Re: [R] Error in a regression

Hi Andrea, Assuming that your model is something like: lm(y~x,data=mydata) See what: cor(mydata$y,mydata$x) returns. If it is very very close to 1 or -1, there lies your problem. If one or more of your predictor variables is an almost perfect predictor of the response, you don't have much room

Re: [R] rsync: failed to connect to cran.r-project.org (137.208.57.37): No route to host (113)

I ran traceroutes & BGP traces from Marseille & Paris routers to that CRAN IPv4 address (it's 10hrs after your mail, tho) and there's no network errors. You can use any CRAN mirror, though. You aren't limited to that one. On Mon, Oct 24, 2016 at 9:49 AM, Etienne Borocco

Re: [R] Extract word from string based on pattern match

On Oct 24, 2016 6:05 PM, "Joe Ceradini" wrote: > > Excellent - thanks David! > Regex syntax never fails to scare the crap out of me :) > > David absolutely solved my problem (in record time, no less), so it > can be put to rest. However, if anyone knows how to accomplish

Re: [R] Extract word from string based on pattern match

Excellent - thanks David! Regex syntax never fails to scare the crap out of me :) David absolutely solved my problem (in record time, no less), so it can be put to rest. However, if anyone knows how to accomplish the same thing through non base packages, like stringr or stringi, I'd be interested

[R] Extract word from string based on pattern match

R Helpers, I would like to extract the entire word beginning with "BT" (or "BT-") and not any thing else in the string. Or, I would like to extract from BT up until the next space. test <- data.frame(x = c("abc", "Sample BT-1501-2E stuff", "Bt-1599-3E stuff")) test So, from test$x I would like

Re: [R] nlme

Wild guess: Santiago is putting a and b in his formula when they are the coefficients he wants to extract? If Mr S wants better answers he needs to read about reproducibility and avoid HTML format email. -- Sent from my phone. Please excuse my brevity. On October 24, 2016 2:58:42 PM CDT,

Re: [R] function which returns number of occurrences of a pattern in string

Bob and Max, I thank you. It helped me much. 2016-10-21 3:47 GMT+02:00 Bob Rudis : > `stringi::stri_count()` > > I know that the `stringr` pkg saves some typing (it wraps the > `stringi` pkg), but you should really just use the `stringi` package. > It has many more very useful

Re: [R] nlme

> summary(nlme(Btronc~a+b*dbh**2*haut, data=cbind(dat,g="a"), fixed=a+b_1, > start=start, > > groups=~g, weights=varPower(form=~dbh))) Shouldn't 'fixed' be a formula? Perhaps a+b~1? Bill Dunlap TIBCO Software wdunlap tibco.com On Mon, Oct 24, 2016 at 9:03 AM, Santiago Bueno

Re: [R] nlme

Without access to the data, or commented, minimal, self-contained, reproducible code, it's pretty hard to speculate. I suggest that you reframe your question so that we can see what you can see. Andrew On 25 October 2016 at 03:03, Santiago Bueno wrote: > Dear people: > > > I

[R] nlme

Dear people: I am getting the following error when trying to run the piece of code below. Any insights?? Error in nlme.formula(Btronc ~ a + b * dbh^2 * haut, data = cbind(dat, : object 'a' not found library(nlme) start <- coef(lm(Btronc~I(dbh**2*haut),data=dat)) names(start) <-

Re: [R] Finding starting values for the parameters using nls() or nls2()

I've spent quite a bit of time trying to convince people on various lists that the solution to these kinds of problems lies in the stable parameterization of the model. I write the solutions in AD Model Builder because it is easy. But R people are generally stuck in R (or mired) so the

[R] Krippendorff's alpha bootstrapping implementation

I noticed the 2014 discussion of bootstrapping Krippendorff's alpha referring to Andrew Hayes website. Whoever is interested in this algorithm: One of Andrew Hayes' student discovered an oddity in the distribution obtained by this algorithm when data are very sparse. This has been corrected by

Re: [ESS] ESS 16.10 released

> Le 24 oct. 2016 à 12:36, Martin Maechler a écrit > : > >> Vincent Goulet >>on Mon, 24 Oct 2016 10:35:15 -0400 writes: > [snipped announcement] >> To Martin and ESS core: > >> I realize I should have tested this in beta

Re: [R] Error in a regression

Probably not. This is a statistics issue, not an R issue. But you need to show us your code to make sure it's not a syntax error. Assuming it's not, you'll need to consult a local statistical expert for help. Bert [[alternative HTML version deleted]]

[R] Error in a regression

Hi guys, When I try to do a linear regression into the console appears this warning message: >* attempting model selection on an essentially perfect fit is nonsense* Some one could tell me what does it mean and maybe a way to solve it. Thanks in advance, Andrea Marcela [[alternative

Re: [R] using nested ifelse when i want to process values from more than 3 columns of data frame

Indira, I think you are wanting to define a new column (target) with "all_true", "all_false", or "other" based on columns H1, H2, H3, and H8 all being equal to 1, all being equal to 0, and other wise respectively. If so, then you do not need apply() or ifelse(). I believe this does what you

Re: [R] using nested ifelse when i want to process values from more than 3 columns of data frame

You really need to provide more information. The error message without the command that generated it and the structure of the data sets you are using is a bare minimum. A reproducible example is often necessary to debug code such as this. You can simplify your code substantially with something

Re: [R] using nested ifelse when i want to process values from more than 3 columns of data frame

Got past the syntax error,now I got new error below Error in match.fun(FUN) : c("'ifelse((kmeans.data$HBV51OpenDmd & kmeans.data$HBV52OpenDmd & ' is not a function, character or symbol", "' kmeans.data$HBV53OpenDmd & kmeans.data$HBV8OpenDmd) == 1, ' is not a function, character or symbol", "'

[R] Error in DESeq Installation

Dear all when I run this cammand to install DESeq it show somw error: ## try http:// if https:// URLs are not supported source("https://bioconductor.org/biocLite.R;) biocLite("DESeq") it shows this error: > source("https://bioconductor.org/biocLite.R;) Bioconductor version 3.4 (BiocInstaller

[R] using nested ifelse when i want to process values from more than 3 columns of data frame

Hi, I would like to process each row of data frame having 8 columns of which I am interested in 4 columns for my analysis.I tried using apply function but I get syntax error,although I checked for missing syntaxes ,couldn't figure out the mistake.Can you also suggest me more efficient way to

Re: [R] rsync: failed to connect to cran.r-project.org (137.208.57.37): No route to host (113)

I still have the same problem today. Has the issue been fixed in Vienna? Le 19/10/2016 à 22:46, Duncan Murdoch a écrit : > On 19/10/2016 11:36 AM, Etienne Borocco wrote: >> Hello, >> >> I folowed this tutorial here: >> http://singmann.org/installing-r-devel-on-linux/ >> >> I tried to install

Re: [R] Lattice equivalent to ggplot function

Hi, Yes, it is available in "latticeExtra" package in function "panel.smoother()". Thanks, Carlos Ortega www.qualityexcellence.es 2016-10-24 15:13 GMT+02:00 Sébastien Bihorel : > Hi, > > The ggplot2 includes the very convenient stat_summary function to summarize > y variable

[R] Lattice equivalent to ggplot function

Hi, The ggplot2 includes the very convenient stat_summary function to summarize y variable data and plot this summary statistic in a y vs x graph. I need to implement similar functionality in a lattice-based framework. Googling this topic using keywords like lattice, equivalent, stat_summary, did

[R] Limit the y-axis line with ggplot2 (not the axis itself, but the line used at the left of the graph)

Hello everybody, Using ggplot2 package, is there a way to force to stop the y-axis line at a specified point ? (not using ylim because I want that some text written using annotate() at the top of the graph is still shown). Bellow is a simple example to show what I would like do: Thanks a

Re: [R] Error In DESeq installation

On 10/23/2016 10:13 PM, Yogesh Gupta wrote: Dear All, I am getting error in DESeq installation in R. package ‘DESeq’ is not available (for R version 3.3.1) source("http://www.Bioconductor.org/biocLite.R;) Bioconductor version 3.4 (BiocInstaller 1.24.0), ?biocLite for help

Re: [R-es] Quitar datos atípicos de una recta

Hola, Otra alternativa que puedes utilizar es filtrar los datos que estén fuera del IQR... Saludos, Carlos Ortega www.qualityexcellence.es El 24 de octubre de 2016, 11:03, Jesús Para Fernández < j.para.fernan...@hotmail.com> escribió: > Buenas Olivier > > > Te lo agradezco, pero no quiero

Re: [R-es] Quitar datos atípicos de una recta

Igual, no hace falta quitarlos: require(MASS) fit=rlm(y~x) # regresión robusta abline(fit) Un saludo. Olivier - Mensaje original - De: "Jesús Para Fernández" Para: "Isidro Hidalgo Arellano" , r-help-es@r-project.org Enviados: Lunes, 24 de

Re: [R-es] Quitar datos atípicos de una recta

Hay un paquete que lo hace, pero no lo he utilizado, así que no sé cómo se porta: "outliers"... Un saludo Isidro Hidalgo Arellano Observatorio del Mercado de Trabajo Consejería de Economía, Empresas y Empleo http://www.castillalamancha.es/ -Mensaje original- De: R-help-es

Re: [R] Using with() to avoid $ ?

Bill et. al. If I understand correctly, your example does not answer my query. I have already acknowledged that the data argument is required for nse formula evaluation. The question is: can with() also be used to evaluate other arguments, some of which also might be in the formula's