similar to: generating a new variable based on results of a by command

Hi all. I have a numerical function f(x), with x being a vector of generic size (say k=4), and I wanna take the numerically computed gradient, using deriv or numericDeriv (or something else). My difficulties here are that in deriv and numericDeric the function is passed as an expression, and one have to pass the list of variables involved as a char vector... So, it's a pure R programming

>From Internet I downloaded the file Hmisc.zip and used it for R package updation. and R gave the message 'Hmisc' successfull unpacked. But when I use the functions like aregImpute the package is displaying coundn't find the function Where as in help.search it is giving that use of the function >

I have got a dataframe containing measurement of aircraft noise like this: > Id <- c(1,4,5,2,3,6,4,1,2,5,6,3) > Noise <- c(88,94,97,98,92,56,103,102,87,95,92,97) > Height <- c(190, 150, 120, 115, 188, 104, 101, 189, 146, 111, 124, 126) > > df <- data.frame(Id, Noise, Height) Now I would like to split this in two new dataframes. The first one containing the rows

Thanks Dimitris!!! That's much clearer now. Still have a lot of work to do this weekend to understand every bit but your code will prove very useful. Cheers, Aziz -----Original Message----- From: Dimitrios Rizopoulos [mailto:Dimitris.Rizopoulos at med.kuleuven.be] Sent: May 12, 2006 4:35 PM To: Chaouch, Aziz Subject: RE: [R] Maximum likelihood estimate of bivariate

Hi all, My question is not really urgent. I can write a loop and solve the problem. But I know that I'll be in a similar situation many more times so it would be useful to find out the answer Is there a fast way to perform linear fit to all the columns of a matrix? (or in the one dimension of a multi-dimensional array.) I'm talking about many single linear fits, not about a multiple fit.

Dear R-devels, I'd like to create a plot method for a class of objects that passes the '...' argument to both plot() and legend(), e.g., x <- list(data = rnorm(1000)) class(x) <- "foo" plot.foo <- function(x, legend = FALSE, cx = "topright", cy = NULL, ...){ dx <- sort(x$data) plot(dx, dnorm(dx), type = "l", ...) if (legend)

At the risk of being wacked for asking what should be obvious.... I have a data frame with one categorical variable "CAT" and several numeric variables. I want to be able to get simple statistics on the numeric variables by level. For example, just as you can use table (CAT) to get the counts, I'd like to be able to get the means and sums by category. If someone could point me

Dear All, I got these results from the example in the function "dbeta": >x <- seq(0, 1, length=21) > dbeta(x, 1, 1) [1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 Any Idea? TIA Giovanni dr. Giovanni Parrinello Section of Medical Statistics Department of Biosciences University of Brescia 25127 Viale Europa, 11 Brescia Italy Tel: +390303717528 Fax: +390303701157

hi all: xlim and ylim are used to define the interval limits of a plot. I'm interested in the scale of values between this limits. suppose xlim=c(0,10) we can have e.g. 0 5 10 0 2 4 6 8 10 0 1 2 3 4 5 6 7 8 9 10 which is the parameter that allows me to modify this? thanks in advance alexandre

I have a vector that has 1,974 elements and each element is one of the following (B, F, N, Y). How do I recreate that vector accept in the place of N put 0 and in the place of B, F or Y put a 1? Thanks, Jacob [[alternative HTML version deleted]]

Dear useR I want to know why package gregmisc did not work very well. I did not find this package in my library directory. > local({a <- CRAN.packages() + install.packages(select.list(a[,1],,TRUE), .libPaths()[1], available=a, dependencies=TRUE)}) trying URL `http://cran.r-project.org/bin/windows/contrib/2.0/PACKAGES' Content type `text/plain; charset=iso-8859-1' length 21630 bytes

Hi R-users, How do I calculate a number of NA's in a row of every second column in my data frame? As a starting point: dfr <- data.frame(sapply(x, function(x) sample(0:x, 6, replace = TRUE))) dfr[dfr==0] <- NA So, I would like to count the number of NA in row one, two, three etc. of columns X1, X3, X5 etc. Thanks in advance Lauri [[alternative HTML version deleted]]

Hi everyone, I am new to R, but it's really great and helped me a lot! But now I have 2 questions. It would be great, if someone can help me: 1. I want to integrate a normal distribution, given a median and sd. The integrate function works great BUT the first argument has to be a function so I do integrate(dnorm,0,1) and it works with standard m. and sd. But I have the m and sd given.

Dear Rs: outer(1:3, 1:3, function(df1, df2) qf(0.95, df1, df2)) I compare this F distribution results with the table, the answers were perfect. But I need to see for chi-sqaured distribution. When I employed the similar formula outer(1:3, 1:3, function(df1, df2) qchisq(0.95, df1, df2)) , I am getting unexpected results. I need to see the following values: p=0.750 ..... 1 1.323

Dear friends, After running the lm() model, we can get summary resluts like the following: Coefficients: Estimate Std. Error t value Pr(>|t|) x1 0.11562 0.10994 1.052 0.2957 x2 -0.13879 0.09674 -1.435 0.1548 x3 0.01051 0.09862 0.107 0.9153 x4 0.14183 0.08471 1.674 0.0975 . x5 0.18995 0.10482 1.812 0.0732 . x6 0.24832 0.10059 2.469 0.0154 * x7

Thanks a lot to Demitris for a prompt answer some minutes ago on another tread (see below). To avoid excess mails on the list, I move onto next question: I have another small plotting problem that confuses me. I want to plot results from a field trial series, using the numbers of the trials as symbols in the plot. pch = as.character(trial_no) works fine, but truncates the trial number to the

for example: > a$tic[1:10] [1] "AIR " "ABCB " "ABXA " "ACMR " "ADCT " "ADEX " [7] "ABM " "AFCE " "AG " "ATG " Can anyone please tell me how to strip the white spaces from a$tic? Thanks, Roger [[alternative HTML version deleted]]

Hi Everyone, I have some data that predicts both a nominal and ordinal response variable. I was wondering what packages in R would help me analyze the data? I was also curious if anyone could recomend me some textbooks that would help with the analysis of such data? I have the 5th edition of "Applied Multivariate Statistical Analysis" by Richard A. Johnson and Dean W. Wichern

Dear R helpers: Thanks for the previous reply. I am using Friedman racing test. According the the book "Pratical Nonprametric Statistic" by WJ Conover, after computing the statistics, he suggested to use chi-squared or F distribution to accept or reject null hypothesis. After looking into the source code, I found that R uses chi-sqaured distribution as below: PVAL <-

Hello there! My operating system is Windows XP, my version of R is the latest (R-2.5.0). Recently I have downloaded the package "mvtnorm" and a problem with the command "pmvnorm" occured. Trying to enter the lines ... A <- diag(3) A[1,2] <-0.5 A[1,3] <- 0.25 A[2,3] <- 0.5 pvmnorm(lower=c(-Inf,-Inf,-Inf), upper=c(2,2,2),mean = c(0,0,0), corr=A) I got the following