similar to: Using Flexible Discriminant Analysis (fda) in mda

Hi all, Has anyone tried to do k-fold cross validation for flexible discriminant analysis ( mda library), for example, using crossval() in bootstrap? The problem is that the function crossval() requires a separate matrix for predictors and another for responses, whereas the function fda(), using the formula argument only. Is there another way of doing k-fold cross validation for functions which

Hello, I am using the mda package and in particular the fda routine to classify in term of gear a set of 20 trips. I preformed a flexible discriminant analysis (FDA) using a set of 151 trips. FDAT1 <- fda(as.factor(gear) ~ . , data =matrizR) A total of 22 predictors were considered. 20 of the predictors are "numeric" and 2 are "factors/discrete". The resulting FDA

Hello R help list, I am using the mda package and in particular the fda routine to classify a set of 4409 trips. I preformed a flexible discriminant analysis (FDA) using a set of 148 trips. A total of 36 predictors were considered. the resulting FDA rule was applied to the 4409 trips and for the same predictors in order to predict to which group the trip will belong. A consistent error is

Dear Dr Hornik / R help list, I am using the mda package and in particular the fda routine to classify a set of 162 neurons falling in to 11 neuronal cell types according to 17 morphological variables. I would like to use a cross-validation approach in which I split the data, train with one part amd then test the predictive accuracy of the discriminant functions with the remaining part. However

Dear all, I'm trying to build some fda objects using smooth.pos() from fda package. Here is what I try: >X <-c(0.4541139, 0.4802537, 0.5091228, 0.3894931, 2.1512258, >7.9301281, 62.3876109, 54.1168247, 67.8769904, 91.0670615, 20.0682440) >basis <- create.bspline.basis(c(-100, 100), 7, 5) >MDA.fdPar <- fdPar(basis, 2, 0.01) >MDA.fda.joint <-

For a private package ("soon" to be on CRAN), I started looking at and thinking about the function confusion() from the mda package and wondered if it wouldn't make sense to provide the generic function in base R and also think about making the default for the `true' argument equal to fitted(object). One could write methods for confusion() for almost all classifiers which

Shuji, I suspect that bruto blows up because your data are linearly separable. To see this (if you didn't already know), try library(lattice) splom(~x, groups = y) and look at the first row. If you are trying to do classification, there are a few methods that would choke on this (logistic regression) and a few that won't (trees, svms etc). I would guess that bruto is in the latter

** High Priority ** I am a french student working on discriminant analysis issues. I am a new user of R language and have a few questions about its use : + About the mda package how can I plot the decision boundaries in the space of predictors from the results of the fda function ? + Does R include 3-D plots ? + How can I use bootstrap and cross-validation in classification ? I

NEW: CRAN/src/contrib/devel/mda_0.1-1.tar.gz I have made a first shot at porting the Hastie & Tibshirani mda package t= o R ... this is almost not tested at all ... but it works for the iris data and what else could a statistician be possibly interested in anyway = :-) All BRUTO stuff is missing because there are some unresolved symbols: R.binary: can't resolve symbol

Hello, I am using the function mda of the mda library in order to discriminate 4 groups with 8 explanatory variables. I only have 66 observations. I tested all possible combinations of those variable and run for each the Mixture Discriminant Analysis. For some iterations, I got an error message: "error in kmeans(xx, start): initial centers are not distinct". I understood that the

Hi, I'm using mda library to solve a discriminant analysis. I get results, but the thing is that I want to use Fisher's method to obtain the classification functions and I'm lost in what I should do: libraries to use, ... Can anybody give me a clue?? Thanks. Carlos Niharra L??pez

Dear R users, I'm trying to perform flexible discriminant analysis (fda) with method bruto. I applied the fda function on my training data: bruto.fda <- fda (fda.formula,data=train.data) where fda.formula is: PRES ~ VA_D123 + VA_D124 + VA_D127 + VA_DARU + VA_DCAN + VA_DFON + VA_DLAP + VA_DRID + VA_DRIR + VA_VVEG + VA_WDIN + VA_DIF3 + VA_DIF4 + VA_DIF5 + VA_CAAC + VA_CABC +

Hi Alejo, According to my knowledge the two plots are different because in the first one a point belongs to a group depending on its group in the data whereas in the second plot a point belongs to the group predicted by the linear discriminant analysis. I hope somebody will correct me if I am wrong. Alain Alejo C.S. wrote: > Hi Alain, this is the code: > > > library(MASS) >

Hello. First, I want to thank those responsible for Dovecot IMAP as it was a real treat to implement in comparison to my mostly-failed attempts with Cyrus. The passwd-file authentication was exactly what I needed as I really didn't want to have to deal with PAM or LDAP but where I am setting up a server with virtual accounts. I'm using Postfix as an MTA, and it quite handily passes

Can one perform a QDA in R? I do not see it anywhere within the mda package. Any pointers here would be appreciated. Thanks, cjf -- ~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~* Christopher J. Fonnesbeck Ph.D. Student Georgia Cooperative Wildlife Unit University of Georgia Athens, GA 30602 Email: cjf at fonnesbeck.net Yahoo: fonnesbeck_chris ~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*~*

Hi, I''m currently thinking of writing my bachelorthesis about the use of model driven architecture within webdevelopment. I''m now trying to figure out about the benefits of using MDA to generate Rails Code. So, which Components of an Web-/Rails App would you like to be generated via MDA? In which way do you think the generators shipped with Rails can be improved? -- Posted via

Hello all, So I'm doing some data analysis using MARS. I have a matrix of 65 independent variables, from which I'm trying to predict 71 dependent variables. I have 900+ data points (so a 900x136 matrix of data), which I randomly split into training and validation sets, for ~450 data points in each set. Occasionally, this works well, and I get decent predictions. However, quite often

I was trying to produced bagged importance estimates of attributes in earth using the caret package with the following commands:   fit2 <- bagEarth(loyalty ~ ., data=model1, B = 10)   bagImpGCV <- varImp(fit2,value="gcv") My bootstrap estimates are produced however the second command "varImp" produces the following error:    Error in UseMethod("varImp") : no

** High Priority ** Hello R users My issue is both theorical and technical. I would like to run a penalised discriminant analysis with the fda() function, but I don''t know all the details of splines theory. I try on the example of the phonems from the article "Penalised Discriminant Analysis" of Hastie, Buja and Tibshirani 1994 : 5 groups and 256 variables. The 256

Hi everyone, I suspect this is an easy task however I've not been able to accomplish it. I'd like to create an mtext title which has certain words bold, the rest not bold. So far I've been able to create one which is all bold, one which is all not bold and one which has bold and not bold superimposed on one another. Any suggestion would be appreciated. Many thanks, Joe Retzer # Not