similar to: will one of you help me advocate a change in t.test (patch attached)

I'd like to learn the process of revising R functions & packages and then submitting proposed patches to the R Core team. Would someone be willing to mentor me through one example? For starters, consider an example. I'd like to revise the t.test function to return the stderr value to the user. We only need to change the "rval" in the third-from-the end line of

As a very new user of R, and a user of S with very limited experience, I thought I would start humbly with a simple t.test. The response to the command sequence sample <- scan() 4 5 6 7 8 9 t.test(sample,mu=20) rather surprised me, because of the idiosyncratic choice of a confidence interval for the mean of the population from which the sample was drawn. I asked my colleague Bob Henery

Hello, I'm looking to calculate a 95% confidence interval about my estimate for a sample's weighted mean, where the calculated confidence interval would equal the t-test confidence interval of the sample in the case when all of the weights are equal. My initial thought was to simply implement a modified version of the t-test function but substituting the weighted variance and mean for the

Hello, I wuold like to propose my modifications of the original cor.test to you : I tried to calcolate the correct p-value for Spearman and Kendall's test with ties. Let me know what you think. Thanks you for your time. Antonietta di Salvatore test <- function(x, ...) UseMethod("test") test.default <- function(x, y, alternative = c("two.sided",

Dear R Users, Is the p-value reported in a two-tailed binomial exact test in error or is it a feature? If it is a feature, could someone provide a reference for its two-tailed p-value computations? Using Blaker's (2000 - Canad. J. Statist 28: 783-798) approach,the p-value is the minimum of the two-tailed probabilities $P \left(Y\geq y_{obs}\right)$ and $P\left(Y\leq y_{obs}\right)$

Hi, R newb here. I've coded a function that inputs N dimensional array(s) [or class=numeric if it's dim=1] of coefficients and tstats, where dim(coef_matrix)=dim(tstat_matrix), it will then output a same dimension matrix of coefficients pasted to tstats in brackets pasted to significance stars. If I go straight to the code INSIDE the function, it works 100% as it's supposed to. The

Full_Name: Dirk Koschuetzki Version: 2.1.1 OS: source code Submission from: (NULL) (194.94.136.34) Hello, >From the source code (R-2.1.1, file: .../R-2.1.1/src/library/stats/R/) ****************************** cor.test.default <- function(x, y, alternative = c("two.sided", "less", "greater"), method = c("pearson", "kendall",

Hello! I am running a very simple mini Monte-Carlo below using the function tstatistic (right below this sentence): tstatistic = function(x,y){ m=length(x) n=length(y) sp=sqrt( ((m-1)*sd(x)^2 + (n-1)*sd(y)^2)/(m+n-2) ) t=(mean(x)-mean(y))/(sp*sqrt(1/m+1/n)) return(t) } alpha=.1; m=10; n=10 # sets alpha, m, n - for run 1 N=10000 # sets the number of simulations n.reject=0 # counter of num.

Hi, people. I was a bit intrigued by the message quoted below. Indeed, if pt() is given a matrix, it returns a matrix. Should this feature be documented? ?pt speaks about "a vector of quantiles", and says nothing about the type of what it returns. The same might presumably apply to other distribution-related functions. ----- Forwarded message from Martyn Plummer <plummer at

Hello, everybody! I'm back to ask the obvious on behalf of the silent majority :) Today a student asked me "what standard error was used in this t.test output". I looked into it and was a little surprised that a t.test output object does not have a "slot" for the standard error. Of course, we can reconstruct the se=mu-hat/t, but I was surprised. Do you think it would

Hi I just discovered the answer thanks to a previous thread from Peter Daalgart The command is: sapply(test, "[[", "statistic") Cheers, Daniel ----- Original Message ----- To: r-help at r-project.org Subject: extracting values from a "by" function Date: Sun, 6 Jul 2008 05:59:04 +0800 Hello, I am trying to extract t and pvalues from a 1000 ttests using the

Hello, I am trying to extract t and pvalues from a 1000 ttests using the by-function but everythinhg I tried did not work. Unfortunately googling "by" is not very helpful. Any help will be very appreciated. Cheers, Danile Stall *creating a data set library(MASS) dataset <- mvrnorm(160, mu, Sigma) dataset <- as.data.frame(dataset) dataset$GROUP <- rep(1:10, each=16) data.uni

Here's one possibility, assuming muhat and sigmahat are estimtes of mu and sigma from N iid draws of N(mu, sigma^2): tStat <- abs(x - muhat) / sigmahat pValue <- pt(tStat, df=N, lower=TRUE) I'm not quite sure what df tStat should have (exercise for math stat), but given fairly large N, that should make little difference. Andy > From: Ross Clement > > Hi. I have a

Dear R list members, I'd like to make a graph of coefficients of the intercept, variable 1, and variable 2 (and possibly the interaction between variable 1 and variable 2). When I use the lmList function as attached below, it shows a nice coefficient graph. > PACRP.lis <- lmList(PAffect ~ CRPC + CRPT + CINT | ID, redinteract) > coef(PACRP.lis) > PACRPlis.coef <-

o <- (structure(list(sand.silt = structure(list(statistic = structure(185, .Names = "W"), parameter = NULL, p.value = 0.0478835773838087, null.value = structure(0, .Names = "location shift"), alternative = "two.sided", method = "Wilcoxon rank sum test with continuity correction", data.name = ".column by site"), .Names =

Hello, I've posted a question about this subject yesterday, but since there was no R code to comment, no one did. I'm trying to have the print method for class 'htest' print some extra information common in some test, like the time series linearity related tests. Many of them have an 'order' parameter, representing a lag or embedding dimension, and it would be a nice

I am trying to assign values to a vector (pvalue). Similar code works in C but not in R. What am I doing wrong? r <- pvalue <- 0 for(i in (1:(k-1))){ for(j in (i+1):k){ r <- r+1 tstat <- (means[i]-means[j])/rms pvalue[r] <- 2*(1-pt(abs(tstat),df)) } } Thank you. Peter B. -- Peter B. Mandeville mandevip at deimos.tc.uaslp.mx Jefe del

Hi all, I just used power.t.test() in Version 1.9.0 beta (2004-03-31) today under FC1. The following is the output: > power.t.test(delta = .5, power = .95, type = "paired") $n [1] 53.94062 $delta [1] 0.5 $sd [1] 1 $sig.level [1] 0.05 $power [1] 0.95 $alternative [1] "two.sided" $note [1] "n is number of *pairs*, sd is std.dev. of *differences* within

RE t.test in R I objected a day or two ago to the behaviour of the one-sample t.test in R where it is easy to generate a "confidence interval" for the mean of the population which does not contain the sample mean, in the case where the null hypothesis is rejected. It now appears that the same behaviour is latent in the code for the two-sample version of this test. The relevant lines

I am asking this question to see if it is possible or desirable to build a compilation/runtime system for C/C++ that can support the following: 1. allow bc to call native (in dynamically loaded *.so) 2. allow native to call bc (through JIT or interpreter) 3. can compile/interpret C/C++ sources _BASED_ on type info in precompiled bc Motivation: The class files produced by the java compiler