Re: [R] Variables selection in Neural Networks

Thanks to answer Matthew. I hope that there is some function because to do all that by hand with so many variables it can be horrible. In addition, how it would make to see those that are not correlated and those that yes. Which is the threshold to decide one or another thing? _Fede_ Matthew

[R] Variables selection in Neural Networks

models? Regards. _Fede_ -- View this message in context: http://www.nabble.com/Variables-selection-in-Neural-Networks-tp16911299p16911299.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https

Re: [R] Multinomial Logit Regression

w how can be the sintaxis in my case. In case it serves as help in glm I do: z <- glm(response.variable~., data=dataset, subset=train.set, family=binomial(link="logit)) Thank you. _Fede_ _Fede_ wrote: > > Hi all, > > I have a dataset with a response variable with thre

[R] Multinomial Logit Regression

zelig(Alt.categ ~., model = "mlogit",data=train.set) Error in terms.formula(object[[i]], specials = c("id", "tag")) : '.' in formula y there is no 'data' argument What's wrong here? How can I make this in the correct form? Thank you in advance.

Re: [R] Extract from matrix

Thank you all for your help. Fede _Fede_ wrote: > > Hi all. > > I have certain problem with the extraction of data from matrices. I know > how extract elements from a matrix, but what I would like to do is to > extract a concrete number, not an element. For example if I ha

[R] Extract from matrix

Hi all. I have certain problem with the extraction of data from matrices. I know how extract elements from a matrix, but what I would like to do is to extract a concrete number, not an element. For example if I have this matrix X: [,1] [,2] [,3] [,4] [1,]3 13 23 33 [2,]9 19

Re: [R] Bootstrap Confidence Intervals

That is what I wanted. Thank you very much Chuck. _Fede_ Chuck Cleland wrote: > > _Fede_ wrote: >> Sorry for the previous message. I have been reading the help page about >> boot >> library and I have already understood what the arguments made reference >>

Re: [R] Bootstrap Confidence Intervals

bootstrap samples? How can I access them when I use boot function? Thank you in advance. _Fede_ Chuck Cleland wrote: > > _Fede_ wrote: >> Hi again. >> >> Watching this example that appears in the help page >> >> ratio <- function(d, w) sum(d$x * w)/sum(d$u *

Re: [R] Bootstrap Confidence Intervals

Can you explain me, please? Thanks. _Fede_ Chuck Cleland wrote: > > _Fede_ wrote: >> Hi again. >> >> Watching this example that appears in the help page >> >> ratio <- function(d, w) sum(d$x * w)/sum(d$u * w) >> city.boot <- boot(city, ratio, R = 999,

Re: [R] Bootstrap Confidence Intervals

e = c("norm","basic","perc","bca")) But I don't know why this don't work. The editor window shows the following error message: Error in statistic(data, original, ...) : unused argument(s) (1:20) I suppose that something is wrong with my data but I

[R] Bootstrap Confidence Intervals

"bca")) But the output shows the next error: Error en if (ncol(boot.out$t) < max(index)) { : argumento tiene longitud cero I don't know what is wrong. I hope that somebody can help me. Sorry for my english. All have a nice new year. _Fede_ -- View this message in