search

MichaelChirico / r-bugs

A ⚠️read-only⚠️mirror of https://bugs.r-project.org/
20 stars 0 forks source link

[BUGZILLA #14379] nlme package: pooledSD summary.lmList lme do not work for Pinheiro and Bates Exercise 1.3 #3969

Closed MichaelChirico closed 4 years ago

MichaelChirico commented 4 years ago

Created attachment 1127 [details] 3 specific problems and identification of place in code where fix is needed for 2 of the problems.

METADATA

MichaelChirico commented 4 years ago

I can confirm the bug report and will look into it.

On Mon, Sep 13, 2010 at 11:15 PM, <r-bugs@<::CENSORED -- SEE ORIGINAL ON BUGZILLA::>-project.org> wrote:

https://bugs.r-project.org/bugzilla3/show_bug.cgi?id=14379

          Summary: nlme package: pooledSD summary.lmList lme do not work
                   for Pinheiro and Bates Exercise 1.3
          Product: R
          Version: R 2.11.1
         Platform: All
       OS/Version: Windows
           Status: NEW
         Severity: major
         Priority: P5
        Component: Models
       AssignedTo: R-core@<::CENSORED -- SEE ORIGINAL ON BUGZILLA::>-project.org
       ReportedBy: rmh@<::CENSORED -- SEE ORIGINAL ON BUGZILLA::>
  Estimated Hours: 0.0

Created an attachment (id=1127)
 --> (https://bugs.r-project.org/bugzilla3/attachment.cgi?id=1127)
3 specific problems and identification of place in code where fix is needed
for
2 of the problems.

--
Configure bugmail:
https://bugs.r-project.org/bugzilla3/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.

_______________________________________________
R-core list: https://stat.ethz.ch/mailman/listinfo/r-core

METADATA

MichaelChirico commented 4 years ago

One of my students found another change in R so Exercise 4.2 (b) i. no longer works. The exercise says to use:

gapply(Orthodont, "distance", diff)

This works in S-Plus. It does not work in R. IN R, the longer statement is needed:

gapply(Orthodont, "distance", function(x) diff(data.matrix(x)))

The reason is that at the end of the gapply function, the line

val <- lapply(split(object, groups), FUN, ...)

creates a list of data.frames. diff of a data.frame doesn't convert it to a matrix in R.

version

TIBCO Spotfire S+ Version 8.1.1 for Microsoft Windows : 2008 

diff(data.frame(1:3))

X1 2 1 3 1

version
           _

platform i386-pc-mingw32
arch i386
os mingw32
system i386, mingw32
status
major 2
minor 11.1
year 2010
month 05
day 31
svn rev 52157
language R
version.string R version 2.11.1 (2010-05-31)

diff(data.frame(1:3))

data frame with 0 columns and 3 rows

This example does not work in R-1.6.2

METADATA

MichaelChirico commented 4 years ago

Is exercise 4.2 (b) actually in package nlme? grepping does not show the code stated.

METADATA

MichaelChirico commented 4 years ago

Brian,

From the perspective of my class, the statements in the exercises in the

book don't work.

It is your call as to whether R-Core wants to treat these as bugs in R or as errata for the book. My preference as an instructor using this text is for the statements in the book to work.

I checked the errata at http://stat.bell-labs.com/project/nlme/MEMSS/Errata and none of the four specifics I have identified based on exercises on pages 55 and 198 are listed there.

Rich

On Fri, Oct 1, 2010 at 5:39 PM, <r-bugs@<::CENSORED -- SEE ORIGINAL ON BUGZILLA::>-project.org> wrote:

https://bugs.r-project.org/bugzilla3/show_bug.cgi?id=14379

--- Comment #3 from Brian Ripley <ripley@<::CENSORED -- SEE ORIGINAL ON BUGZILLA::>> 2010-10-01
17:39:40 EDT ---
Is exercise 4.2 (b) actually in package nlme?  grepping does not show the
code stated.

--
Configure bugmail:
https://bugs.r-project.org/bugzilla3/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You reported the bug.

[[alternative HTML version deleted]]

METADATA

MichaelChirico commented 4 years ago

On Fri, Oct 1, 2010 at 5:16 PM, RICHARD M. HEIBERGER <rmh@<::CENSORED -- SEE ORIGINAL ON BUGZILLA::>> wrote:

Brian,

From the perspective of my class, the statements in the exercises in the
book don't work.

It is your call as to whether R-Core wants to treat these as bugs in R or as
errata for the
book.  My preference as an instructor using this text is for the statements
in the book to
work.

I checked the errata at
http://stat.bell-labs.com/project/nlme/MEMSS/Errata
and none of the four specifics I have identified based on exercises on pages
55 and 198 are
listed there.

It was not the best choice to state in the book that the errata are listed at that URL because neither Jose nor I can update that page.

Rich

On Fri, Oct 1, 2010 at 5:39 PM, <r-bugs@<::CENSORED -- SEE ORIGINAL ON BUGZILLA::>-project.org> wrote:
>
> https://bugs.r-project.org/bugzilla3/show_bug.cgi?id=14379
>
> --- Comment #3 from Brian Ripley <ripley@<::CENSORED -- SEE ORIGINAL ON BUGZILLA::>> 2010-10-01
> 17:39:40 EDT ---
> Is exercise 4.2 (b) actually in package nlme?  grepping does not show the
> code stated.
>
> --
> Configure bugmail:
> https://bugs.r-project.org/bugzilla3/userprefs.cgi?tab=email
> ------- You are receiving this mail because: -------
> You reported the bug.

METADATA

MichaelChirico commented 4 years ago

You may wish to treat this as book errata, rather than as program bug. From my class's perspective, the book as documentation doesn't match the program.

Changes in nlme program since the text was published.

  1. The order of the arguments was changed. At the time the book was written, the statement on page 85 orthLRTsim <- simulate.lme(fm1OrthF, fm2OrthF, nsim=1000) worked. Now it doesn't and you need to specify the argument names as is shown in file library/nlme/scripts/ch02.R orthLRTsim <- simulate.lme( fm1OrthF, m2 = fm2OrthF, nsim = 1000 )

  2. The behavior of nlme:::plot.simulate.lme was changed At the time the book was written, the statement on page 85 plot( orthLRTsim, df = c(1, 2) ) # produces Figure 2.3 displayed the reference line. Now it doesn't and you need a panel function plot( orthLRTsim, df = c(1, 2), panel=function(...) { panel.xyplot(...) panel.abline(a=0, b=1, lty=3) } ) # produces Figure 2.3

METADATA