similar to: Bug in cor function (PR#7689)

Full_Name: nobody Version: 2.2.0 OS: any Submission from: (NULL) (219.66.34.183) 2 x 2 table, such as > x [,1] [,2] [1,] 10 12 [2,] 11 13 > chisq.test(x) Pearson's Chi-squared test with Yates' continuity correction data: x X-squared = 0.0732, df = 1, p-value = 0.7868 but, X-squared = 0.0732 is over corrected. when abs(a*d-b*c) <= sum(a,b,c,d), chisq.value

Arrrrr, I think I've found a bug in the behavior of the stats::cor function when NAs are present, but in case I'm missing something, could you look over this example and let me know what you think: > a = c(1,3,NA,1,2) > b = c(1,2,1,1,4) > cor(a,b,method="spearman", use="complete.obs") [1] 0.8164966 > cor(a,b,method="spearman",

Full_Name: foo ba baz Version: R2.2.0 OS: Mac OS X (10.4) Submission from: (NULL) (219.66.32.183) chisq.test(matrix(c(9,10,9,11),2,2)) Chi-square value must be 0, and, P value must be 0 R does over correction when | a d - b c | < n / 2 &#65292;chi-sq must be 0

I''ve got a fixed list of several thousand Things, and a User base that may grow to who knows how big (we can only hope ,right?) Users have and belong to many Things. I want to display a list of top Things, based on how many users each has. Things with 0 users are not displayed. Two questions. First, I expect the density of the relatioships to focus on a small percentage of the

Hi, I plan to propose 'Math Aware search' project. After the literature review on the topic, I found Tangent or MIaS system would be a good start. With that, I studied both of the systems well. I plan to pick Tangent because it performs better. Also, it has a good literature(thesis report and few papers available) and reference code available. I keep the summary of both the system, I

> > > > The approach I was thinking would look something like this: > > * instead of Features, which is really a namespace implemented as a > class, we separate out the calculation of the different features > into distinct subclasses of Feature, whose only job is to calculate > a single feature. Currently the FeatureManager calls these (via >

On Sun, Jul 31, 2016 at 12:44:16AM +0100, Olly Betts wrote: > Would a method which swapped two elements of an MSet provide what you > need? That would provide a more generic way to adjust the ranking of > an MSet which for example could be used to implement a diversification > feature or something like SQL "GROUP BY". Isn't the most common use going to be that the

Dear All, I'm guruprasad hegde. I would like to contribute to Xapian through GSOC-2018. Thank you for this wonderful opportunity. My Introduction: I study MSc in Computer science at the University of Saarland. I finished my 4th semester. Some of the courses I took include NLP, Information Retrieval & Data mining, statistical learning. These courses helped me develop the interest in

Using Windows System, R 2.1.0 d is a data frame, 48 rows, 10 columns cor(d) works properly providing all pairwise Pearson correlation coefficients among columns cor.test(d) gives error message "Error in cor.test.default(d) : argument "y" is missing, with no default" Why? Thanks, MCG

Dear R maintainers, R is great. Now that I have that out of the way, I believe I have encountered a bug, or at least an inconsistency, in how Spearman and Kendall rank correlations are handled. Specifically, cor() and cor.test() do not produce the same answer when the data contain NAs. cor() treats the NAs as data, while cor.test() eliminates them. The option use="complete.obs" has

Hi, Is there a simple way to do correlation coefficient tests with "cor.test" like I would do with "cor" function? I have a data frame where each column is a list. ================================================ y <- data.frame(a=sample(30, 20), b=sample(30, 20), c=sample(30,20)) cor(y) ================================================ But, cor.test does not take y

Hello, I am trying to make a correlation matrix in R using cor() and also to get the p-value for each correlation using cor.test(). I can't get these commands to work. I'm getting errors like the following: cor(Pollution, Wet.days) Error in inherits(x, "data.frame") : Object "Wet.days" not found cor("Pollution", "Wet.days") Error in

Hi, I am trying to use R for some survey analysis, and need to compute the significance of some correlations. I read the man pages for cor and cor.test, but I am confused about - whether these functions are intended to work the same way - about how these functions handle NA values - whether cor.test supports 'use = complete.obs'. Some example output may explain why I am confused:

Hello, I'm trying to do cor(x1,x2) and I get the following error: Error in cor.default(x1, x2) : missing observations in cov/cor A few things: 1. I've used cor() many times and have never encountered this error. 2. length(x1) = length(x2) 3. is.numeric(x1) = is.numeric(x2) = TRUE 4. which(is.na(x1)) = which(is.na(x2)) = integer(0) {the same goes for is.nan()} 5. I also try

I'm a little bit confused with how exactly the 'cor' function handles missing values. Should the last two function calls give the same results? Thanks, ...Tao ========================================== >x=rnorm(10) >y=rnorm(10) >x[1]=NA >y[2]=NA >cor(x,y,method="spearman") [1] -0.006060606

Hallo! Is there an error in cor to calculate Spearman correlation with cor if there are NA's? cor.test gives the correct result. At least there is a difference. Or am I doing something wrong??? Does anybody know something about this? a<-c(2,4,3,NA) b<-c(4,1,2,3) cor(a, b, method="spearman", use="complete.obs") # -0.9819805 cor.test(a, b,

Dear Sir: I am interesting in to call function "cor" from C code. The reason for this, is that I need to obtain a matrix of correlation in a C program, and I have think to link my program in C code with R. But I don?t know make this link. I have read R-exts.pdf document, but I have not found a direct way to link. But I have a problem which I have not found information in

Hello all, I'm trying to use cor.test across a range of values via the apply command, c <- apply(X,1,cor.test,y) where X is an array, giving me multiple output from cor.test. I can access individual elements of this by e.g. c[[1]] or c[[1]]$estimate or c[[n]] or whatever, but is there a way to get out the vector of all estimates, or all p-values? i.e. if I want to get out a vector p

The following is internally consistent, but not intuitive: R : Copyright 2002, The R Development Core Team Version 1.4.1 (2002-01-30) [...] > library(ts) > x<-rnorm(100) # white noise > xTS<-ts(x,start=1) # as time series > xTSl<-lag(xTS,lag=-1) # lagged once > cor(xTS,xTSl) # Big surprise [1] 1 > cor(cbind(xTS,xTSl),use="pairwise") # what was really

Hello, I want to compute a correlation test but I do not want to use the degrees of freedom that are calculated by default but I want to set a particular number of degrees of freedom. I looked in the manual, different other functions but I did not found how to do it Thanks in advance for your answers Yours Florence Dufour PhD Student AZTI Tecnalia - Spain