Re: [R] glm.fit: fitted probabilities numerically 0 or 1 occurred?
Dear ted, thanks for your help. Now, everything is more clear. I read something about linear separation you mentioned, and my data set is very suitable for this problem. But, there is a confusing question for me; I can not controll the process adequately because of usage of bootstrap. So, this warnings will arise. After the analyse, If I interpret the result with these warnings, does this right? At least i may control the warnings glm.fit: algorithm did not converge with gm.control, but fitted probabilities numerically 0 or 1 occurred will certainly arise. Does the interpretation of results with this warning right? Many thanks. - Best regards Ufuk -- View this message in context: http://r.789695.n4.nabble.com/glm-fit-fitted-probabilities-numerically-0-or-1-occurred-tp4490722p4496710.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] glm.fit: fitted probabilities numerically 0 or 1 occurred?
Dear Ellison, Many thanks for your reply. The information you typed is clear and now I know what to do. Your suggestion about finding some coffee while running simulation is so good =) Regards - Best regards Ufuk -- View this message in context: http://r.789695.n4.nabble.com/glm-fit-fitted-probabilities-numerically-0-or-1-occurred-tp4490722p4492436.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] glm.fit: fitted probabilities numerically 0 or 1 occurred?
Hi all, I am doing bootstrap with logistic regression by using glm function, and I get the errors; glm.fit: fitted probabilities numerically 0 or 1 occurred and glm.fit: algorithm did not converge I have read some things about this issue in the mailing list. I can guess what was the problem. My data contains one or may be two outliers. Does the error occur due to these extreme values or something else such as MLE? Is there any way to to fix this problem? Regards, Ufuk - Best regards Ufuk -- View this message in context: http://r.789695.n4.nabble.com/glm-fit-fitted-probabilities-numerically-0-or-1-occurred-tp4490722p4490722.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Robust Statistics for Outlier Detection
Hi Dear All, Can someone give me a suggestion about which robust statistics are most appropriate for outlier detection in linear models, and is available with R ? Thanks for any idea. -- View this message in context: http://r.789695.n4.nabble.com/Robust-Statistics-for-Outlier-Detection-tp3438493p3438493.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Why unique(sample) decreases the performance ?
Hi, I' am interested in differences between sample's result when samples consist of full elements and consist of only distinct elements. When sample consist of full elements it take about 120 sec., but when consist of only distinct elements it take about 4.5 or 5 times more sec. I expected that opposite of this result, because unique(sample) has less elements than full sample. Code as follows; e - rnorm(n=50, mean=0, sd=sqrt(0.5625)) x0 - c(rep(1,50)) x1 - rnorm(n=50,mean=2,sd=1) x2 - rnorm(n=50,mean=2,sd=1) x3 - rnorm(n=50,mean=2,sd=1) x4 - rnorm(n=50,mean=2,sd=1) y - 1+ 2*x1+4*x2+3*x3+2*x4+e x2[1] = 10 #influential observarion y[1] = 10 #influential observarion X - matrix(c(x0,x1,x2,x3,x4),ncol=5) Y - matrix(y,ncol=1) Design.data - cbind(X, Y) for (j in 1:nrow(X)) { result - vector(list, ) for( i in 1: 3100) { data - Design.data[sample(50,50,replace=TRUE),] # and unique(Design.data.) dataX - data[,1:5] dataY - data[,6] B.cap.simulation - solve(crossprod(dataX)) %*% crossprod(dataX, dataY) P.simulation - dataX %*% solve(crossprod(dataX)) %*% t(dataX) Y.cap.simulation - P.simulation %*% dataY e.simulation - dataY - Y.cap.simulation dX.simulation - nrow(dataX) - ncol(dataX) var.cap.simulation - crossprod(e.simulation) / (dX.simulation) ei.simulation - as.vector(dataY - dataX %*% B.cap.simulation) pi.simulation - diag(P.simulation) var.cap.i.simulation - (((dX.simulation) * var.cap.simulation)/(dX.simulation - 1)) - (ei.simulation^2/((dX.simulation - 1) * (1 - pi.simulation))) ti.simulation - ei.simulation / sqrt(var.cap.simulation * (1 - pi.simulation)) ti.star.simulation - ei.simulation / sqrt(var.cap.i.simulation * (1 - pi.simulation)) pi.star.simulation - pi.simulation + ei.simulation^2 / crossprod(e.simulation) WKi.simulation - (ti.star.simulation)*sqrt(pi.simulation/(1-pi.simulation)) Wi.simulation - WKi.simulation * sqrt((nrow(dataX)-1)/(1-pi.simulation)) result[[i]] - list(outWi.simulation=(Wi.simulation),influ.obs = any (dataY ==Y[j,] )) } i.obs - sapply(result,function(x) {x$influ.obs}) ni.result - result[! i.obs] ni.Wi.simulation - sapply(ni.result,function(x) {x$outWi.simulation}) if (j==1) { ni.Wi.simulation1 - ni.Wi.simulation }else if (j==2) { ni.Wi.simulation49 - matrix(ni.Wi.simulation , nrow=1) }else{ ni.Wi.simulation49 -cbind(ni.Wi.simulation49,matrix(ni.Wi.simulation,nrow=1)) } } Can someone give me an idea ? Many thanks. -- View this message in context: http://r.789695.n4.nabble.com/Why-unique-sample-decreases-the-performance-tp3391199p3391199.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Why unique(sample) decreases the performance ?
Sorry, the last part of code does not work when uniqu() are used, the true version; e - rnorm(n=50, mean=0, sd=sqrt(0.5625)) x0 - c(rep(1,50)) x1 - rnorm(n=50,mean=2,sd=1) x2 - rnorm(n=50,mean=2,sd=1) x3 - rnorm(n=50,mean=2,sd=1) x4 - rnorm(n=50,mean=2,sd=1) y - 1+ 2*x1+4*x2+3*x3+2*x4+e x2[1] = 10 #influential observarion y[1] = 10 #influential observarion X - matrix(c(x0,x1,x2,x3,x4),ncol=5) Y - matrix(y,ncol=1) Design.data - cbind(X, Y) for (j in 1:nrow(X)) { result - vector(list, ) for( i in 1: 3100) { data - Design.data[sample(50,50,replace=TRUE),] # and unique(Design.data.) dataX - data[,1:5] dataY - data[,6] B.cap.simulation - solve(crossprod(dataX)) %*% crossprod(dataX, dataY) P.simulation - dataX %*% solve(crossprod(dataX)) %*% t(dataX) Y.cap.simulation - P.simulation %*% dataY e.simulation - dataY - Y.cap.simulation dX.simulation - nrow(dataX) - ncol(dataX) var.cap.simulation - crossprod(e.simulation) / (dX.simulation) ei.simulation - as.vector(dataY - dataX %*% B.cap.simulation) pi.simulation - diag(P.simulation) var.cap.i.simulation - (((dX.simulation) * var.cap.simulation)/(dX.simulation - 1)) - (ei.simulation^2/((dX.simulation - 1) * (1 - pi.simulation))) ti.simulation - ei.simulation / sqrt(var.cap.simulation * (1 - pi.simulation)) ti.star.simulation - ei.simulation / sqrt(var.cap.i.simulation * (1 - pi.simulation)) pi.star.simulation - pi.simulation + ei.simulation^2 / crossprod(e.simulation) WKi.simulation - (ti.star.simulation)*sqrt(pi.simulation/(1-pi.simulation)) Wi.simulation - WKi.simulation * sqrt((nrow(dataX)-1)/(1-pi.simulation)) result[[i]] - list(outWi.simulation=(Wi.simulation),influ.obs = any (dataY ==Y[j,] )) } i.obs - sapply(result,function(x) {x$influ.obs}) ni.result - result[! i.obs] ni.Wi.simulation - sapply(ni.result,function(x) {x$outWi.simulation}) if (j==1) { ni.Wi.simulation1 - ni.Wi.simulation }else if (j==2) { ni.Wi.simulation49 - ni.Wi.simulation }else{ ni.Wi.simulation49 -c(ni.Wi.simulation49, ni.Wi.simulation) } } -- View this message in context: http://r.789695.n4.nabble.com/Why-unique-sample-decreases-the-performance-tp3391199p3391522.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] A question about list
Many thanks to all -- View this message in context: http://r.789695.n4.nabble.com/A-question-about-list-tp3385711p3387410.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] A question about list
Hi dear all, It may be a simple question, i have a list output with different number of elements as following; [[1]] [1] 0.86801402 -0.82974691 0.3974 -0.98566707 -4.96576856 -1.32056754 [7] -5.54093319 -0.07600462 -1.34457280 -1.04080125 1.62843297 -0.20473912 [13] 0.30659907 2.66908117 2.53791837 0.53788013 -0.57463077 0.27708874 [19] -2.94233200 1.54565643 -6.83694100 7.21556266 -3.14823536 -1.34590796 [25] 0.78660855 5.53692735 1.22511890 7.65249980 -0.43008997 -0.10536125 [[2]] [1] -2.80332826 0.54414548 4.38232256 -1.38407653 -1.59241491 -1.35509664 [7] 1.04806755 -0.27685465 -1.36671548 -3.16649719 2.17194692 -3.49404253 [13] 4.69102017 2.78297615 0.34565006 1.05954751 1.78836097 -0.80393182 [19] 3.74315304 1.17427902 1.62354686 0.53186688 -6.56519965 -3.39045485 [25] 0.01043676 -0.18857654 -0.57070351 -0.06135564 6.92331269 -1.46544614 [31] -1.65309767 [[3]] [1] 4.1923546 0.6319591 -0.8568113 -3.3115788 -2.4166481 -1.1543074 [7] -0.9333245 0.2632038 -0.6909956 -3.1008763 -2.9557687 1.5382464 [13] 1.2713290 6.6527302 1.0433603 -0.9916190 -2.7724673 -1.6554250 [19] 1.8023591 -1.5101793 1.2604704 -0.2853326 -2.4312827 -0.4731487 [25] 3.5061061 1.7392190 1.5493419 -0.7203778 -0.6995221 2.7686406 [31] 6.1813364 -1.8665294 I want to compute the percentile of all of 94 elements, i tried quantile(data) but i got an error like Error in sort.list(x, partial = unique(c(lo, hi))) : 'x' must be atomic for 'sort.list' Have you called 'sort' on a list? Can some one help me abouth this ? Thanks for any idea... -- View this message in context: http://r.789695.n4.nabble.com/A-question-about-list-tp3385711p3385711.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] selection of a subset from a loop
Hi dear all, The code like this; e - rnorm(n=50, mean=0, sd=sqrt(0.5625)) x0 - c(rep(1,50)) x1 - rnorm(n=50,mean=2,sd=1) x2 - rnorm(n=50,mean=2,sd=1) x3 - rnorm(n=50,mean=2,sd=1) x4 - rnorm(n=50,mean=2,sd=1) y - 1+ 2*x1+4*x2+3*x3+2*x4+e x2[1] = 10 #influential observarion y[1] = 10 #influential observarion X - matrix(c(x0,x1,x2,x3,x4),ncol=5) Y - matrix(y,ncol=1) Design.data - cbind(X, Y) result - list () for( i in 1: 3100) { data - Design.data[sample(50,50,replace=TRUE),] dataX - data[,1:5] dataY - data[,6] B.cap.simulation - solve(crossprod(dataX)) %*% crossprod(dataX, dataY) P.simulation - dataX %*% solve(crossprod(dataX)) %*% t(dataX) Y.cap.simulation - P.simulation %*% dataY e.simulation - dataY - Y.cap.simulation dX.simulation - nrow(dataX) - ncol(dataX) var.cap.simulation - crossprod(e.simulation) / (dX.simulation) ei.simulation - as.vector(dataY - dataX %*% B.cap.simulation) pi.simulation - diag(P.simulation) var.cap.i.simulation - (((dX.simulation) * var.cap.simulation)/(dX.simulation - 1)) - (ei.simulation^2/((dX.simulation - 1) * (1 - pi.simulation))) ti.simulation - ei.simulation / sqrt(var.cap.simulation * (1 - pi.simulation)) ti.star.simulation - ei.simulation / sqrt(var.cap.i.simulation * (1 - pi.simulation)) pi.star.simulation - pi.simulation + ei.simulation^2 / crossprod(e.simulation) WKi.simulation - (ti.star.simulation)*sqrt(pi.simulation/(1-pi.simulation)) result- c(result,list(WKi.simulation)) } Finally i get the result which contains 3100 WKi.simulation. I'm trying to get a subset for those subset do not contain any Y[1,] that is point 10. Can anyone help me about how to be? Thanks for any idea... -- View this message in context: http://r.789695.n4.nabble.com/selection-of-a-subset-from-a-loop-tp3329057p3329057.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Problem about for loop
Hi everyones, my function like; e - rnorm(n=50, mean=0, sd=sqrt(0.5625)) x0 - c(rep(1,50)) x1 - rnorm(n=50,mean=2,sd=1) x2 - rnorm(n=50,mean=2,sd=1) x3 - rnorm(n=50,mean=2,sd=1) x4 - rnorm(n=50,mean=2,sd=1) y - 1+ 2*x1+4*x2+3*x3+2*x4+e x2[1] = 10 #influential observarion y[1] = 10 #influential observarion data.x - matrix(c(x0,x1,x2,x3,x4),ncol=5) data.y - matrix(y,ncol=1) data.k - cbind(data.x,data.y) dataX - data.k[,1:5] dataY - data.k[,6] theta - function(data) { B.cap - solve(crossprod(dataX)) %*% crossprod(dataX,dataY) P - dataX %*% solve(crossprod(dataX)) %*% t(dataX) Y.cap - P %*% dataY e - dataY - Y.cap dX - nrow(dataX) - ncol(dataX) var.cap - crossprod(e) / (dX) ei - as.vector(dataY - dataX %*% B.cap) pi - diag(P) var.cap.i - (((dX) * var.cap) / (dX - 1)) - (ei^2 / ((dX-1) * (1 - pi))) ti - ei / sqrt(var.cap * (1 - pi)) Ci - (ti^2 / (ncol(dataX))) * (pi / (1 - pi)) output.i - mean(Ci)} result - list() for ( i in 1:5){ data - replicate(1, data.k[sample(50,50,replace=T),], simplify = FALSE) output.j - theta(data) result - c(result,(list(output.j))) } table - do.call(rbind.data.frame,result) names(table)=c(cooks) table This function give same results each time, the data is changing every time but mean(Ci)s are always same. Does anyone have an idea about how to be? Thanks for any idea -- View this message in context: http://r.789695.n4.nabble.com/Problem-about-for-loop-tp3221210p3221210.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] selection statistics from function
Hi, My code: e - rnorm(n=50, mean=0, sd=sqrt(0.5625)) x0 - c(rep(1,50)) x1 - rnorm(n=50,mean=2,sd=1) x2 - rnorm(n=50,mean=2,sd=1) x3 - rnorm(n=50,mean=2,sd=1) x4 - rnorm(n=50,mean=2,sd=1) y - 1+ 2*x1+4*x2+3*x3+2*x4+e x2[1] = 10 #influential observarion y[1] = 10 #influential observarion data.x - matrix(c(x0,x1,x2,x3,x4),ncol=5) data.y - matrix(y,ncol=1) data.k - cbind(data.x,data.y) result - list() for( i in 1: 3100) { data - data.k[sample(50,50,replace=TRUE),] dataX - data[,1:5] dataY - data[,6] B.cap - solve(crossprod(dataX)) %*% crossprod(dataX,dataY) P - dataX %*% solve(crossprod(dataX)) %*% t(dataX) Y.cap - P %*% dataY e - dataY - Y.cap dX - nrow(dataX) - ncol(dataX) var.cap - crossprod(e) / (dX) ei - as.vector(dataY - dataX %*% B.cap) pi - diag(P) var.cap.i - (((dX) * var.cap) / (dX - 1)) - (ei^2 / ((dX-1) * (1 - pi))) ti - ei / sqrt(var.cap * (1 - pi)) Ci - (ti^2 / (ncol(dataX))) * (pi / (1 - pi)) result - c(result,list(mean(Ci)))} table-do.call(rbind.data.frame,result) names(table)=c(Cook's Distance) table I want to find data's statistics (mean(Ci)) which do not contain influential observation. That is do not contain the value of 10. Can someone help me? Thanks for advices ! -- View this message in context: http://r.789695.n4.nabble.com/selection-statistics-from-function-tp3221267p3221267.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Computing and Finding
Hi dear all, i am triying to do jackknife-after bootstrap for detection of influential observation. my data and resamples are following ; e - rnorm(n=50, mean=0, sd=sqrt(0.5625)) x0 - c(rep(1,50)) x1 - rnorm(n=50,mean=2,sd=1) x2 - rnorm(n=50,mean=2,sd=1) x3 - rnorm(n=50,mean=2,sd=1) x4 - rnorm(n=50,mean=2,sd=1) y - 1+ 2*x1+4*x2+3*x3+2*x4+e x2[1] = 10 #influential observarion y[1] = 10 #influential observarion data.x - matrix(c(x0,x1,x2,x3,x4),ncol=5) data.y - matrix(y,ncol=1) replicate(3100, data.x[sample(50,50,replace=T),], simplify = FALSE) replicate(3100, data.y[sample(50,50,replace=T),], simplify = FALSE) now i want to calculate each of 3100 resamples's Cook's Distance like this formula ; B.cap - solve(crossprod(data.x)) %*% crossprod(data.x, data.y) P - data.x %*% solve(crossprod(data.x)) %*% t(data.x) Y.cap - P %*% data.y e - data.y - Y.cap dX - nrow(data.x) - ncol(data.x) var.cap - crossprod(e) / (dX) ei - as.vector(data.y - data.x %*% B.cap) pi - diag(P) var.cap.i - (((dX) * var.cap)/(dX - 1)) - (ei^2/((dX - 1) * (1 - pi))) ti - ei / sqrt(var.cap * (1 - pi)) ti.star - ei / sqrt(var.cap.i * (1 - pi)) pi.star - pi + ei^2 / crossprod(e) Ci - (ti^2/ncol(data.x))*(pi/(1-pi)) (Cook's Distance) and i want to compute each of resamples, which do not include the influential observation, Cook's Distances. Can someone help me about this ? Thanks for any idea.. -- View this message in context: http://r.789695.n4.nabble.com/Computing-and-Finding-tp3220423p3220423.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] selection of outputs from the function
Thanks so much Joshua Wiley you are right your function better than mine :) -- View this message in context: http://r.789695.n4.nabble.com/selection-of-outputs-from-the-function-tp3163361p3163853.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] selection of outputs from the function
Hi Dear All, This is a function which contains Covariance Ratio and Likelihood Distance values (CVRi, LDi). i want to compute the all row's values, that is run this function for nrow(X) times. The X and Y matrices are; X-matrix(c(1125,920,835,1000,1150,990,840,650,640,583,570,570,510,555,460,275,510,165,244,79,232,268,271,237,192,202,184,200,180,165,151,171,243,147,286,198,196,210,327,334,7160,8804,8108,6370,6441,5154,5896,5336,5041,5012,4825,4391,4320,3709,3969,3558,4361,3301,2964,2777,85.9,86.5,85.2,83.8,82.1,79.2,81.2,80.6,78.4,79.3,78.7,78.0,72.3,74.9,74.4,72.5,57.7,71.8,72.5,71.9,8905,7388,5348,8056,6960,5690,6932,5400,3177,4461,3901,5002,4665,4642,4840,4479,4200,3410,3360,2599),nrow=20) Y-matrix(c(1.5563,0.8976,0.7482,0.7160,0.3130,0.3617,0.1139,0.1139,-0.2218,-0.1549,0.,0.,-0.0969,-0.2218,-0.3979,-0.1549,-0.2218,-0.3979,-0.5229,-0.0458),nrow=20) theta - function(X,Y) { B.cap - solve(t(X)%*%X)%*%t(X)%*%Y P - X%*%solve(t(X)%*%X)%*%t(X) Y.cap - P%*%Y e - Y-Y.cap var.cap-(t(e)%*%e)/(nrow(X)-ncol(X)-1) ei - Y[i,]-X[i,]%*%B.cap pi - P[i,i] var.cap.i - (((nrow(X)-ncol(X)-1)*var.cap)/(nrow(X)-ncol(X)-2))-(ei^2/((nrow(X)-ncol(X)-2)*(1-pi))) ti - ei/(sqrt(var.cap)*sqrt(1-pi)) ti.star - ei/(sqrt(var.cap.i)*sqrt(1-pi)) X.star - cbind(X,Y) pi.star - pi+(ei^2/(t(e)%*%e)) LDi - nrow(X)*log(((nrow(X))/(nrow(X)-1))*(((nrow(X)-ncol(X)-2))/ (ti.star^2+nrow(X)-ncol(X)-2)))+((ti.star^2*(nrow(X)-1))/((1-pi)*(nrow(X)-ncol(X)-2)))-1 CVRi - (((nrow(X)-ncol(X)-1-ti^2)/(nrow(X)-ncol(X)-2))^(nrow(X)))/(1-pi) list(ti=ti,ti.star=ti.star,pi=pi,pi.star=pi.star,LDi=LDi,CVRi=CVRi) } obj-list() for(i in 1:nrow(X)){ X-X Y-Y out-theta(X,Y) obj-c(obj,list(out))} obj Finally i get values... Is there any way to get the outputs as a list or data.frame like pi CVRi 1 11 2 22 3 33 4 44 5 55 6 66 7 77 8 88 9 99 10 10 10 11 11 11 12 12 12 13 13 13 14 14 14 15 15 15 16 16 16 17 17 17 18 18 18 19 19 19 20 20 20 for all values (pi,pi.star,ti,ti.star,CVRi,LDi)... Thanks so much for any idea ! -- View this message in context: http://r.789695.n4.nabble.com/selection-of-outputs-from-the-function-tp3163361p3163361.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] selection of outputs from the function
Thank so much David ! -- View this message in context: http://r.789695.n4.nabble.com/selection-of-outputs-from-the-function-tp3163361p3163421.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] regression
Hi dear all, suppose that s is a statistic code; i have a matrix (x) which has 7 columns (1=x1,2=x23=x3,4=x4,5=x5,6=x6 and7=y) and has 20 rows. i want to do linear reggression like reg-lm(x[,7]~1+x[,1]+x[,2]+...+x[,6]) but i want to do delete i th row for nrows times and create regression model like above and compute each models' s statistics and list them. but i could not do. i always get only one model and statistic. How can i do this Thanks any idea! -- View this message in context: http://r.789695.n4.nabble.com/regression-tp3161328p3161328.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] regression
Thank you so much i did with your idea.. thank you :) -- View this message in context: http://r.789695.n4.nabble.com/regression-tp3161328p3161524.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] regression
sorry not read i want to say write -- View this message in context: http://r.789695.n4.nabble.com/regression-tp3161328p3161551.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] regression
thank you so much, and i have a question too if i read some statistic for example cook-weisberg statistic or welsh-kuh distance and i say stat-welsh.kuh than i put this statistic in your idea, can i get the statistics each times? -- View this message in context: http://r.789695.n4.nabble.com/regression-tp3161328p3161549.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] delete-d jackknife
Thank you so much :) -- View this message in context: http://r.789695.n4.nabble.com/delete-d-jackknife-tp3058335p3059364.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] delete-d jackknife
Hi dear all, Can aynone help me about delete-d jackknife usually normal jackknife code for my data is: n - nrow(data) y - data$y z - data$z theta.hat - mean(y) / mean(z) print (theta.hat) theta.jack - numeric(n) for (i in 1:n) theta.jack[i] - mean(y[-i]) / mean(z[-i]) bias - (n - 1) * (mean(theta.jack) - theta.hat) print(bias) but how i can apply delete-d jackknife when d=2 or 3. Thanks forany idea.. -- View this message in context: http://r.789695.n4.nabble.com/delete-d-jackknife-tp3058335p3058335.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Counting
Hi dear all, i have a data (data.frame) which contain y and x coloumn(i.e. y x 1 0.58545723 0.15113102 2 0.02769361 -0.02172165 3 1.00927527 -1.80072610 4 0.56504053 -1.12236685 5 0.58332337 -1.24263981 6 -1.70257274 0.46238255 7 -0.88501561 0.89484429 8 1.14466282 0.34193875 9 0.58827457 0.15923694 10 -0.79532232 -1.44193770) i changed the first data points by an outlier (i.e. y x 1 1025 2 0.02769361 -0.02172165 3 1.00927527 -1.80072610 4 0.56504053 -1.12236685 5 0.58332337 -1.24263981 6 -1.70257274 0.46238255 7 -0.88501561 0.89484429 8 1.14466282 0.34193875 9 0.58827457 0.15923694 10 -0.79532232 -1.44193770 ) then i generate the 1000 bootstrap sample with this data set, some of them not contain these outliers, some of them contain once and some of them contain many time... Now i want to count how many samples not contain these outliers. Thank so much any idea! -- View this message in context: http://r.789695.n4.nabble.com/Counting-tp3045756p3045756.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Counting
thank you very much for your idea, if i write code as; my data name is data. samples-function(data,num){ resamples-lapply(1:num,function(i) sample(data,n,replace=TRUE)) list(resamples=resamples)} n=10 data-rnorm(n=10,mean=5,sd=2) data[1]=100 obj-samples(data,1000) i generate 1000 sample, i did not use 'boot'. 100 is a outlier in the data set and same stuation, some of samples not contain , some of samples contain once and some of them contain many times. Now can you tell me how i count how many samples are there not contain any outlier in the 1000 samples? -- View this message in context: http://r.789695.n4.nabble.com/Counting-tp3045756p3045842.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Counting
Thank you so much -- View this message in context: http://r.789695.n4.nabble.com/Counting-tp3045756p3045918.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Counting
Thank you so much -- View this message in context: http://r.789695.n4.nabble.com/Counting-tp3045756p3045917.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] jackknife-after-bootstrap
I am always trying but i could not do it. Are there any example about this -- View this message in context: http://r.789695.n4.nabble.com/Re-jackknife-after-bootstrap-tp3043213p3043398.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.