* using log directory 'd:/Rcompile/CRANpkg/local/3.0/BayesSummaryStatLM.Rcheck'
* using R version 3.0.3 (2014-03-06)
* using platform: i386-w64-mingw32 (32-bit)
* using session charset: ISO8859-1
* checking for file 'BayesSummaryStatLM/DESCRIPTION' ... OK
* checking extension type ... Package
* this is package 'BayesSummaryStatLM' version '1.0'
* checking package namespace information ... OK
* checking package dependencies ... OK
* checking if this is a source package ... OK
* checking if there is a namespace ... OK
* checking for hidden files and directories ... OK
* checking for portable file names ... OK
* checking whether package 'BayesSummaryStatLM' can be installed ... OK
* checking installed package size ... OK
* checking package directory ... OK
* checking DESCRIPTION meta-information ... OK
* checking top-level files ... OK
* checking for left-over files ... OK
* checking index information ... OK
* checking package subdirectories ... OK
* checking R files for non-ASCII characters ... OK
* checking R files for syntax errors ... OK
* checking whether the package can be loaded ... OK
* checking whether the package can be loaded with stated dependencies ... OK
* checking whether the package can be unloaded cleanly ... OK
* checking whether the namespace can be loaded with stated dependencies ... OK
* checking whether the namespace can be unloaded cleanly ... OK
* checking loading without being on the library search path ... OK
* checking dependencies in R code ... OK
* checking S3 generic/method consistency ... OK
* checking replacement functions ... OK
* checking foreign function calls ... OK
* checking R code for possible problems ... OK
* checking Rd files ... OK
* checking Rd metadata ... OK
* checking Rd cross-references ... OK
* checking for missing documentation entries ... OK
* checking for code/documentation mismatches ... OK
* checking Rd \usage sections ... OK
* checking Rd contents ... OK
* checking for unstated dependencies in examples ... OK
* checking contents of 'data' directory ... OK
* checking data for non-ASCII characters ... OK
* checking data for ASCII and uncompressed saves ... OK
* checking examples ... ERROR
Running examples in 'BayesSummaryStatLM-Ex.R' failed
The error most likely occurred in:

> ### Name: bayes.regress
> ### Title: MCMC posterior sampling of Bayesian linear regression model
> ###   parameters using only summary statistics
> ### Aliases: bayes.regress
> ### Keywords: combine consensus subposterior posterior parallel
> 
> ### ** Examples
> 
> ##################################################
> ## Simulate data 
> ##################################################
> 
> set.seed(284698)
> 
> num.samp  <- 100 # number of data values to simulate
> 
> # The first value of the beta vector is the y-intercept:
> beta <- c(-0.33, 0.78, -0.29, 0.47, -1.25)
> 
> # Calculate the number of predictor variables:
> num.pred <- length(beta)-1
> 
> rho       <- 0.0  # correlation between predictors
> mean.vec  <- rep(0,num.pred)
> sigma.mat <- matrix(rho,num.pred,num.pred) + diag(1-rho,num.pred)
> sigmasq.sim <- 0.05
> 
> # Simulate predictor variables:
> x.pre       <- rmvn(num.samp, mu=mean.vec, sigma=sigma.mat)       
> 
> # Add leading column of 1's to x.pre for y-intercept:
> x <- cbind(rep(1,num.samp),x.pre)
> 
> epsilon <- rnorm(num.samp, mean=0, sd=sqrt(sigmasq.sim))
> 
> y  <- as.numeric( x %*% as.matrix(beta) +  epsilon)
> 
> ## Compute summary statistics (alternatively, the
> # "read.regress.data.ff() function (in this package) can be 
> # used to calculate summary statistics; see example below).
> 
> xtx <- t(x)%*%x 
> xty <- t(x)%*%y 
> yty <- t(y)%*%y 
> 
> data.values<-list(xtx=xtx, xty=xty, yty=yty,
+                   numsamp.data = num.samp, 
+                   xtx.inv = chol2inv(chol(xtx)))
> 
> ##########################################################
> ## Bayesian linear regression analysis
> ##########################################################
> 
> Tsamp.out <- 100 # number of MCMC samples to produce
> 
> ## Choose priors for beta and sigma-squared. Here,
> # beta: Uniform prior; sigma-squared: Inverse Gamma prior. 
> 
> beta.prior    <- list( type = "flat")
> sigmasq.prior <- list(type = "inverse.gamma", inverse.gamma.a = 1.0, 
+                       inverse.gamma.b = 1.0, sigmasq.init = 1.0 )
> 
> set.seed(284698)
> 
> # Run the "bayes.regress" function using the data simulated above.
> 
> MCMC.out <- bayes.regress(data.values, 
+                           beta.prior, 
+                           sigmasq.prior = sigmasq.prior, 
+                           Tsamp.out = Tsamp.out)
> 
> # Next, print the posterior means of the unknown model parameters.
> # Alternatively, the "coda" package can be used for analysis.
> 
> print(c(colMeans(MCMC.out$beta), mean(MCMC.out$sigmasq)))
[1] -0.31718660  0.77275199 -0.27380379  0.52685576 -1.22473866  0.07465078
> 
> # Check that output is close to simulated values (although num.samp and
> # Tsamp.out are small here); note that the output includes both beta and 
> # sigmasq:
> # c(-0.33,  0.78, -0.29,  0.47, -1.25,  0.05)
> 
> ## Run all 6 combinations of priors for 3 "beta.prior" choices and 
> #  2 "sigmasq.prior" choices:
> 
> beta.priors <- list(
+   list( type = "flat"),
+   
+   list( type = "mvnorm.known", 
+         mean.mu = rep(0.0,    (num.pred+1)), 
+         prec.Cinv = diag(1.0, (num.pred+1))),
+         
+   list( type = "mvnorm.unknown",
+         mu.hyper.mean.eta         = rep(0.0,(num.pred+1)),  
+         mu.hyper.prec.Dinv        = diag(1.0, (num.pred+1)),  
+         Cinv.hyper.df.lambda      = (num.pred+1), 
+         Cinv.hyper.invscale.Vinv  = diag(1.0, (num.pred+1)),  
+         mu.init                   = rep(1.0, (num.pred+1)), 
+         Cinv.init                 = diag(1.0,(num.pred+1)))   
+ )
> 
> sigmasq.priors <- list(
+   list(type = "inverse.gamma", 
+        inverse.gamma.a = 1.0, 
+        inverse.gamma.b = 1.0, 
+        sigmasq.init = 0.1 ),       
+   list( type="sigmasq.inverse", sigmasq.init = 0.1)
+ )
> 
> for (beta.prior in beta.priors)
+ {
+   for(sigmasq.prior in sigmasq.priors)
+   {
+     set.seed(284698)
+     MCMC.out <- bayes.regress(data.values, 
+                               beta.prior, 
+                               sigmasq.prior = sigmasq.prior, 
+                               Tsamp.out = Tsamp.out)
+     print(c(colMeans(MCMC.out$beta), mean(MCMC.out$sigmasq)))
+   }
+ }
[1] -0.31754170  0.77234799 -0.27435855  0.52767691 -1.22488276  0.07436599
[1] -0.31789780  0.77237323 -0.27497950  0.52769906 -1.22532299  0.05490155
[1] -0.31711481  0.77187886 -0.27426407  0.52739342 -1.22429838  0.07437203
[1] -0.31758096  0.77202514 -0.27490930  0.52748880 -1.22488935  0.05490578
[1] -0.31480149  0.77445508 -0.28014614  0.53223970 -1.22722827  0.07401473
[1] -0.31559684  0.77421916 -0.27994271  0.53161283 -1.22739629  0.05464019
> 
> # Check that output is close to simulated values (although num.samp and
> # Tsamp.out are small here); note that the output includes both beta and 
> # sigmasq:
> # c(-0.33,  0.78, -0.29,  0.47, -1.25,  0.05):
> 
> 
> #######################################################################
> ## Read the data from a file, calculate the summary statistics and run 
> ## the Bayesian linear regression analysis
> #######################################################################
> 
> Tsamp.out <- 100
> 
> ## Assume non-zero y-intercept data.
> 
> # Read the files and compute summary statistics using the "read.regress.data.ff()" 
> # function (in this package).
> 
> 
> filename <- system.file('data/regressiondata.nz.all.csv.gz', package='BayesSummaryStatLM')
> data.values <- read.regress.data.ff(filename)
Error in read.table.ffdf(file = fname, , fileEncoding = fileEncoding,  : 
  unkown arguments: numerals,skipNul
Calls: read.regress.data.ff -> read.table.ffdf
Execution halted