Thanks for the indications. All these suggestion will help a lot. The TINN-R application is impressive.
However, I think something more PROBLEM directed is needed. I agree that Google and the ?RSiteSearch helps a lot, but yet the explanations (like this discussion) are not clear enough in many cases. Any way, this is my impression as a technical user. The R stuff is really good, but it is difficult to find what you need in many instances. Then, people tend to define its own functions (I'm doing this too), and a lack of standardization makes it difficult to keep everything into control. Albert Sorribas Professor of Statistics and Operational Research Departament de Ciències Mèdiques Bàsiques Universitat de Lleida Montserrat Roig 2 25008-Lleida (Espanya) web.udl.es/Biomath/Group -----Mensaje original----- De: Gabor Grothendieck [mailto:[EMAIL PROTECTED] Enviado el: miércoles, 26 de abril de 2006 17:47 Para: Albert Sorribas CC: r-help@stat.math.ethz.ch Asunto: Re: [R] Were to find appropriate functions for a given task in R There is a reference sheet here: http://www.rpad.org/Rpad/R-refcard.pdf a function finder here: http://biostat.mc.vanderbilt.edu/s/finder/find.html and task views here: http://cran.r-project.org/src/contrib/Views/ Also use of RSiteSearch and help.search from within R can be helpful. On 4/26/06, Albert Sorribas <[EMAIL PROTECTED]> wrote: > This is a generic request concerning were to look for finding > appropriate information on a precise procedure in R. > I'm using R for teaching introductory statistics and my students are > learning how to deal with it. However, I find it difficult to locate > some of the procedures. For instance, for basic crosstabulation, it is > obvious that basic functions as table, ftable, and prop.table can be > used. But there is a CrossTable function that is very useful. This is > hidden in gmodels and gregmisc, as far as I've been able to explore the > packages. However, there is no way (unless I sit down to r-help for > hours) to be sure if there is some other place in which a very useful > function is hidden for table manipulation (for instance controlling for > other variables). This is only an example. But there are many more. Were > to look for CI for proportions? I can find it but it is not easy. > > I understand R is more appropriate for difficult statistical procedures > (glm and similar), BUT students need to start somewhere . > > My specific claim is about the need for a sort of guide in which the > different procedures could be classified (and some redundancies could be > deleted ..by the way). Is there something similar around? Any project > working on this? Any clue for? > > If not, I would suggest starting some kind of easy reference based on > the problem to solve. This could indicate were to look for. Last day I > find in package vcd that a function exist for testing the > goodness-of-fit of a sample to binomial and other distributions .but > this was VERY difficult to locate. > > Any way, as usual, any indication will be very useful (spaecially for my > students!!!) > > > > Albert Sorribas > Professor of Statistics and Operational Research > Departament de Ciències Mèdiques Bàsiques > Universitat de Lleida > Montserrat Roig 2 > 25008-Lleida (Espanya) > web.udl.es/Biomath/Group > > > > [[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