[R] numbering observations: help please!
Dear Friends, I have the very simple problem of needing to number observations in a data frame. After scratching the rest of my hair off my head without inspiration, I'm using a silly loop. I'm sure that there is a much more elegant and faster solution - can anyone help? Here is an example: my.data - data.frame (person=c(1,1,1,1,2,2,3,3,3,3,3,3,3,4,4,4)) # now I want to number those observations sequentially # for each person my.data$item.number - 0 for (i in 1:length(unique(my.data$person))) { my.data$item.number [which (my.data$person == unique(my.data$person)[i])] - seq (1:dim(tmp)[1]) } -- View this message in context: http://r.789695.n4.nabble.com/numbering-observations-help-please-tp4649457.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] peer-reviewed (or not) publications on R
Dear Friends, I'm contributing to a paper on a new R package for a clinical (medicine, ophthalmology) audience, and part of the mission is to encourage people who might be occasional users of Excel or SPSS, to become more familiar with R. I'd really appreciate any pointers to more recent papers that describe R, it's growth (statistics on user base, number of packages, volume of help list traffic) and application in many diverse fields. Published peer-reviewed papers of course would be best, but I'd appreciate any pointers to other resources and compilations that might float around somewhere. Is there anything bibliometric (number of citations)? I will happily send something back to the list... Best wishes Paul -- View this message in context: http://r.789695.n4.nabble.com/peer-reviewed-or-not-publications-on-R-tp4647871.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] symmetric dotplot? (Wilkinson 1999, Am Stat 53 (3) 276-281
DeaR all, The stripchart function (graphics) is provides jittered and stacked univariate scatterplots, but I wonder if anyone has implemented a *symmetric* version of this - as in the lower panel of Wilkinson's paper: http://www.jstor.org/stable/2686111 I have looked through several functions in contributed packages that do similar things, but not found one that can do this. What am I missing? Thanks! Paul -- View this message in context: http://r.789695.n4.nabble.com/symmetric-dotplot-Wilkinson-1999-Am-Stat-53-3-276-281-tp2540757p2540757.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] off topic but need your pointers about statistics
Publication of Exploratory Data Analysis by John Tukey. Strange Tukey's name has not been mentioned so far. You should consider re-posting your most interesting question with a less apologetic title - perhaps you will get a larger range of replies. Best wishes Paul losemind wrote: Thanks so much for the invaluable pointers folks! I just also wanted to note that my definition of statistics also includes data-mining, generic data-analysis, etc. , i.e. the statistics in the broad sense. Any more thoughts? Thanks a lot! On Thu, Jun 18, 2009 at 4:05 PM, Richard M. Heibergerr...@temple.edu wrote: Alan Izenman suggests: I have lots of places worth checking out for him. It means a lot of reading. Probably the first (and best) place to start is the set of Springer books entitled Breakthroughs in Statistics, which was edited by Kotz Johnson. There' are three (3) volumes: 1 (1992, corrected edition 2008), 2 (1993), and III (1997). He should remember that the choices of breakthroughs are those of the editors, and may not be others' choices. These volumes should lead him in all sorts of directions. Each chapter in each of these volumes contains the original paper with an introduction as to its significance. His project is bordering on the history of statistics, for which there are many (many!) books to consult. If he needs further direction, let him contact me. Best, Alan. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/off-topic-but-need-your-pointers-about-statistics-tp24098656p24109026.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] off topic but need your pointers about statistics
I re-read the posting guide every night before going to bed. The usefulness of this list stems partly from it being a broad church with lots of experts. And my concern wasn't with the off-topic label so much as with the slightly inspecific title (although I should have made this clear - mea culpa). A clearer heading might have attracted more readers. In my (personal) view none of the other lists you mention really compare to this one (R-help), but allstat might be added also. David Winsemius wrote: On Jun 19, 2009, at 6:36 AM, Paul Artes wrote: [...] You should consider re-posting your most interesting question with a less apologetic title - perhaps you will get a larger range of replies. You might consider (re-?) reading the Posting Guide. The OP was correct in thinking this is off topic. There are other venues where it would not be so. There are three stats newsgroups (which unlike the r-lists specifically encourage cross- posting: sci.stat.math, sci.stat.edu, and sci.stat.consult and one GoogleGroup, MedStats, where such a question might be on-topic. David Winsemius, MD Heritage Laboratories West Hartford, CT __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- View this message in context: http://www.nabble.com/off-topic-but-need-your-pointers-about-statistics-tp24098656p24111585.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] one-sample t-test with correlated (clustered) observations
I would like to estimate the difference between two measurement techniques. With both techniques, 4 measurements were obtained in each of 15 individuals. (These are not *repeated* measurements though - each of the 4 is of a different attribute). The naive approach would be a paired t-test, but of course this assumes that the 4 measures contributed by each individual are not dependent (which they are), and would inflate the CI of the differences. I found t.test.cluster {Hmisc}, but this works for the 2-sample problem only as far as I understand... Could someone please point me in the right direction? Many thanks! Paul -- View this message in context: http://www.nabble.com/one-sample-t-test-with-correlated-%28clustered%29-observations-tp21875193p21875193.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] psychometric functions
There is a nice paper by Yssaad-Fesselier and Knoblauch on Modelling Psychometric Functions in R. http://hal.archives-ouvertes.fr/docs/00/13/17/99/PDF/B125.pdf You might also be interested in this: http://www.journalofvision.org/5/5/8/article.aspx which comes from the same group as the psignifit toolbox for matlab (methinks), but is a step ahead. Best wishes Paul -- View this message in context: http://www.nabble.com/psychometric-functions-tp19086590p19091317.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] re cognizing patterns
DeaRs, i'm looking for some references on a statement as follows: Humans are good at spotting trends and patterns in data, but they are also good at spotting those patterns where none really exist. This is not verbatim but there must be some scholarly work on this. I can't remember where I came across it - perhaps I dreamed it up? Help, anyone? Best wishes Paul -- View this message in context: http://www.nabble.com/recognizing-patterns-tp15434260p15434260.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] independence of censoring in survival analyses
Dear all (not an R question per se, but given that the Real pRo's are all heRe I hope you foRgive) survival analyses assume that censoring is independent of hazard etc (eg, MASS 4th ed, pg. 354). Is there a standard test for this assumption? If there is not, what would you do to examine it empirically? (over and above some thinking about how censoring might be related to baseline factors). Would very much appreciate your thoughts and any pointers you can give Best wishes Paul aRtes = Paul H Artes, PhD Associate Professor Foundation Scholar in Glaucoma Research Ophthalmology and Visual Sciences, Dalhousie University Rm 2035 West Victoria, 1278 Tower Rd, Halifax, Nova Scotia B3H 2Y5 Canada -- View this message in context: http://www.nabble.com/independence-of-censoring-in-survival-analyses-tp15340503p15340503.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.