similar to: predict.loess() segfaults for large n?

Dear R community, I am trying to understand how the predict function, specifically, the predict.loess function works. I understand that the loess function calculates regression parameters at each data point in 'data'. lo <- loess ( y~x, data) p <- predict (lo, newdata) I understand that the predict function predicts values for 'newdata' according to the loess regression

Hi all, I am doing a projection pursuit regression using the ppr() function from modreg. I would also like to use predict.ppr(). However, I cannot find any information about it in the help files. There is a link to predict.ppr in the index for modreg, but that link is to the help for ppr(). Has predict.ppr() not been implemented? If not, does anyone have a suggestion as to how to implement

Dear list, I am trying to reclaim what I think is lost memory in R, I have been using gc(), rm() and also using Rprof to figure out where all the memory is going but I might be missing something. I have the following situation basic loop which calls memoryHogFunction: for i in (1:N) { dataset <- generateDataset(i) fit <- try( memoryHogFunction(dataset, otherParameters)) } and

Hi, I want to test for independence in my GLS model fitp2, but when I try to use the dwtest function in the lmtest library, I get the error message "Error in terms.default(formula) : no terms component". The model and data set are below. Any suggestions would be really helpful! Thanks a lot in advance, M. Grace fitp2:

Hello all, I'm having a nightmare of a time trying to get stable results with SIP clients on Asterisk. I can't seem to find a configuration that works! In our office, we run a Sonicwall Pro 200, which is a sip aware, stateful firewall. Originally, I had configured Asterisk to run on the NAT side so that those within the office could connect easily, and those outside the office

I have been attempting to use cph models to get better calibration of my models for which I had originally used logistic regression. I tried running with 40 repetitions and got an error. I then tried 500 repetitions (thinking that the NaNs in the output below might be caused by that choice) and then let my computer crunch for several hours and got only the same error message and

Dear R-help, I have encountered some errors when trying to compile R-1.3.1 from source on my WinNT4SP6 laptop (PII w/128MB RAM). I have installed all the tools following the instruction in src/gnuwin32/INSTALL, with the exception that the mingw compiler I have might be a bit older (they are the ones recommended for R-1.3.0, I believe). I have also compiled the ATLAS libraries from source using

Greetings, I'm attempting to install R-0.64.1 on a Sun Sparc 20 running Solaris 2.4 with gcc-2.7.2.2, g77-0.5.20 and Gnu make 3.76-1. On several occasions, the make process aborted when trying to build the shared object file for the modreg package (its first attempt at such a beast). In all attempts, the error message is as follows: ../../../../bin/R SHLIB -o modreg.so bsplvd.o bvalue.o

> install.packages("gam") Warning in install.packages("gam") : argument 'lib' is missing: using /usr/local/lib/R/site-library --- Please select a CRAN mirror for use in this session --- Loading Tcl/Tk interface ... done trying URL 'http://cran.cnr.Berkeley.edu/src/contrib/gam_0.97.tar.gz' Content type 'application/x-gzip' length 89613 bytes opened URL

Hello, I tried to compile v2.3.1 on Solaris x86 with SUN Pro compilers. I had an error while stats libarary was being compiled and I notice that "-xtarget=generic64" was not passed to f95 while cc used it. Could you tell me how to fix this problem? f95 -PIC -O -I/mounts/devel/SUNWspro/prod/include -c sgram.f -o sgram.o f95 -PIC -O -I/mounts/devel/SUNWspro/prod/include -c

Full_Name: Benjamin Tyner Version: 2.1.0, 4/18/2005 OS: i686-redhat-linux-gnu Submission from: (NULL) (4.64.8.220) # Just run my.test() below in a newly opened R session. Once too many models have been fit (~20 on my system), the computed standard error jumps to a different value. This is (superficially) due to a different residual sum of squares, not a different one.delta. No other aspect of

I tried to compile R-0.63.1 to R-0.63.3 on my DEC Alpha with the operating system of UNIX 4.0. All have the same problem after R.binary has been successfully compiled. The last few lines of the message are shown as below: ... make[4]: Entering directory `/home/ming/R-0.63.3/src/library/modreg/src' f77 -c bsplvd.f -o bsplvd.o f77 -c bvalue.f -o bvalue.o f77 -c bvalus.f -o bvalus.o f77

Hello again! Thanks to Dr. Brian Ripley, the make problem I reported earlier has been solved, and R-0.64.1 is now successfully installed and tested. There were two essential problems with the stock configuration: (i) the Fortran option -fPIC was not being propagated to certain Makefiles further down the tree; (ii) gmake was not being recognized when the library files were being

Hi, if make and gmake are different on any machine (for example Solaris with gnu make as gmake), then compiling fails with gmake. A small transcript follows. If i make a link from gmake to make as under linux, then it works. This problem exists in all versions of R. g77 -O2 -fPIC -c sslvrg.f -o sslvrg.o g77 -O2 -fPIC -c stxwx.f -o stxwx.o ../../../../bin/R SHLIB -o modreg.so bsplvd.o bvalue.o

Hi has anyone succeeded in installing R on DEC alpha OSF 4.0 with gcc/g77 ? The PLATFORMS file mentions successful installtion on OSF 3.2 using cc. Here is the output I get when trying to compile: ld -shared -o eda.so line.o smooth.o ld: Warning: Unresolved: floor ceil rsort __exc_add_pc_range_table __exc_add_gp_range __exc_remove_pc_range_table __exc_remove_gp_range make[4]: Leaving

Dear R-help community, I have had trouble in the past installing the latest version of R: we got the errors shown below (the computer specifications and version of R are below that). Does anybody have tips for compiling the latest version of R so that I can avoid these errors? configure make ... ... ... f90: CODE: 0 WORDS, DATA: 0 WORDS gcc -G -L/usr/local/lib -o stats.so init.o kmeans.o

I have noticed on a Centos 4.3 server where I had set some >8 characters passwords for some accounts, that only the first 8 characters are needed (if I forget or mistype the others I login all the same). Can I "move" the live, running system to longer passwords, and how? or is a reinstall necessary? TIA, Marco -- Marco Fioretti mfioretti, at the server

Full_Name: Frank Beimfohr Version: 0.64.1, devel. OS: Solaris 2.5.1 Submission from: (NULL) (129.217.131.31) I try to compile R on my Sparc 4 (Solaris 2.5.1) but the compilation fails. I tried the developer-version and the contributed 0.64.1-Version. I start configure with the --g77-Option. During the compilation it stops with an error, which says that the R/src/library/modreg/src/bsplvd.f

I have determined why there are many "WARNING: Duplicate symbol:" messages. *** My apologies for the length *** There is a lot of detail - but I hope the detail will help R - and others - setup correct options for shared libraries. *** As I press send, I have not stopped testing (my final trial here might not even work) - but! *** the message is that shared libraries do not need to have

On 2015-10-15 15:02, Prof Brian Ripley wrote: > On 15/10/2015 13:32, Michael Felt wrote: >> Hi. >> >> Just wanted to let you know I am getting close to packaging R for AIX in rephrase - would like to be active in keeping R binaries current for AIX. My interest in not in R per se (rather a colleague who has a project that uses R, so I hope to assist him, and others like him).