#### Do not export calculatePosteriorMean

Rob Scharp authored on 11/10/2011 12:17:35
Showing 1 changed files
 ... ... @@ -54,12 +54,12 @@ predictionRegion(object, copyNumber) 54 54  %% ~Make other sections like Warning with \section{Warning }{....} ~ 55 55   56 56  \seealso{ 57 - \code{\link{calculatePosteriorMean}}, 57 +% \code{\link{calculatePosteriorMean}}, 58 58  \code{\link{posteriorProbability}}, \code{\link{genotypes}} 59 59  } 60 60  \examples{ 61 -data(sample.CNSet) 62 -pr <- predictionRegion(sample.CNSet, copyNumber=0:4) 61 +data(cnSetExample) 62 +pr <- predictionRegion(cnSetExample, copyNumber=0:4) 63 63  names(pr) 64 64  ## bivariate normal prediction region for NULL genotype (homozygous deletion) 65 65  str(pr[["NULL"]])

#### Update help files for posteriorProbability and calculatePosteriorMean

Rob Scharp authored on 01/10/2011 04:47:53
Showing 1 changed files
 ... ... @@ -36,10 +36,10 @@ predictionRegion(object, copyNumber) 36 36   37 37  A list named by the genotype. NULL' refers to copy number zero, A' 38 38  is a hemizygous deletion, etc. Each element is a list of the means 39 - (mu) and covariance (cov) for each marker. The covariance for each 40 - marker is stored as a vector in the order variance A, correlation, 41 - variance B. For nonpolymorphic markers, only the first mu and the 42 - first variance are used. 39 + (mu) and covariance (cov) for each marker stored as an array. For 40 + mu', the dimensions of the array are marker x allele (A or B) x 41 + batch. For cov', the dimensions of the array are marker x 3 42 + (varA, cor, and varB) x batch. 43 43   44 44  } 45 45 

#### Add example for predictionRegion help

Rob Scharp authored on 01/10/2011 04:47:12
Showing 1 changed files
 ... ... @@ -54,13 +54,17 @@ predictionRegion(object, copyNumber) 54 54  %% ~Make other sections like Warning with \section{Warning }{....} ~ 55 55   56 56  \seealso{ 57 - 57 + \code{\link{calculatePosteriorMean}}, 58 + \code{\link{posteriorProbability}}, \code{\link{genotypes}} 58 59  } 59 60  \examples{ 60 61  data(sample.CNSet) 61 -pr <- predictionRegion(cnSet, copyNumber=0:4) 62 +pr <- predictionRegion(sample.CNSet, copyNumber=0:4) 63 +names(pr) 64 +## bivariate normal prediction region for NULL genotype (homozygous deletion) 65 +str(pr[["NULL"]]) 62 66  } 63 67  % Add one or more standard keywords, see file 'KEYWORDS' in the 64 68  % R documentation directory. 65 -\keyword{ ~kwd1 } 66 -\keyword{ ~kwd2 }% __ONLY ONE__ keyword per line 69 +\keyword{distribution} 70 +\keyword{list} 67 71 \ No newline at end of file

#### Add Rd files for calculatePosteriorMean, genotypes, posteriorProbability, and predictionRegion

Rob Scharp authored on 01/10/2011 04:46:59
Showing 1 changed files
 1 1 new file mode 100644 ... ... @@ -0,0 +1,66 @@ 1 +\name{predictionRegion} 2 +\alias{predictionRegion} 3 +\alias{predictionRegion,CNSet,integer-method} 4 +\title{Prediction regions for integer copy number} 5 +\description{Bivariate normal prediction regions for integer copy 6 + number. Copy numbers 0-4 allowed.} 7 +\usage{ 8 +predictionRegion(object, copyNumber) 9 +} 10 +%- maybe also 'usage' for other objects documented here. 11 +\arguments{ 12 + \item{object}{A \code{CNSet} object.} 13 + \item{copyNumber}{Integer vector. 0-4 allowed.} 14 +} 15 +\details{ 16 + 17 + We fit a linear regression for each allele to the diallic genotype 18 + cluster medians. Denoting the background and slope by nu and phi, 19 + respectively, the mean for the bivariate normal prediction region is 20 + given by 21 + 22 + mu_A = nu_A + CA * phi_A 23 + 24 + and 25 + 26 + mu_B nu_B + CB * phi_B 27 + 28 + The variance and correlation of the normalized intensities is 29 + estimated from the diallelic genotype clusters AA, AB, and BB on the 30 + log-scale. For copy number not equal to two, we assume that the 31 + variance is approximately the same for copy number not equal to 2. 32 + 33 +} 34 + 35 +\value{ 36 + 37 + A list named by the genotype. NULL' refers to copy number zero, A' 38 + is a hemizygous deletion, etc. Each element is a list of the means 39 + (mu) and covariance (cov) for each marker. The covariance for each 40 + marker is stored as a vector in the order variance A, correlation, 41 + variance B. For nonpolymorphic markers, only the first mu and the 42 + first variance are used. 43 + 44 +} 45 + 46 + 47 +\references{ 48 + Scharpf et al., 2011, Biostatistics. 49 +} 50 +\author{ 51 + R. Scharpf 52 +} 53 + 54 +%% ~Make other sections like Warning with \section{Warning }{....} ~ 55 + 56 +\seealso{ 57 + 58 +} 59 +\examples{ 60 +data(sample.CNSet) 61 +pr <- predictionRegion(cnSet, copyNumber=0:4) 62 +} 63 +% Add one or more standard keywords, see file 'KEYWORDS' in the 64 +% R documentation directory. 65 +\keyword{ ~kwd1 } 66 +\keyword{ ~kwd2 }% __ONLY ONE__ keyword per line