similar to: gam() and library( modreg )

Hi, Is there any difference in the gam() function in R and Splus? I just tried to do an Ace Plot (plotting the result of the gam() ) on a dataset. R gave me four (the data set has one response and four explanatory variables) ace plot with perfectly straight lines. I kind of felt that it is highly unlikely, so I tried it in Splus. Using the exact commands Splus gave me four completely

Hi there I'm trying to construct a model of mortality risk in 2D space that requires numerical integration of a hazard function, for which I'm using the integrate function. I'm occasionally encountering parameter combinations that cause integrate to terminate with error "Error in integrate... the integral is probably divergent", which I'm not sure how to interpret. The

Hi, Can anyone tell me what might cause this error message? Error in .Fortran("swallocate", as.double(mtx), as.double(wt), as.integer(n), : C/Fortran function name not in load table This occurs when I copied the Splus stepwise() function into R. I can source into R fine, but when I need to call that function on some dataset, I got the above error message. Platform

Hi, Somehow I forgot how to do this... Say I have a command that produced a 28 x 28 data matrix. How can I output the matrix into a txt file (rather than copy/paste the matrix)? Thanks... Kevin ------------------------------------------------- Ko-Kang Kevin Wang Statistical Analysis Division Leader Software Developers' Klub University of Auckland New Zealand

Hi there, I'm using R1.0.1 Windows 98. This file contains some inputs and an aov function code. Can someone check it for me? Somehow I got completely different answer when typing them in R and in Splus. Splus gives me this: > summary( Turnip.aov ) Error: Blocks Df Sum of Sq Mean Sq F Value Pr(F) Residuals 3 163.7367 54.57891 Error: Plots %in% Blocks

Hi there, Just out of curious, is there any difference between loess() and lowess() in R (and Splus in fact). Which one is more often used? Thanks, Ko-Kang Wang ------------------------------------------------------------------------------ Ko-Kang Kevin Wang Statistical Analysis Division Leader Software Developers' Klub (SDK) University of Auckland New Zealand

Hi, Can anyone tell me how I can compile R from source under Windows environemtn (I kind of know how to do it in a UNIX enviroment)? What I mean is, suppose I make some changes in the R base, or reorganising the libraries, and want to compile into a Setup.exe file (like the one located in CRAN), how should I do this? Many thanks in advance... Ko-Kang Wang

Hi, I am interested in seeing the LaTeX version of R manuals (such as An Introduction to R), and I found from CRAN that: "The texinfo sources of the latest version of these documents are contained in every R source distribution (in the subdirectory doc/manual of the extracted archive). " However when I went into that directory I only found the pdf and html version. Are there any

Hi, Suppose I have a dataset with 10 columns, let's call it "foo". Now if I want to extract out only column 2 ~ 8, then I know I can use either: foo[ ,2:8] or fooNew <- list( foo[ ,2:8] ) (Is there any other alternative, just out of curiosity?) But, if I only want, say, column 1, 4 and 7, I tried: fooNew <- list( x = foo[ ,1], y = foo[ ,4], z = foo[ , 7] )

Hi, I was tutoring in the lab when a student asked me this question. Is it possible to save the work done in R, then source it back in AND display all the work within R later? I know that one can save the history (i.e. all the codes in a session) in *.R format, then source it back in at a later stage. However the historical codes will not be displayed within R, only the line source(...) is

Well, R is not S+ nor SPSS. Although it is sort of similar to S+ in terms of how you use it... You can get it from http://cran.r-project.org/ To know more about what it really is, you can get my PowerPoint presentation from: http://www.stat.auckland.ac.nz/~kwan022/pub/R/Introduction/ or and article I wrote from: http://www.stat.auckland.ac.nz/~kwan022/pub/SDK/SAD/Journal/ If you're a

Hi there, I'm trying to get the manual for an R package (that I'm creating) to work... Firstly, I created the *.Rd files (by following the instructions in "Writing R Extensions" and using prompt() in R, then edit the *.Rd files. I then copy them into the "pkg/man" directory as suggested by the manual. However when I load the library (successfully) in R, I cannot

Hi, Suppose I have a matrix with, say 12 columns. I would like to extract out column 2 ~ 8 and 11 ~ 12 then combine them together. I tried with success to extract out the columns by doing: foo <- test[,2:8] goo <- test[,11:12] However then I am having trouble combining foo and goo. Helps are appreciated! Cheers, Kevin ----------------------------------- Ko-Kang Kevin Wang

Hi, I input this command on a data matrix: > apply( traffic, 2, function(z){z-mean(z)}) and got the following error messages: Error in sum(..., na.rm = na.rm) : invalid "mode" of argument Can anyone tell me what is wrong here? Running R1.2.2 on Windows ME. Cheers, Kevin ------------------------------------------------- Ko-Kang Kevin Wang Statistical Analysis Division

At 06:09 AM 5/1/00 +0100, Prof Brian D Ripley wrote: >On Sun, 30 Apr 2000, Stephen R. Laniel wrote: > >> I was just now surprised to note that functions to go generalized additive >> models don't appear to exist under R 1.000. In particular, the gam() and >> loess() functions aren't there. Are they hidden somewhere and I just >> haven't noticed? >

Hi, Suppose I've got a data set that I found the eigenvalues and eigenvectors. Then I want to draw a screeplot for the eigenvalues. However it returns: Error in matrix(w.m, nc = NC) : negative extents to matrix Then I tried a plot() function on the eigenvalues of the data set, and I can successfully draw it! And the output looks like what the screeplot would show to me. Is there any

Hi there, I'm trying to write an R library (for Windows version) when I encountered this problem. I put in a dataset called mussels into a sub-folder, data (I saw this is how it is done in other libraries). However when I load the library in R and typed: data(mussels) it complains it cannot find the data set in the library. Everything else works fine (so far), am I missing something

Hi, I've been reading the Data Import and Export manual (page 25 on Connection chapter) but somehow I can't manage to get what I want. I have a 28x28 distance matrix, which I would like to export to a file. What I did was something like: zz <- file("ex.data", "w") # open an output file connection cat( traffic.manDist, file = zz ) # traffic.manDist is my

Hi, Suppose I want to test a set of random numbers (using the Binormal random number generator), input the following command to generate a set of random numbers: test <- rbinom( 10000000, 1, 0.5 ) How can I, after obtaining the result, export the vector "test" into an text file? Then, suppose I want to do something like: > x <- 1e10 > x [1] 1e+10

Hi, Is it possible to create a legend in a pairs() plot? For example, suppose I have the following R codes: data(iris) pairs(iris[1:4], main = "Anderson's Iris Data -- 3 species", pch = 21, bg = c("red", "green3", "blue")[codes(iris$Species)]) How can I created a legend that shows which colour represents to which Iris species? Thanks,