similar to: Sampling distribution (PDF & CDF) of correlation

Hi all, I'm using the code below within a loop that I run thousands of times and even with the super-computing resources at my disposal this is just too slow. The snippet below takes about 10s on my machines, which is an order of magnitude or two slower than would be preferable; in the end I'd like to set the number of monte carlo experiments to 1e4 or even 1e5 to ensure stable

Hi all, Hopefully this will be quick, I'm looking for pointers to packages/ functions that would allow me to calculate the power of a t.test when the DV has measurement error. That is, I understand that, ceteris paribus, experiments using measure with more error (lower reliability) will have lower power. Mike -- Mike Lawrence Graduate Student, Department of Psychology, Dalhousie

Hi all, By default a call to xyplot from the Lattice package when using 2 factors [eg xyplot( dv~iv | XY * AB ) ] yields the following shingle structure: |_A_|_A_|_B_|_B_| |_X_|_Y_|_X_|_Y_| However, I'm wondering if it is possible to merge the upper shingle within levels of that factor, as in: |___A___|___B___| |_X_|_Y_|_X_|_Y_| Mike -- Mike Lawrence Graduate Student, Department of

Suppose F(x, y; rho) is the cdf of a bivariate normal distribution, with standardized marginals and correlation parameter rho. For any fixed x and y, I wonder if F(x, y; rho) is a monotone increasing function of rho, i.e., there is a 1 to 1 map from rho to F(x, y; rho). I explored it using the function pmvnorm in package mvtnorm with different x and y. The plot suggests the statement may be true.

Hi all, This is my first post to the developers list. As I understand it, aggregate() currently repeats a function across cells in a dataframe but is only able to handle functions with single value returns. Aggregate() also lacks the ability to retain the names given to the returned value. I've created an agg() function (pasted below) that is apparently backwards compatible (i.e.

Hi all, Consider the following function: #### my.func = function(x){ y=ifelse(x>-.5,0,ifelse(x< -.8,abs(x)/2,abs(x))) print(c(x,y)) #print what was tested and what the result is return(y) } curve(my.func,from=-1,1) #### When I attempt to find the maximum of this function, which should be -.8, I find that optimize gets stuck in the plateau area and doesn't bother testing the

Hi all, A suggestion derived from discussions amongst a number of R users in my research group: set the default column names produced by aggregate () equal to the names of the objects in the list passed to the 'by' object. ex. it is annoying to type with( my.data ,aggregate( my.dv ,list( one.iv = one.iv ,another.iv = another.iv ,yet.another.iv = yet.another.iv )

I'm looking to analyze a large data set: a within-Ss 2*2*1500 design with 20 Ss. However, aov() gives me an error, reproducible as follows: id = factor(1:20) a = factor(1:2) b = factor(1:2) d = factor(1:1500) temp = expand.grid(id=id, a=a, b=b, d=d) temp$y = rnorm(length(temp[, 1])) #generate some random DV data this_aov = aov( y~a*b*d+Error(id/(a*b*d)) , data=temp ) While yields the

Hi all, Just thought I'd share something I discovered last night. I was interested in creating animations consisting of a series of plots and after finding very little in the usual sources regarding animation in R directly, and disliking the imagemagick method described here (http://tolstoy.newcastle.edu.au/R/help/05/10/13297.html), I discovered that if one exports the plots to a

Hi all, Worked & looked around for a while on this to no avail. I'm trying to create a plotmath expression that achieves: ?i >> 0 and while: expression(Delta*i>0) comes close, I'd prefer to have the >> (denoting "very much greater than"). Maybe >> is a non-standard expression and therefore not supported? Mike -- Mike Lawrence Graduate

Hi all, I understand that it is simple to create data with a specific correlation (say, .5) using mvrnorm from the MASS library: > library(MASS) > set.seed(1) > > a=mvrnorm( + n=10 + ,mu=rep(0,2) + ,Sigma=matrix(c(1,.5,.5,1),2,2) + ,empirical=T + ) > a [,1] [,2] [1,] -1.0008380 -1.233467875 [2,] -0.1588633 -0.003410001 [3,] 1.2054727 -0.620558768

Hi all, I have collected response time data from 178 participants ('sub') for each combination of 4 within-Ss factors ('con','int','tone','cue'). Additionally, I have recorded the gender of each participant, so this forms a between-Ss factor ('gender'). Normally this would be analyzed using aov:

Has anyone successfully compiled pnmath (http://www.stat.uiowa.edu/~luke/R/experimental ) for an intel processor running mac OS 10.5? When I attempt to do so via the R package installer (choosing "Local Source Package" and pointing to the pnmath_0.0-2.tar.gz file), I get the following errors: * Installing *source* package 'pnmath' ... ** libs ** arch - i386 gcc -arch i386

Hi R-users,   I have this code below and I understand the error message but do not know how to correct it.  My question is how do I get rid of “with absolute error < 7.5e-06” attach to value of cdf so that I can carry out the calculation.   integrand <- function(z) { alp  <- 2.0165   rho  <- 0.868   # simplified expressions   a      <- alp-0.5   c1     <-

Hi R-users,   I have this code here: library(numDeriv)   fprime <- function(z) { alp  <- 2.0165;   rho  <- 0.868;   # simplified expressions   a      <- alp-0.5   c1     <- sqrt(pi)/(gamma(alp)*(1-rho)^alp)   c2     <- sqrt(rho)/(1-rho)   t1     <- exp(-z/(1-rho))   t2     <- (z/(2*c2))^a   bes1   <- besselI(z*c2,a)   t1bes1 <- t1*bes1   c1*t1bes1*t2 }   ## Newton

Hi all, I'm working with data to which I'm fitting three-parameter weibull distributions (shape, scale & shift). The data are of low sample sizes (between 10 and 80 observations), so I'm reluctant to check my fits using chi-square (also, I'd like to avoid bin choice issues). I'd use the Kolmogorov-Smirnov test, but of course this is invalid when the distribution

Hi all, I am extremely newbie to R. Can anybody jump-start me with any clues as to how do I get a cumulative histogram from two independent variables, cumhist(X,Y) ? -jose [[alternative HTML version deleted]]

Hello, i'm trying to find a more modern system to reproduce the functionality that was available through the Histoscope program (from Fermilab). Namely, the capability of connecting to a running process and having plots update in realtime in response to new data. Is this possible with R? Thank you, Charles Cosse [[alternative HTML version deleted]]

#Quick one hopefully. Shouldn't dnorm be returning the pdf? Last time I checked, #a probability shouldn't be greater than 1 as produced by: curve(dnorm(x,0,.1),from=-1,to=t) #Shouldn't I be getting an axis more like that produced by: f=function(x,m,s){ y=rep(NA,length(x)) for(i in 1:length(x)){ y[i]=integrate( dnorm , upper=x[i]+sqrt(.Machine$double.eps) ,

This question might seem silly, because I felt that it MUST be in the mailing list archives or help files somewhere, but I simply couldn't find it. I want to make some simple CDF (cumulative distribution function) plots to check whether distributions are Gaussian / normal. But in order to check how "normal" the distribution is, I really need the y-axis to be Gaussian as well