Re: [R] Interpolating / smoothing missing time series data
Francisco J. Zagmutt wrote: I don't have much experience in the subject but it seems that library(akima) should be useful for your problem. Try library(help=akima) to see a list of the functions available in the library. I hope this helps Francisco Yes, function aspline() of package akima is well suited for such things: no wiggles like in spline() and less variance reducing than approx(). But in any case: excessive interpolation will definitely lead to biased results, in particular artificial autocorrelations. If ever possible, David should look for methods, capable of dealing with missing data directly. Thomas P. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Creating very small plots (2.5 cm wide) in Sweave
Dear Francisco, thanks for your solution. It turns out that it's best for me to use \setkeys{Gin}{width=0.15\textwidth} directly before I call the plot - that seems to work just fine. Andrwe On Thu, Sep 08, 2005 at 05:44:59AM +, Francisco J. Zagmutt wrote: Others may propose more elegant solutions but, in windows one quick an dirty option would be to change the argument 'pin' and 'fin' within par to get an image of exactly 1 inch (2.54 cm) i.e. y - c(40, 46, 39, 44, 23, 36, 70, 39, 30, 73, 53, 74) x - c(6, 4, 3, 6, 1, 5, 6, 2, 1, 8, 4, 6) par(pin=c(1,1), fin=c(1,1)) plot(x, y, xlab=, ylab=) abline(h=mean(y), col=red) #Save the plot in bmp format savePlot(myplot, bmp) and then manually crop the picture using your favorite picture package or even within a word processor. I hope this helps Francisco From: Andrew Robinson [EMAIL PROTECTED] To: R-Help Discussion r-help@stat.math.ethz.ch Subject: [R] Creating very small plots (2.5 cm wide) in Sweave Date: Thu, 8 Sep 2005 13:40:17 +1000 Hi everyone, I was wondering if anyone has any code they could share for creating thumbnail plots in Sweave. For example, I'd like a plot like the following: y - c(40, 46, 39, 44, 23, 36, 70, 39, 30, 73, 53, 74) x - c(6, 4, 3, 6, 1, 5, 6, 2, 1, 8, 4, 6) opar - par(mar=c(3,3,0,0)) plot(x, y, xlab=, ylab=) abline(h=mean(y), col=red) par(opar) to come out about 2.5 cm wide. Thanks for any assistance, Andrew -- Andrew Robinson Senior Lecturer in Statistics Tel: +61-3-8344-9763 Department of Mathematics and StatisticsFax: +61-3-8344-4599 University of Melbourne, VIC 3010 Australia Email: [EMAIL PROTECTED]Website: http://www.ms.unimelb.edu.au __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Andrew Robinson Senior Lecturer in Statistics Tel: +61-3-8344-9763 Department of Mathematics and StatisticsFax: +61-3-8344-4599 University of Melbourne, VIC 3010 Australia Email: [EMAIL PROTECTED]Website: http://www.ms.unimelb.edu.au __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Text Size in Legend
Hello, I need to reduce the size of the text in a legend since the legend is overlapping with the curves in my plot. I've not been able to identify any way to achieve this in the documentation. Anyone have any suggestions on how to scale down the text or the overall legend? Thanks in advance for your help! Chris Diehl [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Text Size in Legend
Hi Chris, To change the scale of the whole legend you can use the argument 'cex' in legend. I hope this helps! Regards, Roula = Spyridoula Tsonaka Doctoral Student Biostatistical Centre Catholic University of Leuven Kapucijnenvoer 35 B-3000 Leuven Belgium Tel: +32/16/336899 Fax: +32/16/337015 - Original Message - From: Chris Diehl [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Sent: Wednesday, September 07, 2005 10:31 PM Subject: [R] Text Size in Legend Hello, I need to reduce the size of the text in a legend since the legend is overlapping with the curves in my plot. I've not been able to identify any way to achieve this in the documentation. Anyone have any suggestions on how to scale down the text or the overall legend? Thanks in advance for your help! Chris Diehl [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Using R map data to determine associated state for a coordinate?
Hi! I have no idea if this is maybe an easy task utilizing R since I read there is geographical map data in some package: I have a huge number of geographical points with their coordinates in Germany. Now I want to determine for each point in which Bundesland = state it is located. Can anybody tell me if this is doable relatively easy in R and if so give me some hints or links how to do it? Thanks a million, Werner __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Too long to display problem
Dear list, I used read.xls in gdata package to read a worksheet in which certain field contains very long character strings (nucleotides sequence, nchar 10,000). Then, the values in these fields are automatically converted to TOO LONG TO DISPLAY. How can I get those original characters instead of TOO LONG TO DISPLAY? Thanks, Wuming __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Survival model with cross-classified shared frailties
Dear All, The coxph function in the survival package allows multiple frailty terms. In all the examples I saw, however, the frailty terms are nested. What will happen if I have non-nested (that is, cross-classified) frailties in the model? Will the model still work? Do I need to take special cares when specifying these models? Thanks! Shige [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] variables from command line
Omar == Omar Lakkis [EMAIL PROTECTED] on Wed, 7 Sep 2005 10:47:43 -0400 writes: Omar How can I pass parameters to an R script from the Omar command line. And how can I read them from within the Omar script? Omar This is how I want to invoke the script: R CMD BATCH Omar r.in r.out input values Omar The script with read in the input values, process them Omar and spit the output to r.out. I think commandArgs()should solve this. Regard, Martin Maechler __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] FW: Re: Doubt about nested aov output
Your response nicely clarifies a question that I've had for a long time, but which I've dealt with by giving each subject a unique label. Unless I'm missing something, both techniques should work as the toy example below gives exactly the same output in all 3 cases below (forgetting about the convergence problem). Would there be a reason to prefer labeling the levels one way or another or is it just a matter of convenience? library(lmer) y - rnorm(15) cond - gl(3, 5, 15) obs - gl(15, 1) subj - gl(5, 1, 15) dd - data.frame(y = y, cond = cond, obs = obs, subj = subj) l1 - lmer(y~cond + (1|cond:obs), dd) l2 - lmer(y~cond + (1|cond:subj), dd) l3 - lmer(y~cond + (1|obs), dd) Douglas Bates a écrit: The difference between models like lmer(Glycogen~Treatment+(1|Rat)+(1|Rat:Liver)) and lmer(Glycogen~Treatment+(1|Treatment:Rat)+(1|Treatment:Rat:Liver)) is more about the meaning of the levels of Rat than about the meaning of Treatment. As I understood it there are three different rats labelled 1. There is a rat 1 on treatment 1 and a rat 1 on treatment 2 and a rat 1 on treatment 3. Thus the levels of Rat do not designate the experimental unit, it is the levels of Treatment:Rat that do this. -- Ken Knoblauch Inserm U371 Cerveau et Vision Dept. of Cognitive Neuroscience 18 avenue du Doyen Lépine 69500 Bron France tel: +33 (0)4 72 91 34 77 fax: +33 (0)4 72 91 34 61 portable: +33 (0)6 84 10 64 10 http://www.lyon.inserm.fr/371/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Too long to display problem
Dear list, Please ignore this thread - the TOO LONG TO DISPLAY is brought by another tool when parsing data sets. Sorry for this ... Wuming On 9/8/05, Wuming Gong [EMAIL PROTECTED] wrote: Dear list, I used read.xls in gdata package to read a worksheet in which certain field contains very long character strings (nucleotides sequence, nchar 10,000). Then, the values in these fields are automatically converted to TOO LONG TO DISPLAY. How can I get those original characters instead of TOO LONG TO DISPLAY? Thanks, Wuming __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Using R map data to determine associated state for a coordinate?
Werner Wernersen wrote: Hi! I have no idea if this is maybe an easy task utilizing R since I read there is geographical map data in some package: I have a huge number of geographical points with their coordinates in Germany. Now I want to determine for each point in which Bundesland = state it is located. Can anybody tell me if this is doable relatively easy in R and if so give me some hints or links how to do it? Thanks a million, Werner Hello Werner, two building blocks, but don't know if the precision meets your needs. 1. Do you have a good map of Germany *with* Federal States? * If YES and if it's free: == I would be interested! Please post it's source. * If NO: == Downloadable map data are available on: http://www.vdstech.com/map_data.htm 2. The following approach reads and converts a shapefile with functions from maptools and then follows the example of inside.owin() from the spatstat package. Hope that helps Thomas Petzoldt ## library(maptools) library(spatstat) ger - read.shape(germany.shp) plot(ger) pger - Map2poly(ger) sx- pger[[13]] lines(sx, type=l, col=red) # Saxony ;-) ## Create an owin (observation window) object # direction of coordinates must be reversed, in some cases # if error message: remove rev()'s saxony - owin(poly=list(x=rev(sx[,1]), y=rev(sx[,2]))) # random points in rectangle x - runif(1000, min= 6, max=15) y - runif(1000, min=46, max=56) ok - inside.owin(x, y, saxony) points(x[ok], y[ok]) points(x[!ok], y[!ok], pch=.) ## __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Interpolating / smoothing missing time series data
On 9/7/05 10:19 PM, Gabor Grothendieck [EMAIL PROTECTED] wrote: On 9/7/05, David James [EMAIL PROTECTED] wrote: The purpose of this email is to ask for pre-built procedures or techniques for smoothing and interpolating missing time series data. I've made some headway on my problem in my spare time. I started with an irregular time series with lots of missing data. It even had duplicated data. Thanks to zoo, I've cleaned that up -- now I have a regular time series with lots of NA's. I want to use a regression model (i.e. ARIMA) to ill in the gaps. I am certainly open to other suggestions, especially if they are easy to implement. My specific questions: 1. Presumably, once I get ARIMA working, I still have the problem of predicting the past missing values -- I've only seen examples of predicting into the future. 2. When predicting the past (backcasting), I also want to take reasonable steps to make the data look smooth. I guess I'm looking for a really good example in a textbook or white paper (or just an R guru with some experience in this area) that can offer some guidance. Venables and Ripley was a great start (Modern Applied Statistics with S). I really had hoped that the Seasonal ARIMA Models section on page 405 would help. It was helpful, but only to a point. I have a hunch (based on me crashing arima numerous times -- maybe I'm just new to this and doing things that are unreasonable?) that using hourly data just does not mesh well with the seasonal arima code? Not sure if this answers your question but if you are looking for something simple then na.approx in the zoo package will linearly interpolate for you. z - zoo(c(1,2,NA,4,5)) na.approx(z) 1 2 3 4 5 1 2 3 4 5 Alternatively, if you are looking for more smoothing, you could look at using a moving average or median applied at points of interest with an appropriate window size--see wapply in the gplots package (gregmisc bundle). There are a number of other functions that can accomplish the same task. A search for moving window or moving average in the archives may produce some other ideas. Sean __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Using R map data to determine associated state for a coordinate?
On Thu, 8 Sep 2005, Thomas Petzoldt wrote: Werner Wernersen wrote: Hi! I have no idea if this is maybe an easy task utilizing R since I read there is geographical map data in some package: I have a huge number of geographical points with their coordinates in Germany. Now I want to determine for each point in which Bundesland = state it is located. Can anybody tell me if this is doable relatively easy in R and if so give me some hints or links how to do it? Thanks a million, Werner Hello Werner, two building blocks, but don't know if the precision meets your needs. 1. Do you have a good map of Germany *with* Federal States? * If YES and if it's free: == I would be interested! Please post it's source. * If NO: == Downloadable map data are available on: http://www.vdstech.com/map_data.htm 2. The following approach reads and converts a shapefile with functions from maptools and then follows the example of inside.owin() from the spatstat package. The example code will work very well, but since yesterday, when we released a new version of maptools depending on the sp package, it can look like: library(maptools) Loading required package: foreign Loading required package: sp nc - readShapePoly(system.file(shapes/sids.shp, package=maptools)[1]) plot(nc, lwd=2, border=grey) bbox(nc) min max r1 -84.32385 -75.45698 r2 33.88199 36.58965 x - runif(1000, min=-84.32385, max=-75.45698) y - runif(1000, min=33.88199, max=36.58965) xypts - SpatialPoints(cbind(x, y)) plot(xypts, add=TRUE, pch=19, cex=0.2) where_am_i - overlay(xypts, nc) plot(xypts[is.na(where_am_i),], add=TRUE, pch=19, cex=0.2, col=grey80) summary(where_am_i) Min. 1st Qu. MedianMean 3rd Qu.Max.NA's 1.00 29.00 51.00 53.11 77.00 100.00 450.00 and in this case the points would be read into the SpatialPoints object directly. Should overlay have trouble with the huge number of points, you could take them in smaller batches, storing the intermediate results. As Thomas said, you need the boundaries of the Bundesland first, and the accuracy of your results will depend on the degree of detail of the boundary polygons. Roger Bivand Hope that helps Thomas Petzoldt ## library(maptools) library(spatstat) ger - read.shape(germany.shp) plot(ger) pger - Map2poly(ger) sx- pger[[13]] lines(sx, type=l, col=red) # Saxony ;-) ## Create an owin (observation window) object # direction of coordinates must be reversed, in some cases # if error message: remove rev()'s saxony - owin(poly=list(x=rev(sx[,1]), y=rev(sx[,2]))) # random points in rectangle x - runif(1000, min= 6, max=15) y - runif(1000, min=46, max=56) ok - inside.owin(x, y, saxony) points(x[ok], y[ok]) points(x[!ok], y[!ok], pch=.) ## __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Roger Bivand Economic Geography Section, Department of Economics, Norwegian School of Economics and Business Administration, Helleveien 30, N-5045 Bergen, Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43 e-mail: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Prediction with multiple zeros in the dependent variable
On 08-Sep-05 John Sorkin wrote: I have a batch of data in each line of data contains three values, calcium score, age, and sex. I would like to predict calcium scores as a function of age and sex, i.e. calcium=f(age,sex). Unfortunately the calcium scorers have a very ugly distribution. There are multiple zeros, and multiple values between 300 and 600. There are no values between zero and 300. Needless to say, the calcium scores are not normally distributed, however, the values between 300 and 600 have a distribution that is log normal. As you might imagine, the residuals from the regression are not normally distributed and thus violates the basic assumption of regression analyses. Does anyone have a suggestion for a method (or a transformation) that will allow me predict calcium from age and sex without violating the assumptions of the model? Thanks, John From your description (but only from your description) one might be tempted to suggest (borrowing a term from Joe Shafer) a semi-continuous model. This means that each observation either takes a discrete value, or takes a value with a continuous distribution. In your case this might be Score = 0 with probability p which is a function of Age and Sex Score = X with probability (1-p) where X has a log-normal distribution. Whether using such a model, for data arising in the context you refer to, is reasonable depends on whether Calcium Score = 0 is a reasonable description of a biological state of things. Even if not a reasonable biological state, it may be a reasonable description of the outcome of a measurement process (e.g. too small to measure), in which case there may be a consequential issue -- what is the likely distribution of calcium values which give rise to Score = 0? (Though your data may be uninformative about this). However, if your aim is simply predicting calcium scores, then this may be irrelevant. With such a model, you should be able to make progress by using a log-linear model for the probability p (which may be adequately addressed by simply using a logistic regression for the event Score = 0 or equivalently score != 0, though you may need to be careful about how you represent Age as a covariate; Sex, being binary, should not present problems). This then allowes you to predict the probability of zero score, and the complementary probability of non-zero score. Then you can consider the problem of estimating the relationship between Score and (Age, Sex) conditional on Score != 0. This, in turn, is no more (and no less!) complicated than estimating the continuous distribution of non-zero scores from the subset of the data which carries such scores. If the distribution of non-zero scores were (as you suggest) a simple log-normal distribution, then a regression of log(Score) on Age and Sex might do well. However, from your description, it may not be a simple log-normal. The absence of scores between 0 and 300, and the containment of score values betweem 300 and 600, suggests a 3-parameter log-normal in which, as well as the mean and SD for the normal distribution of log(X) there is also a lower limit S0, so that it is log(S - S0) which has the N(mean,SD^2) distribution. The distribution might be more complicated than this. So, in summary, provided a semi-continuous model is acceptable, you can proceed by estimating its two aspects separately: The discrete part by a logistic (or other suitable binary) regression, using 'glm' in R; the continuous part by a suitable regression (using e.g. 'lm' in R) perhaps after suitable transformation (though this may need care). In each case, it is only the relevant part of the data (the proportions with Score = 0 and Score != 0 on the one hand, the values of Score where Score != 0 on the other hand, in each case using the corresponding (Age, Sex) as covariates) which will be needed. Once you have these estimated models, they can be used straightforwardly for prediction: Given Age and Sex, the Score will be zero with estimated probability p(Age,Sex) or, with probability (1 - p(Age,Sex)), will have a distribution implied by your regression. So the structure of the predicted values will be the same as the structure of the observed values. All very straightforward, provided this is a reasonable way to go. However, there is a complication in that the above might well not be a reasonable model (as hinted at above). As an example, consider the following (purely hypothetical assumptions). 1. The true distribution of Calcium Score is (say) simple log-normal such that log(Score) is normal with mean linearly dependent on Age and Sex, in all subjects. 2. In attempting to measure true Score (i.e. in obtaining observed Calcium Score data), there is a probability that Score = 0 will be obtained, and this probability depends on the true Score (e.g. the smaller the true Score, the higher the probability of obtaining Score = 0). The resulting non-zero score data will then
[R] Time series ARIMAX and multivariate models
Dear List, The purpose of this e-mail is to ask about R time series procedures - as a biologist with only basic time series knowledge and about a year's experience in R. I have been using ARIMAX models with seasonal components on seasonal data. However I am now moving on to annual data (with only 34 time points) and understand that ARIMA is not suitable for these shorter time periods - does R have other, more robust, methods? I have tried looking through the R help pages documentation for packages but am unsure what model type is suitable. Secondly, I wish to start building multivariate time series models in R to look at how fish condition (for several sizes of fish) is affected by environmental factors and numbers of prey. It would be great if someone could suggest what R packages/documentation would be useful to research? Thankyou, Lillian. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] tcltk, X11 protocol error: Bug?
Dear Nicholas, This problem has been reported before (enter X11 protocol error on the R site search at http://finzi.psych.upenn.edu/search.html to see the previous threads), but as far as I know, there's no definitive explanation or solution. As well, things appear to work fine, despite the warnings. The way I handle the problem in the Rcmdr package is simply to intercept the warnings. I hope this helps, John John Fox Department of Sociology McMaster University Hamilton, Ontario Canada L8S 4M4 905-525-9140x23604 http://socserv.mcmaster.ca/jfox -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Nicholas Lewin-Koh Sent: Monday, September 05, 2005 5:16 PM To: [EMAIL PROTECTED] Subject: [R] tcltk, X11 protocol error: Bug? Hi, I am having trouble debugging this one. The code is attached below, but it seems to be a problem at the C-tk interface. If I run this 1 time there are no problems if I run it more than once I start to get warnings that increase in multiples of 11 everytime I run it. Here is a sample session source(clrramp2.r) Loading required package: tcltk Loading Tcl/Tk interface ... done clrRamp() tt-clrRamp() tt function (n) { x - ramp(seq(0, 1, length = n)) rgb(x[, 1], x[, 2], x[, 3], max = 255) } environment: 0x8b8674c image(matrix(1:10),col=tt(10)) tt-clrRamp() There were 22 warnings (use warnings() to see them) image(matrix(1:10),col=tt(10)) There were 11 warnings (use warnings() to see them) warnings() Warning messages: 1: X11 protocol error: BadWindow (invalid Window parameter) 2: X11 protocol error: BadWindow (invalid Window parameter) 3: X11 protocol error: BadWindow (invalid Window parameter) 4: X11 protocol error: BadWindow (invalid Window parameter) 5: X11 protocol error: BadWindow (invalid Window parameter) 6: X11 protocol error: BadWindow (invalid Window parameter) 7: X11 protocol error: BadWindow (invalid Window parameter) 8: X11 protocol error: BadWindow (invalid Window parameter) 9: X11 protocol error: BadWindow (invalid Window parameter) 10: X11 protocol error: BadWindow (invalid Window parameter) 11: X11 protocol error: BadWindow (invalid Window parameter) I am running R-2.1.1 on ubuntu linux 5.04, compiled from source (not the deb package). My version of tcl/tk is 8.4. The code is below. If anyone sees something I am doing foolish let me know, otherwise I will file a bug report. Nicholas # File clrramp2.r ## require(tcltk) clrRamp - function(n.col, b.color=NULL,e.color=NULL){ B.ChangeColor - function() { b.color - tclvalue(tkcmd(tk_chooseColor,initialcolor=e.color, title=Choose a color)) if (nchar(b.color)0){ tkconfigure(canvas.b,bg=b.color) Rmp.Draw() } } E.ChangeColor - function() { e.color - tclvalue(tkcmd(tk_chooseColor,initialcolor=e.color, title=Choose a color)) ##cat(e.color) if (nchar(e.color)0){ tkconfigure(canvas.e,bg=e.color) Rmp.Draw() } } Rmp.Draw -function(){ cr-colorRampPalette(c(b.color,e.color),space=Lab,interpola te=spline) rmpcol - cr(n.col) #rmpcol-rgb( rmpcol[,1],rmpcol[,2],rmpcol[,3]) inc - 300/n.col xl - 0 for(i in 1:n.col){ ##item - tkitemconfigure(canvas.r,barlst[[i]],fill=rmpcol[i],outline=rmpcol[i]) #xl - xl+inc } } save.ramp - function(){ cr-colorRampPalette(c(b.color,e.color),space=Lab,interpola te=spline) tkdestroy(tt) ##invisible(cr) } tt - tktoplevel() tkwm.title(tt,Color Ramp Tool) frame - tkframe(tt) bframe - tkframe(frame,relief=groove,borderwidth=1) if(is.null(b.color)) b.color - blue if(is.null(e.color)) e.color - yellow if(missing(n.col)) n.col - 100 canvas.b - tkcanvas(bframe,width=50,height=25,bg=b.color) canvas.e - tkcanvas(bframe,width=50,height=25,bg=e.color) canvas.r - tkcanvas(tt,width=300,height=50,bg=white) BColor.button - tkbutton(bframe,text=Begin Color,command=B.ChangeColor) ##tkgrid(canvas.b,BColor.button) EColor.button - tkbutton(bframe,text=End Color,command=E.ChangeColor) killbutton - tkbutton(bframe,text=Save,command=save.ramp) tkgrid(canvas.b,BColor.button,canvas.e,EColor.button) tkgrid(bframe) tkgrid(frame) tkgrid(canvas.r) tkgrid(killbutton) cr-colorRampPalette(c(b.color,e.color),space=Lab,interpolat e=spline) ##rmpcol - hex(mixcolor(alpha,bc,ec,where=LUV)) rmpcol - cr(n.col) inc - 300/n.col xl - 0 #barlst - vector(length=n.col,mode=list) barlst - tclArray() for(i in 1:n.col){ item-tkcreate(canvas.r,rect,xl,0,xl+inc,50, fill=rmpcol[i],outline=rmpcol[i]) ##tkaddtag(canvas.r, point, withtag, item)
[R] Converting a matrix to a dataframe: how to prevent conversion to factor
Colleages I am running R 2.1.0 on a Mac (same problem occurs in Linux). In some situations, I have mixed text/numeric data that is stored as characters in a matrix. If I convert this matrix to a dataframe, the numeric data becomes factors, not what I intend. TEXT- paste(Text, 1:4, sep=) NUMBERS- 10 + 4:1 MATRIX- cbind(TEXT, NUMBERS) FRAME- as.data.frame(MATRIX) str(FRAME) `data.frame':4 obs. of 2 variables: $ TEXT : Factor w/ 4 levels Text1,Text2,..: 1 2 3 4 $ NUMBERS: Factor w/ 4 levels 11,12,13,..: 4 3 2 1 One work-around is to write the matrix (or the dataframe) to a file, then read the file back using the as.is argument. write.table(MATRIX, JUNK, row.names=F) NEWFRAME- read.table(JUNK, as.is=T, header=T) str(NEWFRAME) `data.frame':4 obs. of 2 variables: $ TEXT : chr Text1 Text2 Text3 Text4 $ NUMBERS: int 14 13 12 11 This restores the NUMBERS to their intended mode (integers, not factors). The text column is also not read as a factor (not a problem for me). It appears that the function AsIs [I(x)] would enable me to accomplish this without the write/read steps. However, it is not obvious to me how to implement I(x). Can anyone advise? Thanks in advance. Dennis Fisher Dennis Fisher MD P (The P Less Than Company) Phone: 1-866-PLessThan (1-866-753-7784) Fax: 1-415-564-2220 www.PLessThan.com [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Prediction with multiple zeros in the dependent variable
John Sorkin wrote: I have a batch of data in each line of data contains three values, calcium score, age, and sex. I would like to predict calcium scores as a function of age and sex, i.e. calcium=f(age,sex). Unfortunately the calcium scorers have a very ugly distribution. There are multiple zeros, and multiple values between 300 and 600. There are no values between zero and 300. Needless to say, the calcium scores are not normally distributed, however, the values between 300 and 600 have a distribution that is log normal. As you might imagine, the residuals from the regression are not normally distributed and thus violates the basic assumption of regression analyses. Does anyone have a suggestion for a method (or a transformation) that will allow me predict calcium from age and sex without violating the assumptions of the model? Thanks, John John Sorkin M.D., Ph.D. Chief, Biostatistics and Informatics Baltimore VA Medical Center GRECC and University of Maryland School of Medicine Claude Pepper OAIC John - first I would try a proportional odds model, with zero as its own category then treating all other values as continuous or collapsing them into 20-tiles. If the PO assumption happens to hold (look at partial residual plots) you have a simple solution. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Time Series Analysis: book?
There has been a few questions on the subject lately. Is there any book on the subject, if possible with a computer processing flavor, that you would highly recommend? Many thanks in advance, -- Jean-Luc __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Converting a matrix to a dataframe: how to prevent conversion to factor
Dennis Fisher [EMAIL PROTECTED] writes: Colleages I am running R 2.1.0 on a Mac (same problem occurs in Linux). In some situations, I have mixed text/numeric data that is stored as characters in a matrix. If I convert this matrix to a dataframe, the numeric data becomes factors, not what I intend. TEXT- paste(Text, 1:4, sep=) NUMBERS- 10 + 4:1 MATRIX- cbind(TEXT, NUMBERS) FRAME- as.data.frame(MATRIX) str(FRAME) `data.frame':4 obs. of 2 variables: $ TEXT : Factor w/ 4 levels Text1,Text2,..: 1 2 3 4 $ NUMBERS: Factor w/ 4 levels 11,12,13,..: 4 3 2 1 One work-around is to write the matrix (or the dataframe) to a file, then read the file back using the as.is argument. write.table(MATRIX, JUNK, row.names=F) NEWFRAME- read.table(JUNK, as.is=T, header=T) str(NEWFRAME) `data.frame':4 obs. of 2 variables: $ TEXT : chr Text1 Text2 Text3 Text4 $ NUMBERS: int 14 13 12 11 This restores the NUMBERS to their intended mode (integers, not factors). The text column is also not read as a factor (not a problem for me). It appears that the function AsIs [I(x)] would enable me to accomplish this without the write/read steps. However, it is not obvious to me how to implement I(x). Can anyone advise? I don't think that is going to help There are really several issues here: Your numeric column was converted to character by the cbind, using as.data.frame(I(MATRIX)) will not split it into individual columns, and things like apply(MATRIX,2,f) may do the right thing to begin with, but then there's coercion due to an implicit cbind at the end. It's a bit awkward, but this may do it: FRAME - as.data.frame(lapply(split(MATRIX,col(MATRIX)),type.convert)) names(FRAME) - colnames(MATRIX) str(FRAME) `data.frame': 4 obs. of 2 variables: $ TEXT : Factor w/ 4 levels Text1,Text2,..: 1 2 3 4 $ NUMBERS: int 14 13 12 11 whereas this isn't right: str(apply(MATRIX,2,type.convert)) int [1:4, 1:2] 1 2 3 4 14 13 12 11 - attr(*, dimnames)=List of 2 ..$ : NULL ..$ : chr [1:2] TEXT NUMBERS -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] FW: Re: Doubt about nested aov output
On 9/8/05, Ken Knoblauch [EMAIL PROTECTED] wrote: Your response nicely clarifies a question that I've had for a long time, but which I've dealt with by giving each subject a unique label. Unless I'm missing something, both techniques should work as the toy example below gives exactly the same output in all 3 cases below (forgetting about the convergence problem). Would there be a reason to prefer labeling the levels one way or another or is it just a matter of convenience? library(lmer) y - rnorm(15) cond - gl(3, 5, 15) obs - gl(15, 1) subj - gl(5, 1, 15) dd - data.frame(y = y, cond = cond, obs = obs, subj = subj) l1 - lmer(y~cond + (1|cond:obs), dd) l2 - lmer(y~cond + (1|cond:subj), dd) l3 - lmer(y~cond + (1|obs), dd) I prefer to have a grouping factor constructed with unique levels for each distinct unit. The only reason I mention constructions like Treatment:Rat in the original part of this thread is that data are often provided in that form. Reusing subject labels within another group is awkward and can be error prone. One of the data sets I examine in the MlmSoftRev vignette of the mlmRev package is called Exam and has student identifiers within schools. The student identifiers are not unique but the school:student combination should be. It isn't. These data have been analyzed in scores of books and articles and apparently none of the other authors bothered to check this. There are some interesting ramifications such as some of the schools that are classified as mixed-sex schools are likely single-sex schools because the only student of one of the sexes in that school is apparently mislabelled. BTW, in your example you have only one observation per level of 'obs' so you can't use obs as a grouping factor as this variance component would be completely confounded with the per-observation noise. Douglas Bates a écrit: The difference between models like lmer(Glycogen~Treatment+(1|Rat)+(1|Rat:Liver)) and lmer(Glycogen~Treatment+(1|Treatment:Rat)+(1|Treatment:Rat:Liver)) is more about the meaning of the levels of Rat than about the meaning of Treatment. As I understood it there are three different rats labelled 1. There is a rat 1 on treatment 1 and a rat 1 on treatment 2 and a rat 1 on treatment 3. Thus the levels of Rat do not designate the experimental unit, it is the levels of Treatment:Rat that do this. -- Ken Knoblauch Inserm U371 Cerveau et Vision Dept. of Cognitive Neuroscience 18 avenue du Doyen Lépine 69500 Bron France tel: +33 (0)4 72 91 34 77 fax: +33 (0)4 72 91 34 61 portable: +33 (0)6 84 10 64 10 http://www.lyon.inserm.fr/371/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] FW: Re: Doubt about nested aov output
Thank you for your response. The single response/observer most probably explains the complaints that lmer was giving for my example. Maybe this small modification provides a better example and corrects a more serious error in my previous post: library(lme4) y-rnorm(30) cond - rep(gl(3,5,15), 2) obs-rep(gl(15,1), 2) subj-rep(gl(5,1,15), 2) dd-data.frame(y=y,cond=cond,obs=obs,subj=subj) l1 - lmer(y~cond + (1|cond:obs), data=dd) l2 - lmer(y~cond + (1|cond:subj), data=dd) l3 - lmer(y~cond + (1|obs), dd) Understanding the notation is often about 99% of the job, and it is very helpful to see multiple ways to accomplish the same thing. Douglas Bates a écrit: I prefer to have a grouping factor constructed with unique levels for each distinct unit. The only reason I mention constructions like Treatment:Rat in the original part of this thread is that data are often provided in that form. Reusing subject labels within another group is awkward and can be error prone. One of the data sets I examine in the MlmSoftRev vignette of the mlmRev package is called Exam and has student identifiers within schools. The student identifiers are not unique but the school:student combination should be. It isn't. These data have been analyzed in scores of books and articles and apparently none of the other authors bothered to check this. There are some interesting ramifications such as some of the schools that are classified as mixed-sex schools are likely single-sex schools because the only student of one of the sexes in that school is apparently mislabelled. BTW, in your example you have only one observation per level of 'obs' so you can't use obs as a grouping factor as this variance component would be completely confounded with the per-observation noise. Douglas Bates a écrit: The difference between models like lmer(Glycogen~Treatment+(1|Rat)+(1|Rat:Liver)) and lmer(Glycogen~Treatment+(1|Treatment:Rat)+(1|Treatment:Rat:Liver)) is more about the meaning of the levels of Rat than about the meaning of Treatment. As I understood it there are three different rats labelled 1. There is a rat 1 on treatment 1 and a rat 1 on treatment 2 and a rat 1 on treatment 3. Thus the levels of Rat do not designate the experimental unit, it is the levels of Treatment:Rat that do this. -- Ken Knoblauch Inserm U371 Cerveau et Vision Dept. of Cognitive Neuroscience 18 avenue du Doyen Lépine 69500 Bron France tel: +33 (0)4 72 91 34 77 fax: +33 (0)4 72 91 34 61 portable: +33 (0)6 84 10 64 10 http://www.lyon.inserm.fr/371/ -- Ken Knoblauch Inserm U371 Cerveau et Vision Dept. of Cognitive Neuroscience 18 avenue du Doyen Lépine 69500 Bron France tel: +33 (0)4 72 91 34 77 fax: +33 (0)4 72 91 34 61 portable: +33 (0)6 84 10 64 10 http://www.lyon.inserm.fr/371/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Prediction with multiple zeros in the dependent variable
On Thu, 8 Sep 2005, John Sorkin wrote: I have a batch of data in each line of data contains three values, calcium score, age, and sex. I would like to predict calcium scores as a function of age and sex, i.e. calcium=f(age,sex). Unfortunately the calcium scorers have a very ugly distribution. There are multiple zeros, and multiple values between 300 and 600. There are no values between zero and 300. Needless to say, the calcium scores are not normally distributed, however, the values between 300 and 600 have a distribution that is log normal. [Coronary artery calcium by EBCT, I presume] Our approach to modelling calcium scores is to do it in two parts. First fit something like a logistic regression model where the outcome is zero vs non-zero calcium. Then, for the non-zero use something like a linear regression model for log calcium. You could presumably use such a model for prediction or imputation too, and you can work out means, medians etc from the two models. One particular reason for using this two-part model is that we find different predictors of zero/non-zero and of amount. This makes biological sense -- a factor that makes arterial plaques calcify might well have no impact until you have arterial plaques. Or you could use smooth quantile regression in the rq package. -thomas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Survival model with cross-classified shared frailties
On Thu, 8 Sep 2005, Shige Song wrote: Dear All, The coxph function in the survival package allows multiple frailty terms. Um, no, it doesn't. In all the examples I saw, however, the frailty terms are nested. What will happen if I have non-nested (that is, cross-classified) frailties in the model? This wouldn't work even if it did allow multiple frailty terms. You may want the coxme() function in the kinship package. -thomas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] array indices in synced vectors
Let us start with the following definitions xxx-rep(c(1,2),times=5) yyy-rep(c(1,2),each=5) a-c(11,12) b-matrix(1:4,2,2) a[xxx] produces [1] 11 12 11 12 11 12 11 12 11 12 b[xxx,yyy] produces [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10] [1,]111113333 3 [2,]222224444 4 [3,]111113333 3 [4,]222224444 4 [5,]111113333 3 [6,]222224444 4 [7,]111113333 3 [8,]222224444 4 [9,]111113333 3 [10,]222224444 4 so it does an implicit outer for the indices in xxx and yyy. sapply(1:length(xxx),function(x)b[xxx[x],yyy[x]]) does what I need and produces [1] 1 2 1 2 1 4 3 4 3 4 Is there a function taking xxx,yyy, and b as arguments producing the same result? Essentially, I am asking for a version of lapply and/or sapply which works with functions of more than one argument and takes the iteration arguments as vectors or lists of equal length. -- Erich Neuwirth, Didactic Center for Computer Science University of Vienna Visit our SunSITE at http://sunsite.univie.ac.at Phone: +43-1-4277-39902 Fax: +43-1-4277-9399 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] array indices in synced vectors
On Thu, 8 Sep 2005, Erich Neuwirth wrote: sapply(1:length(xxx),function(x)b[xxx[x],yyy[x]]) does what I need and produces [1] 1 2 1 2 1 4 3 4 3 4 Is there a function taking xxx,yyy, and b as arguments producing the same result? b[cbind(xxx,yyy)] Essentially, I am asking for a version of lapply and/or sapply which works with functions of more than one argument and takes the iteration arguments as vectors or lists of equal length. More generally there is mapply(), but the matrix subscript solution is better in this example mapply(function(i,j) b[i,j], xxx,yyy) [1] 1 2 1 2 1 4 3 4 3 4 -thomas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Predicting responses using ace
I'm trying to run the print method, but according to the documentation it needs as a parameter an object created by |summary.areg.boot| . The thing is that |summary.areg.boot| gives me the following error: Error in bootj[, 1] : incorrect number of dimensions, when I do the simple call --- summary( ace.r) I started the debug browser to see what was going on inside and I noticed that 'bootj' is a numeric class variable with the same number of elements as the 'evaluation' parameter for |areg.boot|. What I found is that it has only one dimension and summary is asking for bootj[, 1], which is an error. Is that the intended behavior and I'm doing something wrong elsewhere, or should I try to adjust it by myself (to boot[1] for example)? In case the answer is the latter I would apretiate some insight about how to do it, 'cause I don't know how to edit the file. Thanks for your help, Luis Pineda On 9/7/05, Frank E Harrell Jr [EMAIL PROTECTED] wrote: Luis Pineda wrote: 2.) I'm evaluating the model's goodness of fit using the Fraction of Variance Unexplained, which I'm calculating as: rsa = za - zs FVUa = sum(rsa*rsa)/(1*var(zs)) #1 is the size of the test set That is not corrected for overfitting. You need to use the print method for the areg.boot object and note the Bootstrap validated R2 -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Predicting responses using ace
I gave a quick read to the documentation again and noticed I misinterpreted it. It was print.summary.areg.boot the method I was referring to (although the summary error should still work). Sorry for the inconvenience Anyway, I used the print method on my |areg.boot| object and I got this: -- Apparent R2 on transformed Y scale: 0.798 Bootstrap validated R2 : 0.681 ... Residuals on transformed scale: Min 1Q Median 3Q Max -1.071312e+00 -2.876245e-01 -3.010081e-02 2.123566e-01 1.867036e+00 Mean S.D. 1.290634e-17 4.462159e-01 -- I suppose thats the R^2 evaluated using the training set, but how do I evaluate the performance of the model on a uncontaminated test set? On 9/8/05, Luis Pineda [EMAIL PROTECTED] wrote: I'm trying to run the print method, but according to the documentation it needs as a parameter an object created by |summary.areg.boot| . [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Prediction with multiple zeros in the dependent variable
John: 1. As George Box long ago emphasized and proved, normality is **NOT** that important in regression, certainly not for estimation and not even for inference in balanced designs. Independence of the observations is far more important. 2. That said, it sounds like what you have here is a mixture of some sort. Before running off to do fancy modeling, I would work very hard to look for some kind of lurking variable or experimental aberration -- what was going on in the experiment or study that might have caused all the zeros? Was there an instrument problem? -- a bad reagent? -- improper handling of the samples? It might very well be that you need to throw away part of the data because it's useless, rather than artificially attempt to model it. 3. And having said that, if a comprehensive model IS called for, one rather cynical approach to take is just to add a grouping variable as a covariate that has a value of 1 for all data in the zero group and 2 for all the nonzero data. Your model is f(age,sex) = 0 for all data in group 1 and your linear or nonlinear regression for group 2. Of course, this merely cloaks the cynicism in respectable dress. It's hard for me to believe that it was Mother Nature and not some kind of experimental problem that you see. A slightly less cynical approach might be to use some sort of changepoint model (in both age and sex) of the form f(age, sex) = g(age,sex) for age=k1 and sex =k2 and h(age,sex) otherwise. Well, perhaps **not** less cynical -- the response data are so widely separated that you'll just be using a bunch of extra (nonlinear, incidentally) parameters to essentially reproduce the use of a covariate. So I guess the point is that unless you already have a previously developed nonlinear model that could explain the behavior you see (perhaps based on some kind of mechanistic reasoning) it's not a good idea to try to develop an artificial empirical model that comprehends all the data. The fact is (a horrible phrase) that no modeling at all is needed for the most important message the data have to convey: rather, focus on the cause of the message instead of statistical artifice. Once you have determined that, you may be able to do something sensible. Clear thinking trumps muddy modeling every time. (Hopefully, this is sufficiently inflammatory that others will vigorously and wisely dispute me). Cheers, -- Bert Gunter Genentech Non-Clinical Statistics South San Francisco, CA The business of the statistician is to catalyze the scientific learning process. - George E. P. Box -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of John Sorkin Sent: Wednesday, September 07, 2005 9:06 PM To: r-help@stat.math.ethz.ch Subject: [R] Prediction with multiple zeros in the dependent variable I have a batch of data in each line of data contains three values, calcium score, age, and sex. I would like to predict calcium scores as a function of age and sex, i.e. calcium=f(age,sex). Unfortunately the calcium scorers have a very ugly distribution. There are multiple zeros, and multiple values between 300 and 600. There are no values between zero and 300. Needless to say, the calcium scores are not normally distributed, however, the values between 300 and 600 have a distribution that is log normal. As you might imagine, the residuals from the regression are not normally distributed and thus violates the basic assumption of regression analyses. Does anyone have a suggestion for a method (or a transformation) that will allow me predict calcium from age and sex without violating the assumptions of the model? Thanks, John John Sorkin M.D., Ph.D. Chief, Biostatistics and Informatics Baltimore VA Medical Center GRECC and University of Maryland School of Medicine Claude Pepper OAIC University of Maryland School of Medicine Division of Gerontology Baltimore VA Medical Center 10 North Greene Street GRECC (BT/18/GR) Baltimore, MD 21201-1524 410-605-7119 -- NOTE NEW EMAIL ADDRESS: [EMAIL PROTECTED] [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] ROracle install problem
Hi, I am trying to install the ROracle package in a Linux-64 machine. I downloaded from Oracle's site their Instant Client bundle but it seems that ROracle needs some stuff not included in that kit in order to compile (in particuar, the 'proc' executable). I did not find any other linux client suite in Oracle's site, (our db runs on a Solaris server, so I can not use the included binaries). Does anybody know how to solve this? Is there any workaround? Thanks, Ariel./ -- Ariel Chernomoretz, Ph.D. Centre de recherche du CHUL 2705 Blv Laurier, bloc T-367 Sainte-Foy, Qc G1V 4G2 (418)-525- ext 46339 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] package installation error (LF versus CR)
Hello, I have the following problem in installing a package (in windows xp) rcmd install -c dlm [ ..stuff deleted ] ... DLL made installing DLL installing R files installing inst files installing data files installing man source files installing indices Errore in load(zfile, envir = envir) : l'input Þ stato danneggiato, LF sostituiti da CR Esecuzione interrotta make[2]: *** [indices] Error 1 make[1]: *** [all] Error 2 make: *** [pkg-dlm] Error 2 *** Installation of dlm failed *** Does anybody please have suggestions? If relevant, the source package was downloaded from a unix server using cvs+ssh Thanks a lot, best, Sonia -- Sonia Petrone Istituto di Metodi Quantitativi Università Bocconi Viale Isonzo 25 20135 Milano, Italia. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] R API call from delphi
Hello, Has anyone tried to call R API from Delphi under windows ? How was it done if it was ? Or has anyone any idea about how it could be done ? Thanks for your answers Laurent Tessier [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Time Series Analysis: book?
TS is a huge topic. The book recomended by statisitcian might be different from the one recommended by econometrician. Finance guy might recommend another. Could you please be more specific? On 9/8/05, [EMAIL PROTECTED] [EMAIL PROTECTED] wrote: There has been a few questions on the subject lately. Is there any book on the subject, if possible with a computer processing flavor, that you would highly recommend? Many thanks in advance, -- Jean-Luc __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- WenSui Liu (http://statcompute.blogspot.com) Senior Decision Support Analyst Cincinnati Children Hospital Medical Center [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] data manipulation
Dear All, I would be grateful if you can help me. My problem is the following: I have a data set like: ID time X1 X2 11 x111 x211 12 x112 x212 21 x121 x221 22 x122 x222 23 x123 x223 where X1 and X2 are 2 covariates and time is the time of observation and ID indicates the cluster. I want to merge the above data by creating a new variable X and type as follows: ID timeXtype 1 1 x111 X1 1 2 x112 X1 1 1 x211 X2 1 2 x212 X2 2 1 x121 X1 2 2 x122 X1 2 3 x123 X1 2 1 x221 X2 2 2 x222 X2 2 3 x223 X2 Where type is a factor variable indicating if the observation is related to X1 or X2... Many thanks in advance, Bernard - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] package installation error (LF versus CR)
sonia wrote: Hello, I have the following problem in installing a package (in windows xp) rcmd install -c dlm [ ..stuff deleted ] ... DLL made installing DLL installing R files installing inst files installing data files installing man source files installing indices Errore in load(zfile, envir = envir) : l'input Þ stato danneggiato, LF sostituiti da CR Esecuzione interrotta make[2]: *** [indices] Error 1 make[1]: *** [all] Error 2 make: *** [pkg-dlm] Error 2 *** Installation of dlm failed *** Does anybody please have suggestions? If relevant, the source package was downloaded from a unix server using cvs+ssh In principle, it should not matter if it works on the unix machine. Anyway, can you try to *build* the package on that unix machine and install from the tar.gz file on Windows. Maybe some line endings got mixed up by cvs... For further report, please set LANGUAGE=en before a sample-run you want to include in a question to R-help, because not everybody understands italian. Uwe Ligges Thanks a lot, best, Sonia __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Interpolating / smoothing missing time series data
(see inline) Sean Davis wrote: On 9/7/05 10:19 PM, Gabor Grothendieck [EMAIL PROTECTED] wrote: On 9/7/05, David James [EMAIL PROTECTED] wrote: The purpose of this email is to ask for pre-built procedures or techniques for smoothing and interpolating missing time series data. I've made some headway on my problem in my spare time. I started with an irregular time series with lots of missing data. It even had duplicated data. Thanks to zoo, I've cleaned that up -- now I have a regular time series with lots of NA's. I want to use a regression model (i.e. ARIMA) to ill in the gaps. I am certainly open to other suggestions, especially if they are easy to implement. My specific questions: 1. Presumably, once I get ARIMA working, I still have the problem of predicting the past missing values -- I've only seen examples of predicting into the future. 2. When predicting the past (backcasting), I also want to take reasonable steps to make the data look smooth. I guess I'm looking for a really good example in a textbook or white paper (or just an R guru with some experience in this area) that can offer some guidance. Venables and Ripley was a great start (Modern Applied Statistics with S). I really had hoped that the Seasonal ARIMA Models section on page 405 would help. It was helpful, but only to a point. I have a hunch (based on me crashing arima numerous times -- maybe I'm just new to this and doing things that are unreasonable?) that using hourly data just does not mesh well with the seasonal arima code? Have you looked at Durbin, J. and Koopman, S. J. (2001) _Time Series Analysis by State Space Methods._ Oxford University Press, cited with ?arima? They explain that Kalman filtering is predicting the future, while Kalman smoothing is using all the data to fill the gaps, which seems to match your question. I was able to reproduce Figure 2.1 in that book but got bogged down with Figure 2.2 before I dropped the project. I can send you the script file I developed when working on that if it would help you. I'm still interested in learning how to reproduce in R all the examples in that book, and I'd happily receive suggestions from others on how to do that. spencer graves Not sure if this answers your question but if you are looking for something simple then na.approx in the zoo package will linearly interpolate for you. z - zoo(c(1,2,NA,4,5)) na.approx(z) 1 2 3 4 5 1 2 3 4 5 Alternatively, if you are looking for more smoothing, you could look at using a moving average or median applied at points of interest with an appropriate window size--see wapply in the gplots package (gregmisc bundle). There are a number of other functions that can accomplish the same task. A search for moving window or moving average in the archives may produce some other ideas. Sean __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Spencer Graves, PhD Senior Development Engineer PDF Solutions, Inc. 333 West San Carlos Street Suite 700 San Jose, CA 95110, USA [EMAIL PROTECTED] www.pdf.com http://www.pdf.com Tel: 408-938-4420 Fax: 408-280-7915 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Tip: I() can designate constants in a regression
Just thought I would share a tip I learned: The function I() is useful for specifying constants to formulas and regressions. It will prevent nls (for example) from trying to treat the variable inside I() as something it needs to estimate. An example is below. -David P.S. This may be obvious to some, but it is not made clear to be by the documentation or common books that I reviewed. These books, of course, do tend to mention others aspects of I(), which seems to be a very diverse function. For example: * ISwR by Dalgaard (p. 160, 177) * MASwS by Venables and Ripley (p.18) However, the books I looked at do not mention the specific tip here: Wrapping I() around a variable will make it a constant from the perspective of a regression. A humble suggestion to the many authors of the many great R and S books out there: I would find it helpful if more R books had the word constants in the index. Perhaps there could be a brief section that explained how to create constants in a regression. These sorts of problems, I would guess, occur more commonly with nls models than lm models. - - - - - - - - Here is the example that motivated my tip: weather.df : a data frame, where each row is one hour weather.df$temp : the temperature weather.df$annual : time offset, adjusted so that its period is one year weather.df$daily : time offset, adjusted so that its period is one day # I want a1,a2 to be constants from the point of view of nls a1 - 66 a2 - -18 nls.example - nls( temp ~ I(a1) + I(a2)*sin( ts.annual ) + a3*sin ( ts.daily ), data=weather.df, start=c(a3=1) ) # leaving out the I() will cause nls to estimate values for a1 and a2 [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] data manipulation
Hi, This may not be the best solution, but at least it's easy to see what i'm doing, assume that your data set is called data: # remove the 4th column data1 = data[,-4] # remove the 3rd column data2 = data[,-3] # use cbind to add an extra column with only X1 #elements data1 = cbind(data1, array(X1, nrow(data1), 1) # use cbind to add an extra column with only X2 #elements data2 = cbind(data2, array(X2, nrow(data2), 1) # use rbind to add them together as rows data3 = rbind(data1, data2) # rename the names of the columns colnames(data3) - c(ID, time, X, type) # show output data3 The only thing I couldn't figure out is how to sort the data set per row, perhaps someone else could help us out on this? Martin --- Marc Bernard [EMAIL PROTECTED] wrote: Dear All, I would be grateful if you can help me. My problem is the following: I have a data set like: ID time X1 X2 11 x111 x211 12 x112 x212 21 x121 x221 22 x122 x222 23 x123 x223 where X1 and X2 are 2 covariates and time is the time of observation and ID indicates the cluster. I want to merge the above data by creating a new variable X and type as follows: ID timeXtype 1 1 x111 X1 1 2 x112 X1 1 1 x211 X2 1 2 x212 X2 2 1 x121 X1 2 2 x122 X1 2 3 x123 X1 2 1 x221 X2 2 2 x222 X2 2 3 x223 X2 Where type is a factor variable indicating if the observation is related to X1 or X2... Many thanks in advance, Bernard - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ Click here to donate to the Hurricane Katrina relief effort. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] data manipulation
Marc Bernard [EMAIL PROTECTED] wrote: Dear All, I would be grateful if you can help me. My problem is the following: I have a data set like: ID time X1 X2 11 x111 x211 12 x112 x212 21 x121 x221 22 x122 x222 23 x123 x223 where X1 and X2 are 2 covariates and time is the time of observation and ID indicates the cluster. I want to merge the above data by creating a new variable X and type as follows: ID timeXtype 1 1 x111 X1 1 2 x112 X1 1 1 x211 X2 1 2 x212 X2 2 1 x121 X1 2 2 x122 X1 2 3 x123 X1 2 1 x221 X2 2 2 x222 X2 2 3 x223 X2 Where type is a factor variable indicating if the observation is related to X1 or X2... Say your original data is in dataframe df, then this might do what you want: R newdf - rbind(df[, 1:3], df[, c(1, 2, 4)]) R names(newdf)[3] - X R newdf$type - substr(c(df[[3]], df[[4]]), 1, 2) Cheers, -- Sebastian P. Luque __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Tip: I() can designate constants in a regression
David James [EMAIL PROTECTED] writes: Just thought I would share a tip I learned: The function I() is useful for specifying constants to formulas and regressions. It will prevent nls (for example) from trying to treat the variable inside I() as something it needs to estimate. An example is below. -David P.S. This may be obvious to some, but it is not made clear to be by the documentation or common books that I reviewed. These books, of course, do tend to mention others aspects of I(), which seems to be a very diverse function. For example: * ISwR by Dalgaard (p. 160, 177) * MASwS by Venables and Ripley (p.18) However, the books I looked at do not mention the specific tip here: Wrapping I() around a variable will make it a constant from the perspective of a regression. A humble suggestion to the many authors of the many great R and S books out there: I would find it helpful if more R books had the word constants in the index. Perhaps there could be a brief section that explained how to create constants in a regression. These sorts of problems, I would guess, occur more commonly with nls models than lm models. First check whether your claim is actually correct: x = 1:10 y = x # perfect fit yeps = y + rnorm(length(y), sd = 0.01) # added noise nls(yeps ~ a + b*x, start = list(a = 0.12345, b = 0.54321), + trace = TRUE) 74.2686 : 0.12345 0.54321 0.0006529895 : -0.002666984 1.000334031 Nonlinear regression model model: yeps ~ a + b * x data: parent.frame() ab -0.002666984 1.000334031 residual sum-of-squares: 0.0006529895 a - 0 nls(yeps ~ a + b*x, start = list(b = 0.54321),trace=TRUE) 80.31713 : 0.54321 0.0006682311 : 0.53 Nonlinear regression model model: yeps ~ a + b * x data: parent.frame() b 0.53 residual sum-of-squares: 0.0006682311 I.e., turning a into a constant works quite happily without the I(). Here is the example that motivated my tip: weather.df : a data frame, where each row is one hour weather.df$temp : the temperature weather.df$annual : time offset, adjusted so that its period is one year weather.df$daily : time offset, adjusted so that its period is one day # I want a1,a2 to be constants from the point of view of nls a1 - 66 a2 - -18 nls.example - nls( temp ~ I(a1) + I(a2)*sin( ts.annual ) + a3*sin ( ts.daily ), data=weather.df, start=c(a3=1) ) # leaving out the I() will cause nls to estimate values for a1 and a2 -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Multinomial Logit and p-values
Hi, I am trying to obtain p-values for coefficient estimates in a multinomial logit model. Although I am able to test for significance using other methods (e.g., Wald statistics), I can't seem to get R to give me simple p-values. I am sure there is a very simple solution to this, but the R archives seem to have nothing on this issue. I would appreciate any help. Thanks in advance! Best, Sangick Jeon __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] data manipulation
This is what reshape() does. -thomas On Thu, 8 Sep 2005, Marc Bernard wrote: Dear All, I would be grateful if you can help me. My problem is the following: I have a data set like: ID time X1 X2 11 x111 x211 12 x112 x212 21 x121 x221 22 x122 x222 23 x123 x223 where X1 and X2 are 2 covariates and time is the time of observation and ID indicates the cluster. I want to merge the above data by creating a new variable X and type as follows: ID timeXtype 1 1 x111 X1 1 2 x112 X1 1 1 x211 X2 1 2 x212 X2 2 1 x121 X1 2 2 x122 X1 2 3 x123 X1 2 1 x221 X2 2 2 x222 X2 2 3 x223 X2 Where type is a factor variable indicating if the observation is related to X1 or X2... Many thanks in advance, Bernard - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Thomas Lumley Assoc. Professor, Biostatistics [EMAIL PROTECTED] University of Washington, Seattle __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] execute R expression from command line
Can I execute an R expression from the command line without having it in an infile, something like perl's -e flag. So it would look like: R {Rexpression;} outfile __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] data manipulation
Also see Hadley Wickham's reshape package for more bells whistles. -- HTH! Jim Porzak Loyalty Matrix Inc. On 9/8/05, Thomas Lumley [EMAIL PROTECTED] wrote: This is what reshape() does. -thomas On Thu, 8 Sep 2005, Marc Bernard wrote: Dear All, I would be grateful if you can help me. My problem is the following: I have a data set like: ID time X1 X2 11 x111 x211 12 x112 x212 21 x121 x221 22 x122 x222 23 x123 x223 where X1 and X2 are 2 covariates and time is the time of observation and ID indicates the cluster. I want to merge the above data by creating a new variable X and type as follows: ID timeXtype 1 1 x111 X1 1 2 x112 X1 1 1 x211 X2 1 2 x212 X2 2 1 x121 X1 2 2 x122 X1 2 3 x123 X1 2 1 x221 X2 2 2 x222 X2 2 3 x223 X2 Where type is a factor variable indicating if the observation is related to X1 or X2... Many thanks in advance, Bernard - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Thomas Lumley Assoc. Professor, Biostatistics [EMAIL PROTECTED]University of Washington, Seattle __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Re-evaluating the tree in the random forest
Dear mailinglist members, I was wondering if there was a way to re-evaluate the instances of a tree (in the forest) again after I have manually changed a splitpoint (or split variable) of a decision node. Here's an illustration: library(randomForest) forest.rf - randomForest(formula = Species ~ ., data = iris, do.trace = TRUE, ntree = 3, mtry = 2, norm.votes = FALSE) # I am going to change the splitpoint of the root node of the first tree to 1 forest.rf$forest$xbestsplit[1,] forest.rf$forest$xbestsplit[1,1] - 1 forest.rf$forest$xbestsplit[1,] Because I've changed the splitpoint, some instances in the leafs are not supposed where they should be. Is there a way to reappoint them to the correct leaf? I was also wondering how I should interpret the output of do.trace: ntree OOB 1 2 3 1: 3.70% 0.00% 6.25% 5.88% 2: 3.49% 0.00% 3.85% 7.14% 3: 3.57% 0.00% 5.56% 5.26% What's OOB and what does the percentages mean? Thanks in advance, Martin __ Click here to donate to the Hurricane Katrina relief effort. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R API call from delphi
On approach is to create a native/foreign interface to R by linking R as a library (libR.a and R.dll) file and calling the C routines in the library to i) initialize the R interpreter ii) call an R function We have done this with many languages and the procedure is well understood at this point, but requires some C-level programming and converting between the standard data types of both systems. Another approach is to use R via DCOM. There are two different approaches to this. One has the R interpreter as the DCOM server and the client (the Delphi application here) would send R commands to that server. The other approach has regular DCOM servers that are implemented via R functions. (The ability to send R commands is a simple case of this.) It is up to you to define the servers via a few extra lines of R code. I would suggest you pursue the DCOM route unless you are keen to do the necessary work to embed the R library in Delphi and deal with some technical details about calling conventions of C routines. D Laurent TESSIER wrote: Hello, Has anyone tried to call R API from Delphi under windows ? How was it done if it was ? Or has anyone any idea about how it could be done ? Thanks for your answers Laurent Tessier [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Predicting responses using ace
Luis Pineda wrote: I gave a quick read to the documentation again and noticed I misinterpreted it. It was print.summary.areg.boot the method I was referring to (although the summary error should still work). Sorry for the inconvenience Anyway, I used the print method on my |areg.boot| object and I got this: -- Apparent R2 on transformed Y scale: 0.798 Bootstrap validated R2 : 0.681 ... Residuals on transformed scale: Min 1Q Median 3Q Max -1.071312e+00 -2.876245e-01 -3.010081e-02 2.123566e-01 1.867036e+00 Mean S.D. 1.290634e-17 4.462159e-01 -- I suppose thats the R^2 evaluated using the training set, but how do I evaluate the performance of the model on a uncontaminated test set? Please read my last note. Bootstrap validated R2 is corrected for overfitting and is an estimate of the likely future R2 on a totally independent dataset. The bootstrap is more efficient than data splitting for this purpose. Frank On 9/8/05, Luis Pineda [EMAIL PROTECTED] wrote: I'm trying to run the print method, but according to the documentation it needs as a parameter an object created by |summary.areg.boot| . [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] data manipulation
I am sure all this work but If you want exaclty the output to be the way you mentioned do this temp-read.table(yourfile, as.is=T, header=T) temp1-temp[, 1:3] temp2-temp[, c(1,2,4)] colnames(temp1)[3]-X colnames(temp2)[3]-X temp3-merge(temp1, temp2, all=T) temp3$type-toupper(substr(temp3$X, 1,2)) after which you can generate factors and such.. note the as.is=T in read.table keeps the variables X1, X2, as characters. This is done for substr... P.S. I am sure you can use reshape instead of the second to the fifth commands above ?reshape Jean On Thu, 8 Sep 2005, Sebastian Luque wrote: Marc Bernard [EMAIL PROTECTED] wrote: Dear All, I would be grateful if you can help me. My problem is the following: I have a data set like: ID time X1 X2 11 x111 x211 12 x112 x212 21 x121 x221 22 x122 x222 23 x123 x223 where X1 and X2 are 2 covariates and time is the time of observation and ID indicates the cluster. I want to merge the above data by creating a new variable X and type as follows: ID timeXtype 1 1 x111 X1 1 2 x112 X1 1 1 x211 X2 1 2 x212 X2 2 1 x121 X1 2 2 x122 X1 2 3 x123 X1 2 1 x221 X2 2 2 x222 X2 2 3 x223 X2 Where type is a factor variable indicating if the observation is related to X1 or X2... Say your original data is in dataframe df, then this might do what you want: R newdf - rbind(df[, 1:3], df[, c(1, 2, 4)]) R names(newdf)[3] - X R newdf$type - substr(c(df[[3]], df[[4]]), 1, 2) Cheers, -- Sebastian P. Luque __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] writing data to sheet in excel workbook
Hi, I believe to remember there is a package that lets you write data from R to different sheets in a Excel workbook. I've been looking around on CRAN but could not find what I am looking for. Any help would be greatly appreciated. Cheers, Adi __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Leading in line-wrapped Lattice value and panel labels
On 9/7/05, Paul Murrell [EMAIL PROTECTED] wrote: Hi Deepayan Sarkar wrote: On 9/7/05, Tim Churches [EMAIL PROTECTED] wrote: Version 2.1.1 Platforms: all What is the trellis parameter (or is there a trellis parameter) to set the leading (the gap between lines) when long axis values labels or panel header labels wrap over more than one line? By default, there is a huge gap between lines, and much looking and experimentation has not revealed to me a suitable parameter to adjust this. There is none. Whatever grid.text does happens. grid does have a lineheight graphical parameter. For example, library(grid) grid.text(line one\nlinetwo, x=rep(1:3/4, each=3), y=rep(1:3/4, 3), gp=gpar(lineheight=1:9/2)) Could you add this in relevant places in trellis.par Deepayan? I will (don't know how soon). The description in ?gpar is not very informative though: lineheight The height of a line as a multiple of the size of text (or maybe it's a standard term in typography that I'm not familiar with). Deepayan __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] execute R expression from command line
On 8 Sep 2005, [EMAIL PROTECTED] wrote: Can I execute an R expression from the command line without having it in an infile, something like perl's -e flag. So it would look like: R {Rexpression;} outfile With a bash-like shell, you can do: echo library(foo); somefunc(5) | R --slave HTH, + seth __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Survival model with cross-classified shared frailties
Hi Thomas, Thanks for the reply, coxme() seems to be the one I need. Best, Shige On 9/8/05, Thomas Lumley [EMAIL PROTECTED] wrote: On Thu, 8 Sep 2005, Shige Song wrote: Dear All, The coxph function in the survival package allows multiple frailty terms. Um, no, it doesn't. In all the examples I saw, however, the frailty terms are nested. What will happen if I have non-nested (that is, cross-classified) frailties in the model? This wouldn't work even if it did allow multiple frailty terms. You may want the coxme() function in the kinship package. -thomas [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Setting width in batch mode
As instructed, I have spent a long time searching the web for an answer to this question. I am trying to use Sweave to produce lecture slides, and have the problem that I can't control the formatting of my R source. Setting options(width), as recommended in this forum, works fine on the R _output_, but seems to have unpredictable effects on the echoing of the source code. If I try setting options(width) directly in R, I note that it has _no_ effect on echoed source code, whereas Sweave does sometimes break source code, but not predictably, and not to the same width as output code. I would be happy with any method of manually or automatically controlling the line width of Sweave source, using R, Sweave or LaTeX options. Making the font smaller does not count, though; I want to break the lines. Any help is appreciated. An example of Sweave input and output is appended. The last break is right, while the others are too late. Jonathan Dushoff -- bug.rnw = options(width=55) data(state) data.frame(area=mean(state.area), pop=mean(state.pop), hop=mean(state.area)) c(medianarea=median(state.area), medianpop=median(state.pop)) c(medianarea=median(median(state.area)), medianpop=median(state.pop)) @ -- bug.tex \begin{Schunk} \begin{Sinput} options(width = 55) data(state) data.frame(area = mean(state.area), pop = mean(state.pop), + hop = mean(state.area)) \end{Sinput} \begin{Soutput} area pop hop 1 72367.98 4246420 72367.98 \end{Soutput} \begin{Sinput} c(medianarea = median(state.area), medianpop = median(state.pop)) \end{Sinput} \begin{Soutput} medianarea medianpop 562222838500 \end{Soutput} \begin{Sinput} c(medianarea = median(median(state.area)), + medianpop = median(state.pop)) \end{Sinput} \begin{Soutput} medianarea medianpop 562222838500 \end{Soutput} \end{Schunk} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] writing data to sheet in excel workbook
On 9/8/05, adalbert duerrer [EMAIL PROTECTED] wrote: Hi, I believe to remember there is a package that lets you write data from R to different sheets in a Excel workbook. I've been looking around on CRAN but could not find what I am looking for. See http://finzi.psych.upenn.edu/R/Rhelp02a/archive/58249.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] R API call from delphi
Follow this thread http://finzi.psych.upenn.edu/R/Rhelp02a/archive/50598.html Cheers Francisco From: Laurent TESSIER [EMAIL PROTECTED] Reply-To: [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Subject: [R] R API call from delphi Date: Thu, 8 Sep 2005 17:47:49 +0200 (CEST) Hello, Has anyone tried to call R API from Delphi under windows ? How was it done if it was ? Or has anyone any idea about how it could be done ? Thanks for your answers Laurent Tessier [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] can't successfully use installed evir package
I'm next at installing packages. I seem to have successfully installed evir, but I can't use it. I'm wondering if I need to specify the installation to match my working directory, or something else. thx, G __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] clustering: Multivariate t mixtures
Hi, Before I write code to do it does anyone know of code for fitting mixtures of multivariate-t distributions. I can't use McLachan's EMMIX code because the license is For non commercial use only. I checked, mclust and flexmix but both only do Gaussian. Thanks Nicholas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] generating a vector from clusters of logicals
dear friends, I have a vector of clusters of TRUE and FALSE like c(TRUE,TRUE,TRUE...,FALSE,FALSE,FALSE,TRUE,TRUE...) and want to make that into a vector of c(1,1,1,1...2,2,2,2,.3,3,3,3) increasing the number assigned to each cluster as they change. How would I do that ? Best wishes Troels Ring, Aalborg, Denmark __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] clustering: Multivariate t mixtures
On Thu, 08 Sep 2005 15:38:55 -0500 Nicholas Lewin-Koh wrote: Hi, Before I write code to do it does anyone know of code for fitting mixtures of multivariate-t distributions. I can't use McLachan's EMMIX code because the license is For non commercial use only. I checked, mclust and flexmix but both only do Gaussian. The Gaussian case is available in a pre-packaged function FLXmclust(), but the flexmix framework is not limited to that case. There is a paper which appeared in the Journal of Statistical Software (http://www.jstatsoft.org/) that explains how to write new M-steps for flexmix. It is also contained in the package as vignette(flexmix-intro) Best, Z Thanks Nicholas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] generating a vector from clusters of logicals
On Thu, 08 Sep 2005 23:03:03 +0200 Troels Ring wrote: dear friends, I have a vector of clusters of TRUE and FALSE like c(TRUE,TRUE,TRUE...,FALSE,FALSE,FALSE,TRUE,TRUE...) and want to make that into a vector of c(1,1,1,1...2,2,2,2,.3,3,3,3) increasing the number assigned to each cluster as they change. How would I do that ? Does this what you want: R set.seed(123) R x - sample(c(TRUE, FALSE), 10, replace = TRUE) R x [1] TRUE FALSE TRUE FALSE FALSE TRUE FALSE FALSE FALSE TRUE R c(1, cumsum(abs(diff(x))) + 1) [1] 1 2 3 4 4 5 6 6 6 7 ? Z Best wishes Troels Ring, Aalborg, Denmark __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] clustering: Multivariate t mixtures
Hi, Actually that was my plan was to implement a new flexmix class. Thanks for the pointer to the jss paper, that will be helpful. Nicholas On Thu, 8 Sep 2005 23:07:13 +0200, Achim Zeileis [EMAIL PROTECTED] said: On Thu, 08 Sep 2005 15:38:55 -0500 Nicholas Lewin-Koh wrote: Hi, Before I write code to do it does anyone know of code for fitting mixtures of multivariate-t distributions. I can't use McLachan's EMMIX code because the license is For non commercial use only. I checked, mclust and flexmix but both only do Gaussian. The Gaussian case is available in a pre-packaged function FLXmclust(), but the flexmix framework is not limited to that case. There is a paper which appeared in the Journal of Statistical Software (http://www.jstatsoft.org/) that explains how to write new M-steps for flexmix. It is also contained in the package as vignette(flexmix-intro) Best, Z Thanks Nicholas __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Time Series Analysis: book?
Wensui Liu wrote: TS is a huge topic. The book recomended by statisitcian might be different from the one recommended by econometrician. Finance guy might recommend another. Could you please be more specific? My software (http://moodss.sourceforge.net) collects, archives in a SQL database and displays data from monitored devices, mostly computers, databases and network equipment. My idea is to use the stored data to perform predictions for capacity planning purposes. For example, based on the trafic on a network line for the last 12 months, what is the expected evolution in the next 3 months. So the data is more of the engineering type, I guess. But since the software is modular, somebody could also use it to monitor the stock market. Actually, anything can be monitored so the data could come from any source although practically mostly from computing related devices and activities. So I would like a book covering at least those subjects if possible. Thanks very much for your help. -- Jean-Luc Fontaine http://jfontain.free.fr/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] generating a vector from clusters of logicals
From: Troels Ring [EMAIL PROTECTED] I have a vector of clusters of TRUE and FALSE like c(TRUE,TRUE,TRUE...,FALSE,FALSE,FALSE,TRUE,TRUE...) and want to make that into a vector of c(1,1,1,1...2,2,2,2,.3,3,3,3) increasing the number assigned to each cluster as they change. How would I do that ? How about: TF - c(TRUE,TRUE,TRUE,FALSE,FALSE,FALSE,TRUE,TRUE,FALSE) rep(1:length(rlel - rle(TF)$lengths), rlel) [1] 1 1 1 2 2 2 3 3 4 HTH, Ray Brownrigg __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] generating a vector from clusters of logicals
Try: x - c(TRUE,TRUE,TRUE,FALSE,FALSE,FALSE,TRUE,TRUE) tmp - rle(x) tmp$values - seq(along=tmp$lengths) new.x - inverse.rle(tmp) new.x Greg Snow, Ph.D. Statistical Data Center, LDS Hospital Intermountain Health Care [EMAIL PROTECTED] (801) 408-8111 Troels Ring [EMAIL PROTECTED] 09/08/05 03:03PM dear friends, I have a vector of clusters of TRUE and FALSE like c(TRUE,TRUE,TRUE...,FALSE,FALSE,FALSE,TRUE,TRUE...) and want to make that into a vector of c(1,1,1,1...2,2,2,2,.3,3,3,3) increasing the number assigned to each cluster as they change. How would I do that ? Best wishes Troels Ring, Aalborg, Denmark __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Data Expo 2006 (off-topic)
Hi This is to let R folks know about the Data Expo that is being run by the ASA Sections on Statistical Graphics, Statistical Computing, and Statistics and the Environment for JSM 2006. This competition provides a data set of geographic and atmospheric data from NASA and entrants are asked to provide a graphical summary of the important features of the data set. The emphasis is on graphical display, but the data set has time series, spatial, and multivariate features that allow the focus to be directed in a number of different ways. Entries will be presented in a poster session at JSM 2006 and the best entries will receive cash prizes totalling $1700 plus NASA merchandise. Student and group entries are encouraged. It would be good to see some R-based entries! For more information, please see the Data Expo web site http://www.amstat-online.org/sections/graphics/dataexpo/2006.php Paul Murrell (on behalf of the Data Expo organising team) -- Dr Paul Murrell Department of Statistics The University of Auckland Private Bag 92019 Auckland New Zealand 64 9 3737599 x85392 [EMAIL PROTECTED] http://www.stat.auckland.ac.nz/~paul/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] ROracle install problem
Ariel Chernomoretz [EMAIL PROTECTED] wrote: Hi, I am trying to install the ROracle package in a Linux-64 machine. I downloaded from Oracle's site their Instant Client bundle but it seems that ROracle needs some stuff not included in that kit in order to compile (in particuar, the 'proc' executable). You can't use the Instant Client. You need to get the full client CD for your platform. I did not find any other linux client suite in Oracle's site It is there. Go to: http://www.oracle.com/technology/software/index.html and click on Oracle Database 10g (or 9i, or whatever), then on your platform, and look for the Client CD. -- Dave __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Re: General Matrix Inner Product?
Roger E. Khayat, Professor Department of Mechanical and Materials Engineering The University of Western Ontario London, Ontario, Canada N6A 5B9 Email: [EMAIL PROTECTED] Tel: (519) 661-2111 Ext 88253 Fax: (519) 661-3020 http://www.engga.uwo.ca/people/rkhayat/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Coarsening Factors
It is not uncommon to want to coarsen a factor by grouping levels together. I have found one way to do this in R: sites [1] F A A D A A B F C F A D E E D C F A E D F C E D E F F D B C Levels: A B C D E F regions - list(I = c(A,B,C), II = D, III = c(E,F)) library(Epi) region - Relevel(sites,regions) region [1] III I I II I I I III I III I II III III II I III I III [20] II III I III II III III III II I I Levels: I II III However this seems like using a sledgehammer to crack a nut. Can someone suggest a simpler way to do this task? Murray Jorgensen -- Dr Murray Jorgensen http://www.stats.waikato.ac.nz/Staff/maj.html Department of Statistics, University of Waikato, Hamilton, New Zealand Email: [EMAIL PROTECTED]Fax 7 838 4155 Phone +64 7 838 4773 wk Home +64 7 825 0441 Mobile 021 1395 862 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Coarsening Factors
Murray Jorgensen [EMAIL PROTECTED] writes: It is not uncommon to want to coarsen a factor by grouping levels together. I have found one way to do this in R: sites [1] F A A D A A B F C F A D E E D C F A E D F C E D E F F D B C Levels: A B C D E F regions - list(I = c(A,B,C), II = D, III = c(E,F)) library(Epi) region - Relevel(sites,regions) region [1] III I I II I I I III I III I II III III II I III I III [20] II III I III II III III III II I I Levels: I II III However this seems like using a sledgehammer to crack a nut. Can someone suggest a simpler way to do this task? Yes, regions - list(I = c(A,B,C), II = D, III = c(E,F)) levels(sites) - regions sites [1] III I I II I I I III I III I II III III II I III I III [20] II III I III II III III III II I I Levels: I II III -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] change in read.spss, package foreing?
Dear All, it seems to me that the function read.spss of package foreign changed its behaviour regarding factors. I noted that in version 0.8-8 variables with value labels in SPSS were transformed in factors with the labels in alphabetic order. In version 0.8-10 they seem to be ordered preserving the order corresponding to their numerical codes in SPSS. However I could not find a description of this supposed change. Since the different behaviour seems to depend on the installed version of the foreign-package I don't know how to give a reproducible example. It also affects spss.get of the Hmisc-package, which is not surprising. I prefer the new behaviour and would like to know, if it will persist in future versions. Comments? Heinz Tüchler __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Time Series Analysis: book?
1. Have you read the appropriate chapter in Venables and Ripley (2002) Modern Applied Statists with S (Springer)? If no, I suggest you start there. 2. Have you worked through the vignettes associated with the zoo package? If no, you might find that quite useful. [Are you aware that edit(vignette(...)) will provide a script file with the R code discussed in the vignette, which can be viewed in Adobe Acrobat while you are working throught the examples line by line, modifying them, etc.? I've found this to be very useful. If you use XEmacs, edit(vignette(...)) may not work. Instead, try Stangle(vignette(...)$file). This will copy the R code to a file in the working directory, which you can then open.] 3. Have you considered Durbin, J. and Koopman, S. J. (2001) _Time Series Analysis by State Space Methods._ Oxford University Press? If no, you might want to spend some time with that. I'm still looking for the right kind of introduction and overview to what is available in R for time series analysis, especially with a Bayesian approach to Kalman filtering and smoothing. Unfortunately, I have yet to find the key I feel I need to get started, though I found the vignettes with zoo to be quite helpful. spencer graves Jean-Luc Fontaine wrote: Wensui Liu wrote: TS is a huge topic. The book recomended by statisitcian might be different from the one recommended by econometrician. Finance guy might recommend another. Could you please be more specific? My software (http://moodss.sourceforge.net) collects, archives in a SQL database and displays data from monitored devices, mostly computers, databases and network equipment. My idea is to use the stored data to perform predictions for capacity planning purposes. For example, based on the trafic on a network line for the last 12 months, what is the expected evolution in the next 3 months. So the data is more of the engineering type, I guess. But since the software is modular, somebody could also use it to monitor the stock market. Actually, anything can be monitored so the data could come from any source although practically mostly from computing related devices and activities. So I would like a book covering at least those subjects if possible. Thanks very much for your help. -- Spencer Graves, PhD Senior Development Engineer PDF Solutions, Inc. 333 West San Carlos Street Suite 700 San Jose, CA 95110, USA [EMAIL PROTECTED] www.pdf.com http://www.pdf.com Tel: 408-938-4420 Fax: 408-280-7915 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] SPSS Dataset
How would one read SPSS data sets directly into R __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Time Series Analysis: book?
Quoting Spencer Graves [EMAIL PROTECTED]: 1. Have you read the appropriate chapter in Venables and Ripley (2002) Modern Applied Statists with S (Springer)? If no, I suggest you start there. 2. Have you worked through the vignettes associated with the zoo package? If no, you might find that quite useful. [Are you aware that edit(vignette(...)) will provide a script file with the R code discussed in the vignette, which can be viewed in Adobe Acrobat while you are working throught the examples line by line, modifying them, etc.? I've found this to be very useful. If you use XEmacs, edit(vignette(...)) may not work. Instead, try Stangle(vignette(...)$file). This will copy the R code to a file in the working directory, which you can then open.] 3. Have you considered Durbin, J. and Koopman, S. J. (2001) _Time Series Analysis by State Space Methods._ Oxford University Press? If no, you might want to spend some time with that. I'm still looking for the right kind of introduction and overview to what is available in R for time series analysis, especially with a Bayesian approach to Kalman filtering and smoothing. Unfortunately, I have yet to find the key I feel I need to get started, though I found the vignettes with zoo to be quite helpful. Thank you very much Spencer and all who responded. I think I have enough to get started with all this valuable information. -- Jean-Luc __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] strata in crr (cmprsk library)
Hi all, I am aware that crr lacks the friendly command structure of functions such as cph. All is clear to me about including covariates until I want to include a stratification term in the competing risk framework (no nice strat command). I am still a bit of a novice in R - I am looking for an example to help me with this, but can't seem to find one. Any advice appreciated (no matter how simple). Thanks Scott Williams MD Peter MacCallum Cancer Centre Melbourne, Australia __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Debugging R/Fortran in Windows
Hi, I'm trying to debug an R interface to a Fortran subroutine from Windows. (Yes, I know I should try Unix/Linux as well, but a quick attempt suggested that the (MinGW g77) Fortran compiler I have installed on my Windows laptop works better on this Fortran code.) I'm trying to follow the instructions in the Writing R Extensions Manual: Start R under the debugger after setting a breakpoint for WinMain. gdb .../bin/Rgui.exe (gdb) break WinMain (gdb) run But when I run gdb on Rgui.exe, I get the message: no debugging symbols found and then when I try break WinMain, I get: No symbol table is loaded. use the 'file' command. I'm using R 2.1.1 on Windows 2000 and gdb 5.2.1 from MSys's MinGW. I'm calling a Fortran function (several times) from R. And I seem to have the basic two-way data communication working - I appear to have succesfully passed all required data types (integer, real, double precision) to and from Fortran with sensible results both from within R and from using WRITE(FILENUM,*) from within Fortran. But unfortunately there is still evidence of memory leakage. Any suggestions would be greatly appreciated. Regards, James __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] SPSS Dataset
RSiteSearch(read spss data) -- library(foreign) ?read.spss Best, Matthias -Ursprüngliche Nachricht- Von: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Im Auftrag von ERICK YEGON Gesendet: Freitag, 09. September 2005 07:02 An: R-help@stat.math.ethz.ch Betreff: [R] SPSS Dataset How would one read SPSS data sets directly into R __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html