[R] summary(lm(x~y)) difference between R-2.2.1 and R-2.3.0

[Martin Maechler]

>>>>> "roger" == roger bos <roger.bos at gmail.com>
>>>>>     on Thu, 27 Apr 2006 11:06:36 -0400 writes:

    roger> Robin, I still don't know what the problem is, but
    roger> your example works on my R-2.3.0pat (created on
    roger> 4/24/2006).  You may want to try the patched version
    roger> if you are not already running it.

    roger> Thanks,

    roger> Roger

    >> x <- 1:10; y <- 10:1; summary(lm(x~y))

    ..................

but that also works on R 2.3.0 - for me.
and probably almost everyone.

Robin is also seeing other strange behavior of R 2.3.0 
(when starting X11() only when running under ESS).
My current guess would go in the direction that Robin's software
or hardware *infrastructure* (i.e. those parts ``below R'') is
acting up for some reason.

Can we get a bit more feedback, on this:
For whom does
     x <- 1:10; y <- 10:1; summary(lm(x~y))
give a bus error (or other kind of crash) ?

Thanks,
Martin


    roger> On 4/27/06, Robin Hankin <r.hankin at noc.soton.ac.uk>
    roger> wrote:
    >>  Hi Roger
    >> 
    >> good point.  I can reproduce the error much more simply:
    >> 
    >> 
    >> 
    >> > x <- 1:10 > y <- 10:1 > summary(lm(x~y))
    >> 
    >> Call: lm(formula = x ~ y)
    >> 
    >> Residuals:
    >> 
    >> *** caught bus error *** address 0x18, cause 'invalid
    >> alignment'
    >> 
    >> Traceback: 1: sort(x, partial = unique(c(lo, hi))) 2:
    >> quantile.default(resid) 3: quantile(resid) 4:
    >> structure(quantile(resid), names = nam) 5:
    >> print.summary.lm(list(call = lm(formula = x ~ [snip]
    >> 
    >> On 27 Apr 2006, at 15:44, roger bos wrote:
    >> 
    >> > I don't know if this is causing the error, by in your
    >> traceback I > saw sort() > was used and sort now removes
    >> all the attributes when it sorts.  I > used to > use
    >> sort() to sort dates in character format and now it turns
    >> them > into > integers and is breaking all my code.  The
    >> problem with upgrading > is your > never know what the
    >> end result will be on your code.  Check and see > if your
    >> > data needs the attributes to remain in order to
    >> function properly.
    >> >
    >> >
    >> >
    >> > On 4/27/06, Robin Hankin <r.hankin at noc.soton.ac.uk>
    >> wrote:
    >> >>
    >> >> Hi
    >> >>
    >> 
    >> --
    >> Robin Hankin Uncertainty Analyst National Oceanography
    >> Centre, Southampton European Way, Southampton SO14 3ZH,
    >> UK tel 023-8059-7743
    >> 
    >> 

    roger> 	[[alternative HTML version deleted]]

    roger> ______________________________________________
    roger> R-help at stat.math.ethz.ch mailing list
    roger> https://stat.ethz.ch/mailman/listinfo/r-help PLEASE
    roger> do read the posting guide!
    roger> http://www.R-project.org/posting-guide.html