similar to: OT: Strange bootstrap approach to significance testing

Hi all, I suspect the answer to this query will be the tongue-in-cheek "use a quantum computer", but I thought my understanding might be sufficiently limited that I'm missing a simpler option. I'm looking for a way to cycle through all possible combinations of 2 groups of data. For 10 data points, that's 2^10 combinations, for 20 data points it's 2^20, etc. combn() from

Hi all, I'm curious if anyone has coded an Expectation-Maximization algorithm that could help me model some circular data I have. I'd like to model it as a mixture of uniform and Von Mises centered on 0, so the only free parameters is the mixing proportion and the kappa of the Von Mises. I couldn't find anything in the contributed packages that seemed to suit this purpose. Any

Hi folks, I have circular data that I'd like to model as a mixture of a uniform and a Von Mises centered on zero. The data are from 2 groups of human participants, where each participant is measured repeatedly within each of several conditions. So, the data frame would look something like: ######## design = expand.grid( person = 1:20 , variable1 = 1:2 , variable2

The ez package was developed to aid those that are new to statistical programming. Over the course of several years of helping colleagues and students learn R, I observed that folks are often initially turned off R because they have difficulty obtaining SPSS-like results quickly (SPSS is the dominant environment in my field, psychology). ez attempts to fill this gap, providing quick and easy

The ez package was developed to aid those that are new to statistical programming. Over the course of several years of helping colleagues and students learn R, I observed that folks are often initially turned off R because they have difficulty obtaining SPSS-like results quickly (SPSS is the dominant environment in my field, psychology). ez attempts to fill this gap, providing quick and easy

Hi guRus, My discipline (experimental psychology) is gradually moving away from Null Hypothesis Testing and towards measures of evidence. One measure of evidence that has been popular of late is the likelihood ratio. Glover & Dixon (2005) demonstrate the calculation of the likelihood ratio from ANOVA tables, but I'm also interested in non-parametric statistics and wonder if anyone has any

I'm having trouble centering multi-line strip text in lattice. As the code below demonstrates bounding box of the text is centered within the strip, but the first line isn't centered in relation to the longer second line. The "adj" argument to par.strip.text doesn't seem to do much. Suggestions? a=data.frame( x=rep(1:10,2) ,y=rep(1:10,2) ,z=rep(c('First Line\nLonger

On my machine (Mac OS 10.5.6, R 2.8.1) the following plot is drawn such that a substantial portion of the descender of the title is covered by the plot: library(ggplot2) qplot(x=1:10,y=1:10,main='p q j g') -- Mike Lawrence Graduate Student Department of Psychology Dalhousie University www.thatmike.com Looking to arrange a meeting? Do so at: http://www.timetomeet.info/with/mike/ ~

Hi all, I have data from an experiment with 3 independent variables, 2 are within and 1 is between. In addition to the dependent variable, I have a covariate that is a single measure per subject. Below I provide an example generated data set and my approach to implementing the ANCOVA. However the output confuses me; why does the covariate only appear in the first strata? Presumably it should

Hi folks, I originally tried R-SIG-Mixed-Models for this one (https://stat.ethz.ch/pipermail/r-sig-mixed-models/2010q3/004170.html), but I think that the final steps to a solution aren't mixed-model specific, so I thought I'd ask my final questions here. I used gamm4 to fit a generalized additive mixed model to data from a AxBxC design, where A is a random effect (human participants in

All, Thanks for all of your help & advice! I created a plot starting with qqnorm, if I remember right, but I had to add a LOT of extras. I was surprised that it doesn't include the probability (e.g. 50% at mean) and instead provides the standard deviations (e.g., 0 at mean) on the axis. Plus, there is no line through Q1 & Q3 to help give a sense of the normality of the graph.

Hi guRus, I'm looking for advice on a good way to approach analysis of some multi-level data I've obtained. I had humans classify words and measured response time. Words were 10 positive words ("happy", "joy", etc) and 10 negative words ("sad","grumpy", etc). Words were also presented in either white, red or green color. All variables were

Hi all, I've noticed that many computational neuroscience research groups use MATLAB. While it's possible that MATLAB may have some features unavailable in R, I suspect that this may instead simply be a case of costly tradition, where researchers were taught MATLAB as students and pay for it as researchers because it's all they know. I'd like to attempt to break the cycle by

Dear R user, I am trying to understand this following code. Basically it's using a permutation method to calculate p value. But I would like to know exactly how the permutation works. #calculates null statistics tt0 <- 0 set.seed(123) B <- 100 for(i in 1:B) { v <- sample(y) tt0 <- c(tt0,ttest(dat,v)$tt) } tt0 <- tt0[-1] #form p-values att <- abs(tt) att0 <- abs(tt0) v

Hi all, Where f(x) is a logistic function, I have data that follow: g(x) = f(x)*.5 + .5 How would you suggest I modify the standard glm(..., family='binomial') function to fit this? Here's an example of a clearly ill-advised attempt to simply use the standard glm(..., family='binomial') approach: ######## # First generate some data ######## #define the scale and location of

I have a question regarding significance testing for the difference in the ratio of means. The data consists of a control and a test group, each with and without treatment. I am interested in testing if the treatment has a significantly different effect (say, in terms of fold-activation) on the test group compared to the control. The form of the data with arbitrary n and not assuming equal

dear group members, I am looking for a function that assess the stability of cluster. The result of hclust function is an hclust object which can be plot as a dendrogram. However to have confidence in the tree topology usualy bootstap is applied. I understand that I can apply bootstarp on the original data and then run hclust(dist() ) as much as I resampled but how to comapre the topologies the I

Insightful are pleased to announce we are now taking bookings for our latest course on "Bootstrap methods and permutation tests" in the UK on 23rd - 24th October. This course will focus in particular on two resampling methods, bootstrapping and permutation tests, which have been applied successfully to areas of statistical modelling where "traditional" standard errors,

Hi all, I wondered whether anyone has some advice on a stats-related 'sanity check', as I ran a nonparametric multivariate test (mulrank function as decribed by R. Wilcox, 2005) on both systems, but got different results (please see below for the system-specific outputs)! The functions I used are attached as well. Any advice would be much appreciated! Thanks in advance for getting back to

I like to bootstrap regression models, saving the entire set of bootstrapped regression coefficients for later use so that I can get confidence limits for a whole set of contrasts derived from the coefficients. I'm finding that ordinary bootstrap percentile confidence limits can provide poor coverage for odds ratios for binary logistic models with small N. So I'm exploring BCa confidence