat<-Cov_Mat + t(Cov_Mat)

diff --git a/R/KMTest_Optimal.R b/R/KMTest_Optimal.R
@@ -305,8 +305,6 @@ SKAT_Optimal_Get_Pvalue<-function(Q.all, Z1, r.all, method){
 			}
 		}
 
-
-
 	}
 
 	return(list(p.value=pval,p.val.each=Each_Info$pval))

diff --git a/inst/doc/SKAT.pdf b/inst/doc/SKAT.pdf
diff --git a/man/SKAT.rd b/man/SKAT.rd
@@ -49,9 +49,13 @@ SKAT.SSD.OneSet_SetIndex(SSD.INFO, SetIndex, obj, \dots )
 	\item{p.value.resampling}{the p-value from resampled outcome. You can get it when you use obj from SKAT_Null_Model function with resampling. See the SKAT_Null_Model. }
 	\item{p.value.noadj}{the p-value of SKAT without the small sample adjustment. It only appears when small sample adjustment is applied.}
 	\item{p.value.noadj.resampling}{the p-value from resampled outcome without the small sample adjustment. It only appears when small sample adjustment is applied. }
-  	\item{Q}{the test statistic of SKAT.}
+  	\item{Q}{the test statistic of SKAT. It has NA when method="optimal".}
 	\item{param}{estimated parameters of each method.}   
 	\item{param$Is_Converged}{ (only with method="davies") an indicator of the convergence. 1 indicates the method is converged, and 0 indicates the method is not converged. When 0 (not converged), "liu" method is used to compute p-value. }  
+	\item{param$n.marker}{a number of SNPs in the genotype matrix}  
+	\item{param$n.marker.test}{a number of SNPs used for the test. It can be different from param$n.marker when 
+	some markers are monomorphic or have higher missing rates than the missing_cutoff. }  
+
 }
 \details{
 The old interface is defunct. Please use the output object of SKAT_Null_Model to run SKAT.
@@ -72,6 +76,7 @@ r.corr represents the \eqn{\rho} parameter of the unified test,
 , where \eqn{Q_S} is a test statistic of SKAT, and \eqn{Q_B} is a score test statistic of weighted burden test. Thus, \eqn{\rho=0} results in the original weighted linear kernel SKAT, and \eqn{\rho=1} results in the weighted burden test (default: \eqn{\rho=0}). If r.corr is a vector, the optimal test will be conducted with automatically seleting \eqn{\rho} from given r.corr. \eqn{\rho} should be a value between 0 and 1. 
 
 If method="optimal", the optimal test is conducted with equal sized grid of 11 points (from 0 to 1).
+The Q has NA, when you use this method.
 
 
 }