Re: [R] [External] Re: unable to access index for repository...
On Fri, 9 Oct 2020 at 12:28, Martin Maechler wrote: > > > Steven Yen > > on Fri, 9 Oct 2020 05:39:48 +0800 writes: > > > Oh Hi Arne, You may recall we visited with this before. I > > do not believe the problem is algorithm specific. The > > algorithms I use the most often are BFGS and BHHH (or > > maxBFGS and maxBHHH). For simple econometric models such > > as probit, Tobit, and evening sample selection models, old > > and new versions of R work equally well (I write my own > > programs and do not use ones from AER or > > sampleSekection). For more complicated models the newer R > > would converge with not-so-nice gradients while R-3.0.3 > > would still do nicely (good gradient). I use numerical > > graduent of course. I wonder whether numerical gradient > > routine were revised at the time of transition from > > R-3.0.3 to newer. > > As R-core member, particularly interested in numerical accuracy > etc, I'm also interested in learning what's going on here. > > I think we (R core) have never heard of anything numerically deteriorating > going from R 3.0.x to R 4.0.x, and now you are claiming that in > public, you should really post *reproducible* code giving > evidence to your claim. > > As was mentioned earlier, the difference may not be in R, but > rather in the versions of the (non-base R, but "extension") R > packages you use; and you were saying earlier you will check > that (using the old version of the 'maxLik' package with a newer > version of R and vice verso) and tell us about it. > > Thank you in advance on being careful and rational about such > findings. I totally agree with Martin: It would be good if Steven could run his code with different combinations of versions of R and maxLik so that we know whether the problem is caused by newer versions of R or by newer versions of maxLik (and hopefully also which version introduced the problem). Steven wrote that the problem appeared both in maxBFGS() and in maxBHHH(). This is somewhat surprising because maxBFGS() uses for the optimisation optim() which is implemented in R's base package "stats", while maxBHHH() uses for the optimisation maxNR() which is implemented in the maxLik package. Hence, it would be a very unlikely coincidence if the optimisation routines in optim() and maxNR() would become worse at the same time. I remember that we slightly changed the user interface and the default values of some arguments of some function in the maxLik package (e.g., maxBFGS, maxBHHH, maxNR, ...) a long time ago. I suggest that Steven checks whether he needs to update his code to reflect the changes in the user interface and/or in the default values of some arguments. Best wishes, Arne -- Arne Henningsen http://www.arne-henningsen.name __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] [External] Re: unable to access index for repository...
> Steven Yen > on Fri, 9 Oct 2020 05:39:48 +0800 writes: > Oh Hi Arne, You may recall we visited with this before. I > do not believe the problem is algorithm specific. The > algorithms I use the most often are BFGS and BHHH (or > maxBFGS and maxBHHH). For simple econometric models such > as probit, Tobit, and evening sample selection models, old > and new versions of R work equally well (I write my own > programs and do not use ones from AER or > sampleSekection). For more complicated models the newer R > would converge with not-so-nice gradients while R-3.0.3 > would still do nicely (good gradient). I use numerical > graduent of course. I wonder whether numerical gradient > routine were revised at the time of transition from > R-3.0.3 to newer. As R-core member, particularly interested in numerical accuracy etc, I'm also interested in learning what's going on here. I think we (R core) have never heard of anything numerically deteriorating going from R 3.0.x to R 4.0.x, and now you are claiming that in public, you should really post *reproducible* code giving evidence to your claim. As was mentioned earlier, the difference may not be in R, but rather in the versions of the (non-base R, but "extension") R packages you use; and you were saying earlier you will check that (using the old version of the 'maxLik' package with a newer version of R and vice verso) and tell us about it. Thank you in advance on being careful and rational about such findings. With regards, Martin Maechler ETH Zurich and R core team > Not knowing how different your versions of maxLik are > between, I will try as I said I would, that is, use new > version of maxLik from old R and vice versa, and see what > happens. > Sent from my iPhone Beware: My autocorrect is crazy >> On Oct 9, 2020, at 4:28 AM, Arne Henningsen >> wrote: >> >> Hi Steven >> >> Which optimisation algorithms in maxLik work better under >> R-3.0.3 than under the current version of R? >> >> /Arne >> >>> On Thu, 8 Oct 2020 at 21:05, Steven Yen >>> wrote: >>> >>> Hmm. You raised an interesting point. Actually I am not >>> having problems with aod per se—-it is just a supporting >>> package I need while using old R. The essential package >>> I need, maxLik, simply works better under R-3.0.3, for >>> reason I do not understand—specifically the numerical >>> gradients of the likelihood function are not evaluated >>> as accurately in newer versions of R in my experience, >>> which is why I continue to use R-3.0.3. Because I use >>> this older version of R, naturally I need to install >>> other supporting packages such as aod and AER. >>> Certainly, I will install the zip file of the older >>> version of maxLik to the latest R and see what >>> happens. Thank you. >>> >>> I will install the new maxLik in old R, and old maxLik >>> in new R, and see what happens. >>> >>> Sent from my iPhone Beware: My autocorrect is crazy >>> > On Oct 9, 2020, at 2:17 AM, Richard M. Heiberger > wrote: I wonder if you are perhaps trying to solve the wrong problem. If you like what the older version of the aod package does, but not the current version, then I think the solution is to propose an option to the aod maintainer that would restore your preferred algorithm into the current version, and then use the current R. A less good, but possibly workable, option is to compile the old version of aod into the current R. > __ > R-help@r-project.org mailing list -- To UNSUBSCRIBE and > more, see https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html and provide > commented, minimal, self-contained, reproducible code. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] [External] Re: unable to access index for repository...
Oh Hi Arne, You may recall we visited with this before. I do not believe the problem is algorithm specific. The algorithms I use the most often are BFGS and BHHH (or maxBFGS and maxBHHH). For simple econometric models such as probit, Tobit, and evening sample selection models, old and new versions of R work equally well (I write my own programs and do not use ones from AER or sampleSekection). For more complicated models the newer R would converge with not-so-nice gradients while R-3.0.3 would still do nicely (good gradient). I use numerical graduent of course. I wonder whether numerical gradient routine were revised at the time of transition from R-3.0.3 to newer. Not knowing how different your versions of maxLik are between, I will try as I said I would, that is, use new version of maxLik from old R and vice versa, and see what happens. Sent from my iPhone Beware: My autocorrect is crazy > On Oct 9, 2020, at 4:28 AM, Arne Henningsen wrote: > > Hi Steven > > Which optimisation algorithms in maxLik work better under R-3.0.3 than > under the current version of R? > > /Arne > >> On Thu, 8 Oct 2020 at 21:05, Steven Yen wrote: >> >> Hmm. You raised an interesting point. Actually I am not having problems with >> aod per se—-it is just a supporting package I need while using old R. The >> essential package I need, maxLik, simply works better under R-3.0.3, for >> reason I do not understand—specifically the numerical gradients of the >> likelihood function are not evaluated as accurately in newer versions of R >> in my experience, which is why I continue to use R-3.0.3. Because I use this >> older version of R, naturally I need to install other supporting packages >> such as aod and AER. >> Certainly, I will install the zip file of the older version of maxLik to the >> latest R and see what happens. Thank you. >> >> I will install the new maxLik in old R, and old maxLik in new R, and see >> what happens. >> >> Sent from my iPhone >> Beware: My autocorrect is crazy >> On Oct 9, 2020, at 2:17 AM, Richard M. Heiberger wrote: >>> >>> I wonder if you are perhaps trying to solve the wrong problem. >>> >>> If you like what the older version of the aod package does, but not >>> the current version, >>> then I think the solution is to propose an option to the aod >>> maintainer that would restore your >>> preferred algorithm into the current version, and then use the current R. >>> >>> A less good, but possibly workable, option is to compile the old >>> version of aod into the current R. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] [External] Re: unable to access index for repository...
Hi Steven Which optimisation algorithms in maxLik work better under R-3.0.3 than under the current version of R? /Arne On Thu, 8 Oct 2020 at 21:05, Steven Yen wrote: > > Hmm. You raised an interesting point. Actually I am not having problems with > aod per se—-it is just a supporting package I need while using old R. The > essential package I need, maxLik, simply works better under R-3.0.3, for > reason I do not understand—specifically the numerical gradients of the > likelihood function are not evaluated as accurately in newer versions of R in > my experience, which is why I continue to use R-3.0.3. Because I use this > older version of R, naturally I need to install other supporting packages > such as aod and AER. > Certainly, I will install the zip file of the older version of maxLik to the > latest R and see what happens. Thank you. > > I will install the new maxLik in old R, and old maxLik in new R, and see what > happens. > > Sent from my iPhone > Beware: My autocorrect is crazy > > > On Oct 9, 2020, at 2:17 AM, Richard M. Heiberger wrote: > > > > I wonder if you are perhaps trying to solve the wrong problem. > > > > If you like what the older version of the aod package does, but not > > the current version, > > then I think the solution is to propose an option to the aod > > maintainer that would restore your > > preferred algorithm into the current version, and then use the current R. > > > > A less good, but possibly workable, option is to compile the old > > version of aod into the current R. > > > >> On Thu, Oct 8, 2020 at 1:45 PM Jeff Newmiller > >> wrote: > >> > >> All support on this list is voluntary, and support for old versions of R > >> is not even necessarily on-topic here which is why you keep getting nudged > >> to upgrade. Your "need" for support for an old version is definitely not > >> "our" problem, so I suggest you start looking for a consultant if this > >> issue is that important to you. Such is the nature of volunteer-developed > >> open source software... so support your local experts. > >> > >>> On October 8, 2020 10:22:54 AM PDT, Steven Yen wrote: > >>> Thanks for the help. I have a reason to continue with R-3.0.3. I used > >>> maxLik to estimate econometric models and some of them are better > >>> handled with R-3.0.3 (but not later)a sad reality I do not like. > >>> > >>> Here is what I did. I downloaded > >>> > >>> https://cran-archive.r-project.org/bin/windows/contrib/3.0/aod_1.3.zip > >>> > >>> and installed the zip file, which worked in both RStudio and R (without > >>> > >>> RStudio). > >>> > >>> In RStudio, I go Tools -> Install packages -> Install from -> (Choose > >>> zip) -> (Browse to the zip file) > >>> > >>> IN R, I go Packages -> Install packages from local file(s) -> (Browse > >>> to > >>> the zip file)... > > __ > R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. -- Arne Henningsen http://www.arne-henningsen.name __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] [External] Re: unable to access index for repository...
Hmm. You raised an interesting point. Actually I am not having problems with aod per se—-it is just a supporting package I need while using old R. The essential package I need, maxLik, simply works better under R-3.0.3, for reason I do not understand—specifically the numerical gradients of the likelihood function are not evaluated as accurately in newer versions of R in my experience, which is why I continue to use R-3.0.3. Because I use this older version of R, naturally I need to install other supporting packages such as aod and AER. Certainly, I will install the zip file of the older version of maxLik to the latest R and see what happens. Thank you. I will install the new maxLik in old R, and old maxLik in new R, and see what happens. Sent from my iPhone Beware: My autocorrect is crazy > On Oct 9, 2020, at 2:17 AM, Richard M. Heiberger wrote: > > I wonder if you are perhaps trying to solve the wrong problem. > > If you like what the older version of the aod package does, but not > the current version, > then I think the solution is to propose an option to the aod > maintainer that would restore your > preferred algorithm into the current version, and then use the current R. > > A less good, but possibly workable, option is to compile the old > version of aod into the current R. > >> On Thu, Oct 8, 2020 at 1:45 PM Jeff Newmiller >> wrote: >> >> All support on this list is voluntary, and support for old versions of R is >> not even necessarily on-topic here which is why you keep getting nudged to >> upgrade. Your "need" for support for an old version is definitely not "our" >> problem, so I suggest you start looking for a consultant if this issue is >> that important to you. Such is the nature of volunteer-developed open source >> software... so support your local experts. >> >>> On October 8, 2020 10:22:54 AM PDT, Steven Yen wrote: >>> Thanks for the help. I have a reason to continue with R-3.0.3. I used >>> maxLik to estimate econometric models and some of them are better >>> handled with R-3.0.3 (but not later)a sad reality I do not like. >>> >>> Here is what I did. I downloaded >>> >>> https://cran-archive.r-project.org/bin/windows/contrib/3.0/aod_1.3.zip >>> >>> and installed the zip file, which worked in both RStudio and R (without >>> >>> RStudio). >>> >>> In RStudio, I go Tools -> Install packages -> Install from -> (Choose >>> zip) -> (Browse to the zip file) >>> >>> IN R, I go Packages -> Install packages from local file(s) -> (Browse >>> to >>> the zip file)... __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] [External] Re: unable to access index for repository...
I wonder if you are perhaps trying to solve the wrong problem. If you like what the older version of the aod package does, but not the current version, then I think the solution is to propose an option to the aod maintainer that would restore your preferred algorithm into the current version, and then use the current R. A less good, but possibly workable, option is to compile the old version of aod into the current R. On Thu, Oct 8, 2020 at 1:45 PM Jeff Newmiller wrote: > > All support on this list is voluntary, and support for old versions of R is > not even necessarily on-topic here which is why you keep getting nudged to > upgrade. Your "need" for support for an old version is definitely not "our" > problem, so I suggest you start looking for a consultant if this issue is > that important to you. Such is the nature of volunteer-developed open source > software... so support your local experts. > > On October 8, 2020 10:22:54 AM PDT, Steven Yen wrote: > >Thanks for the help. I have a reason to continue with R-3.0.3. I used > >maxLik to estimate econometric models and some of them are better > >handled with R-3.0.3 (but not later)a sad reality I do not like. > > > >Here is what I did. I downloaded > > > >https://cran-archive.r-project.org/bin/windows/contrib/3.0/aod_1.3.zip > > > >and installed the zip file, which worked in both RStudio and R (without > > > >RStudio). > > > >In RStudio, I go Tools -> Install packages -> Install from -> (Choose > >zip) -> (Browse to the zip file) > > > >IN R, I go Packages -> Install packages from local file(s) -> (Browse > >to > >the zip file)... > > > >Below is the command line generated and the prompt. > > > >> install.packages("C:/Users/USER/Downloads/aod_1.3.zip", repos = NULL, > > > >type = "win.binary") > >package ‘aod’ successfully unpacked and MD5 sums checked > > > >I will always be able to download the proper .zip file from CRAC > >Archive, right. So, this will always work for me? Thank you all !! If > >there are more direct options that work, I would still be interested to > > > >know. > > > >Steven Yen > > > >On 2020/10/9 上午 12:49, Duncan Murdoch wrote: > >> Don't choose a mirror. That will override the repos choice. > >> > >> Do update R to a current version if you aren't able to debug this > >> yourself. > >> > >> Duncan Murdoch > >> > >> On 08/10/2020 12:38 p.m., Steven Yen wrote: > >>> Sorry Gentlemen and all. Now this is becoming a joke (to me). I > >repeated > >>> what I did earlier, with and without the option to set repos > >suggested > >>> by Duncan. Now it does not work. I wonder whether it is dependent on > >the > >>> mirror I chose, but I do not remember the one I chose earlier when > >it > >>> work. > >>> > >>> I need your help, gentlemen, as I need to use R-3.0.3 for my task. > >>> > >>> > options(repos="https://cran-archive.r-project.org;) > >>> > chooseCRANmirror() > >>> > install.packages("aod") > >>> Warning: unable to access index for repository > >>> https://cran-archive.r-project.org/bin/windows/contrib/3.0 > >>> Warning: unable to access index for repository > >>> http://lib.stat.cmu.edu/R/CRAN/bin/windows/contrib/3.0 > >>> > >>> package ‘aod’ is available as a source package but not as a > >binary > >>> > >>> Warning message: > >>> package ‘aod’ is not available (for R version 3.0.3) > >>> > > >install.packages("aod",repos='https://cran-archive.r-project.org') > >>> Warning: unable to access index for repository > >>> https://cran-archive.r-project.org/bin/windows/contrib/3.0 > >>> Warning message: > >>> package ‘aod’ is not available (for R version 3.0.3) > >>> > >>> On 2020/10/9 上午 12:02, Duncan Murdoch wrote: > Okay, so it's not an RStudio issue. However, I'd guess setting > > options(repos = "https://cran-archive.r-project.org;) > > at the start of your session could make everything work. (I'm > guessing you currently have it set to "http://cran.rstudio.com;, > >which > is the source of the last warning below, probably due to an R bug. > But since you're using an obsolete version of R, it shouldn't > >surprise > you that it has bugs that nobody else is seeing.) > > Duncan Murdoch > > On 08/10/2020 11:54 a.m., Steven Yen wrote: > > Thanks. You gentlemen please tell me what this means. In R > >(outside > > of RStudio) I ran: > > > > install.packages("aod") > > > > Received a warning (and installation did not seem to go through). > > > > Then I tried > > > > install.packages("aod",repos='https://cran-archive.r-project.org') > > > > Received a warning but it went on to try > > > > > >https://cran-archive.r-project.org/bin/windows/contrib/3.0/aod_1.3.zip > > > > and it worked. See log below. > > > > I expect to continue to use R-3.0.3 for a while and I very much > >like > > this to become a routine. Thank you all. > > > > Steven Yen > > > > >