- using R version 3.5.0 Patched (2018-05-23 r74769)
- using platform: i386-pc-solaris2.10 (32-bit)
- using session charset: UTF-8
- using option ‘--no-stop-on-test-error’
- checking for file ‘pan/DESCRIPTION’ ... OK
- this is package ‘pan’ version ‘1.4’
- 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 executable files ... OK
- checking for hidden files and directories ... OK
- checking for portable file names ... OK
- checking for sufficient/correct file permissions ... OK
- checking whether package ‘pan’ can be installed ... OK
- checking installed package size ... OK
- checking package directory ... OK
- checking ‘build’ 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 use of S3 registration ... 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 line endings in C/C++/Fortran sources/headers ... OK
- checking compiled code ... OK
- checking sizes of PDF files under ‘inst/doc’ ... OK
- checking installed files from ‘inst/doc’ ... OK
- checking files in ‘vignettes’ ... OK
- checking examples ... ERROR

Running examples in ‘pan-Ex.R’ failed

The error most likely occurred in:

> ### Name: pan

> ### Title: Imputation of multivariate panel or cluster data

> ### Aliases: pan

> ### Keywords: models

>

> ### ** Examples

>

> ########################################################################

> # This example is somewhat atypical because the data consist of a

> # single response variable (change in heart rate) measured repeatedly;

> # most uses of pan() will involve r > 1 response variables. If we had

> # r response variables rather than one, the only difference would be

> # that the vector y below would become a matrix with r columns, one

> # for each response variable. The dimensions of Sigma (the residual

> # covariance matrix for the response) and Psi (the covariance matrix

> # for the random effects) would also change to (r x r) and (r*q x r*q),

> # respectively, where q is the number of random coefficients in the

> # model (in this case q=1 because we have only random intercepts). The

> # new dimensions for Sigma and Psi will be reflected in the prior

> # distribution, as Dinv and Binv become (r x r) and (r*q x r*q).

> #

> # The pred matrix has the same number of rows as y, the number of

> # subject-occasions. Each column of Xi and Zi must be represented in

> # pred. Because Zi is merely the first column of Xi, we do not need to

> # enter that column twice. So pred is simply the matrix Xi, stacked

> # upon itself nine times.

> #

> data(marijuana)

> attach(marijuana)

> pred <- with(marijuana,cbind(int,dummy1,dummy2,dummy3,dummy4,dummy5))

> #

> # Now we must tell pan that all six columns of pred are to be used in

> # Xi, but only the first column of pred appears in Zi.

> #

> xcol <- 1:6

> zcol <- 1

> ########################################################################

> # The model specification is now complete. The only task that remains

> # is to specify the prior distributions for the covariance matrices

> # Sigma and Psi.

> #

> # Recall that the dimension of Sigma is (r x r) where r

> # is the number of response variables (in this case, r=1). The prior

> # distribution for Sigma is inverted Wishart with hyperparameters a

> # (scalar) and Binv (r x r), where a is the imaginary degrees of freedom

> # and Binv/a is the prior guesstimate of Sigma. The value of a must be

> # greater than or equal to r. The "least informative" prior possible

> # would have a=r, so here we will take a=1. As a prior guesstimate of

> # Sigma we will use the (r x r) identity matrix, so Binv = 1*1 = 1.

> #

> # By similar reasoning we choose the prior distribution for Psi. The

> # dimension of Psi is (r*q x r*q) where q is the number of random

> # effects in the model (i.e. the length of zcol, which in this case is

> # one). The hyperparameters for Psi are c and Dinv, where c is the

> # imaginary degrees of freedom (which must be greater than or equal to

> # r*q) and Dinv/c is the prior guesstimate of Psi. We will take c=1

> # and Dinv=1*1 = 1.

> #

> # The prior is specified as a list with four components named a, Binv,

> # c, and Dinv, respectively.

> #

> prior <- list(a=1,Binv=1,c=1,Dinv=1)

> ########################################################################

> # Now we are ready to run pan(). Let's assume that the pan function

> # and the object code have already been loaded into R. First we

> # do a preliminary run of 1000 iterations.

> #

> result <- pan(y,subj,pred,xcol,zcol,prior,seed=13579,iter=1000)

> #

> # Check the convergence behavior by making time-series plots and acfs

> # for the model parameters. Variances will be plotted on a log

> # scale. We'll assume that a graphics device has already been opened.

> #

> plot(1:1000,log(result$sigma[1,1,]),type="l")

> acf(log(result$sigma[1,1,]))

> plot(1:1000,log(result$psi[1,1,]),type="l")

> acf(log(result$psi[1,1,]))

> par(mfrow=c(3,2))

> for(i in 1:6) plot(1:1000,result$beta[i,1,],type="l")

> for(i in 1:6) acf(result$beta[i,1,])

> #

> # This example appears to converge very rapidly; the only appreciable

> # autocorrelations are found in Psi, and even those die down by lag

> # 10. With a sample this small we can afford to be cautious, so let's

> # impute the missing data m=10 times taking 100 steps between

> # imputations. We'll use the current simulated value of y as the first

> # imputation, then restart the chain where we left off to produce

> # the second through the tenth.

> #

> y1 <- result$y

> result <- pan(y,subj,pred,xcol,zcol,prior,seed=9565,iter=100,start=result$last)

> y2 <- result$y

> result <- pan(y,subj,pred,xcol,zcol,prior,seed=6047,iter=100,start=result$last)

> y3 <- result$y

> result <- pan(y,subj,pred,xcol,zcol,prior,seed=3955,iter=100,start=result$last)

> y4 <- result$y

> result <- pan(y,subj,pred,xcol,zcol,prior,seed=4761,iter=100,start=result$last)

> y5 <- result$y

> result <- pan(y,subj,pred,xcol,zcol,prior,seed=9188,iter=100,start=result$last)

Error in pan(y, subj, pred, xcol, zcol, prior, seed = 9188, iter = 100, :

NA/NaN/Inf in foreign function call (arg 20)

Execution halted - checking for unstated dependencies in vignettes ... OK
- checking package vignettes in ‘inst/doc’ ... OK
- checking re-building of vignette outputs ... [8s/20s] OK
- checking PDF version of manual ... OK
- DONE

Status: 1 ERROR