Re: [R] NAs introduced by coercion warning, while plotting data
Hi, are you reading only one cell of your Excel file? It seems your datalist is not numeric but text. Try saving your Excel file as csv or text, reading in data might be much more straightforward! best daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Baro [babak...@gmail.com] Küldve: 2014. január 7. 16:01 To: PIKAL Petr Cc: R help Tárgy: Re: [R] NAs introduced by coercion warning, while plotting data thank you for your answer, I am reading my Data from an excel File. This is my R code: srow-2421 wb - loadWorkbook(C:\\users\\Babak\\Desktop\\spalte205.xls) dat -readWorksheet(wb, sheet=getSheets(wb)[1], startRow=srow, endRow=srow, startCol=spalte, endCol=spalte,header=FALSE) datalist-dat[,1] datalist-sub(;,,datalist) datalist plot(datalist,type=l,ylim=c(-1,+1)) as an output of my data, I see: datalist [1] 7.0121, -0.673354, 0.749622, -0.549641, 0.435662, -0.328995, 0.0869976, -0.0851428, -0.191019, 0.188799, -0.373707, 0.434814, -0.51979, 0.61944, -0.554766, 0.662571, -0.557779, 0.543724, -0.452397, 0.293651, -0.248438, 0.0532787, -0.0185775, -0.176117, 0.222021, -0.34723, 0.407796, -0.416123, 0.497159, -0.435225, 0.473375, -0.370811, 0.33683, -0.273933, 0.149871, -0.142623, -0.0253748, 0.0205145, -0.134123, 0.167995, -0.209844, 0.266891, -0.242527, 0.326598, -0.235483, 0.275738, -0.195738, 0.168225, -0.114333, 0.0593316, -0.0583527, -0.016594, 0.0363428, -0.0533603, 0.106158, -0.129363, 0.131993, -0.134909, 0.135686, -0.125387, 0.0866545, -0.0668686, 0.043161, -0.0229738 On Tue, Jan 7, 2014 at 6:54 AM, PIKAL Petr petr.pi...@precheza.cz wrote: Hi I did not get any error with your data plot(test) dput(test) c(7.0121, -0.673354, 0.749622, -0.549641, 0.435662, -0.328995, 0.0869976, -0.0851428, -0.191019, 0.188799, -0.373707, 0.434814, -0.51979, 0.61944, -0.554766, 0.662571, -0.557779, 0.543724, -0.452397, 0.293651, -0.248438, 0.0532787, -0.0185775, -0.176117, 0.222021, -0.34723, 0.407796, -0.416123, 0.497159, -0.435225, 0.473375, -0.370811, 0.33683, -0.273933, 0.149871, -0.142623, -0.0253748, 0.0205145, -0.134123, 0.167995, -0.209844, 0.266891, -0.242527, 0.326598, -0.235483, 0.275738, -0.195738, 0.168225, -0.114333, 0.0593316, -0.0583527, -0.016594, 0.0363428, -0.0533603, 0.106158, -0.129363, 0.131993, -0.134909, 0.135686, -0.125387, 0.0866545, -0.0668686, 0.043161, -0.0229738) You shall explain more clearly what you did (code) and what are your data (dput) I presume that the story is not as simple as plotting a vector as you have suggested. Petr -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-bounces@r- project.org] On Behalf Of Baro Sent: Tuesday, January 07, 2014 3:40 PM To: R help Subject: [R] NAs introduced by coercion warning, while plotting data Hi all I have such a Data and I want to plot them but I get this warning Warning message: In xy.coords(x, y, xlabel, ylabel, log) : NAs introduced by coercion 7.0121, -0.673354, 0.749622, -0.549641, 0.435662, -0.328995, 0.0869976, -0.0851428, -0.191019, 0.188799, -0.373707, 0.434814, - 0.51979, 0.61944, -0.554766, 0.662571, -0.557779, 0.543724, -0.452397, 0.293651, -0.248438, 0.0532787, -0.0185775, -0.176117, 0.222021, - 0.34723, 0.407796, -0.416123, 0.497159, -0.435225, 0.473375, -0.370811, 0.33683, -0.273933, 0.149871, -0.142623, -0.0253748, 0.0205145, - 0.134123, 0.167995, -0.209844, 0.266891, -0.242527, 0.326598, - 0.235483, 0.275738, -0.195738, 0.168225, -0.114333, 0.0593316, - 0.0583527, -0.016594, 0.0363428, -0.0533603, 0.106158, -0.129363, 0.131993, -0.134909, 0.135686, -0.125387, 0.0866545, -0.0668686, 0.043161, -0.0229738 Why do I get this warning? how can I solve it? [[alternative HTML version deleted]] __ 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. [[alternative HTML version deleted]] __ 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-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 there is no quarters?
Hi, try x - seq(as.Date(2001/1/1),as.Date(2010/1/1),3 months) best, daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Pancho Mulongeni [p.mulong...@namibia.pharmaccess.org] Küldve: 2013. december 16. 13:05 To: 1248283...@qq.com Cc: r-help@r-project.org Tárgy: Re: [R] why there is no quarters? Hi, I also would like to use quarters. I think a work around would be to just label each record in the dataframe by its quarter. i.e. you add a factor called 'Quarter' with four levels (Q1 to Q4) for each row and you assign the level based on the month of the date. You can easily do this with as.Date and as.character. Pancho Mulongeni Research Assistant PharmAccess Foundation 1 Fouché Street Windhoek West Windhoek Namibia Tel: +264 61 419 000 Fax: +264 61 419 001/2 Mob: +264 81 4456 286 __ 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-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] [Probable spam] RE: how can i add Qtr1 Qtr2 Qtr3 Qtr4 on the x axis?
Hi, try ?axis.Date works similar to the axis function. I hope that helps! daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: 水静流深 [1248283...@qq.com] Küldve: 2013. december 15. 9:17 To: r-help Tárgy: [R] how can i add Qtr1 Qtr2 Qtr3 Qtr4 on the x axis? x-ts(sales,frequency=4,start=c(2010,1)) x Qtr1 Qtr2 Qtr3 Qtr4 2010 1.8 8.0 6.0 3.0 2011 2.0 11.0 7.0 3.5 2012 2.5 14.0 8.0 4.2 2013 3.0 15.2 9.5 5.0 plot.ts(x) __ 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] [Probable spam]RE: how to add a line in the graph?
t- -4:4 y-c(5,7,10,13,15,16,14,12,11) plot(t,y,type=l, ylim=c(-20,20)) curve(0.83*x-0.44*x^2, add=TRUE) I added ylim to plot so that your curve is on the graph. Maybe you wanted to use different parameters. Try going through a basic manual of R! daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: 水静流深 [1248283...@qq.com] Küldve: 2013. december 15. 13:46 To: r-help Tárgy: [R] how to add a line in the graph? t--4:4 y-c(5,7,10,13,15,16,14,12,11) plot(t,y,type=l) how can i add a curve y=0.83*t-0.44*t^2 in the graph? [[alternative HTML version deleted]] __ 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-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] RSM
There is no variable called x1 in the chem dataframe. Did you mean gg1=rsm(yield~ FO(x1,x2),data=ggg,subset = (Block == B1)) hth. daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: IZHAK shabsogh [ishaqb...@yahoo.com] Küldve: 2013. december 15. 15:53 To: r-help@r-project.org Tárgy: [R] RSM kindly help find out why the following code is given me error time-c(80,80,90,90,85,85,85,85,85,85,92,77,85,85) tem-c(170,180,170,180,175,175,175,175,175,175,175,175,182.07,167.93) yield-c(80.5,81.5,82,83.5,83.9,84.3,84,79.7,79.8,79.5,78.4,75.6,78.6,77) Block-c(B1,B1,B1,B1,B1,B1,B1,B2,B2,B2,B2,B2,B2,B2) chem-data.frame(time,tem,Block,yield) ggg-coded.data(chem, x1 ~ (time - 85)/5, x2 ~ (tem - 175)/5) gg1=rsm(yield~ FO(x1,x2),data=chem,subset = (Block == B1)) Error in lapply(X = X, FUN = FUN, ...) : object 'x1' not found gg1=rsm(yield~ SO(x1,x2),data=chem,subset = (Block == B1)) Error in lapply(X = X, FUN = FUN, ...) : object 'x1' not found [[alternative HTML version deleted]] __ 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-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] Change factor levels
Dear Gang, this seem to solve your problem. http://stackoverflow.com/questions/1195826/dropping-factor-levels-in-a-subsetted-data-frame-in-r best daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Gang Chen [gangch...@gmail.com] Küldve: 2013. december 14. 21:09 To: r-help Tárgy: [R] Change factor levels Suppose I have a dataframe 'd' defined as L3 - LETTERS[1:3] d0 - data.frame(cbind(x = 1, y = 1:10), fac = sample(L3, 10, replace = TRUE)) (d - d0[d0$fac %in% c('A', 'B'),]) x y fac 2 1 2 B 3 1 3 A 4 1 4 A 5 1 5 A 6 1 6 B 8 1 8 A Even though factor 'fac' in 'd' only has 2 levels, but it seems to bear the birthmark of 3 levels from its parent 'd0': str(d) 'data.frame': 6 obs. of 3 variables: $ x : num 1 1 1 1 1 1 $ y : num 2 3 4 5 6 8 $ fac: Factor w/ 3 levels A,B,C: 2 1 1 1 2 1 How can I cut the umbilical cord so that factor 'fac' in 'd' would have an accurate birth certificate with the correct number of levels? Apparently the following does not work: levels(d$fac) - c('A', 'B') Also any reason for this heritage? Thanks, Gang [[alternative HTML version deleted]] __ 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-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] Solving a normal distribution pnorm for q
Looks like homework. Try ?qnorm Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Johannes Radinger [johannesradin...@gmail.com] Küldve: 2013. december 12. 14:56 To: R help Tárgy: [R] Solving a normal distribution pnorm for q Hi, I found follwowing example of pnorm here: http://www.r-tutor.com/elementary-statistics/probability-distributions/normal-distribution Problem Assume that the test scores of a college entrance exam fits a normal distribution. Furthermore, the mean test score is 72, and the standard deviation is 15.2. What is the percentage of students scoring 84 or more in the exam? Solution pnorm(84, mean=72, sd=15.2, lower.tail=FALSE) [1] 0.21492 That is straight forward, however what if I want to know the score the best 30% students are reaching at least. So I know the solution of pnorm but want to know its q. How can that be achieved in R? Any suggestions? /Johannes [[alternative HTML version deleted]] __ 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-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] boxcox transformations
Dear Yogi, try the powerTransform function in the car package and boxcox function in the MASS package. there are nice examples for both functions. HTH, daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Yogendra [ykhedi...@gmail.com] Küldve: 2013. december 12. 19:00 To: r-help@r-project.org Tárgy: [R] boxcox transformations Hi, I am new to R. I need help with regards to box cox transformation. I have phenotypic data for e.g. plant height. data is non-normal. Skewness is 0.34. Could you please help me? Regards, Yogi -- View this message in context: http://r.789695.n4.nabble.com/boxcox-transformations-tp4682077.html Sent from the R help mailing list archive at Nabble.com. [[alternative HTML version deleted]] __ 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-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] growth curve estimation
Dear Vito, Robert and David, thank you for your replies, although I made some step forward on my own, your answers helped a lot and gave me more insight. The only question I have left is why this code gives me an error (and that is what David asked for): m1 - lms(BMI,age,data=adatok_fiu, cent=c(3,10,25,50,75,90,97), families=BCCG) centiles.pred(m1, xname=age, xvalues=seq(10,20,.5), cent=c(3,10,25,50,75,90,97)) Error in X[onlydata, , drop = FALSE] : (subscript) logical subscript too long but m3 - gamlss(BMI~pb(age), sigma.formula=~pb(age), nu.formula = ~pb(age), tau.formula = ~pb(age), family=BCT, data=adatok_fiu) centiles.pred(m3, xname=age, xvalues=seq(10,20,.5), cent=c(3,10,25,50,75,90,97)) works as expected (although I get a warning message Warning message: In predict.gamlss(obj, what = tau, newdata = newx, type = response, : There is a discrepancy between the original and the re-fit used to achieve 'safe' predictions I had the feeling centiles.pred should work for the result of an lms() function just like in case of gamlss(). Thank you all again! daniel Feladó: David Winsemius [dwinsem...@comcast.net] Küldve: 2013. december 9. 21:40 To: Dániel Kehl Cc: r-help@r-project.org Tárgy: Re: [R] growth curve estimation On Dec 8, 2013, at 7:45 AM, Dániel Kehl wrote: Dear Community, I am struggling with a growth curve estimation problem. It is a classic BMI change with age calculation. I am not an expert of this field but have some statistical experience in other fields. Of course I started reading classical papers related to the topic and understood the concept of the LMS method. After that I thought it will be a piece of cake, R must have a package related to the topic, so I just need the data and I am just a few lines of code from the results. You might want to look at a more recent discussion: http://www.who.int/entity/childgrowth/standards/velocity/tr3chap_2.pdf (The WHO centre has published their R code.) I encountered some problems: - found at least three packages related to LMS: gamlss, VGAM and an old one lmsqreg (I did not try this because it does not support my R version (3.0.1.)) - it was relatively easy to get plots of percentiles in both packages, although they were far not the same (I also tried an other software, LMSchartmaker it gave different results from the previous ones) - I tried to get tables of predicted values (with the predict function in VGAM and with centiles.pre in gamlss) but without any success. Don't see any code or error messages. - I tried to use the function gamlss() instead of lms() in gamlss but I could not force them to give the same (or very similar results), but the centiles.pred() function did work as expected for the model resulted from galmss() - lms gives really different results if k is specified different ways, which is best? Won't that depend on the amount and distribution of the data? Also I have a general question: some publications state they estimated the centiles so that aroun 18 years of age the curves pass through certain points. How is that possible? Thank you for any suggestions or insights about the methods or preferred package! Here is my code (without data): #gamlss library(gamlss) library(VGAM) library(foreign) adatok - read.spss(MDSZ adatok.sav, to.data.frame=TRUE) adatok_fiu - subset(adatok, adatok$gender == Fiúk)[,2:3] row.names(adatok_fiu) - NULL adatok_lany - subset(adatok, adatok$gender == L÷nyok)[,2:3] row.names(adatok_lany) - NULL m1 - lms(BMI,age,data=adatok_fiu, cent=c(3,10,25,50,75,90,97), families=BCCG) fittedPlot(m1, x=adatok_fiu$age) m1 - lms(BMI,age,data=adatok_fiu, cent=c(3,10,25,50,75,90,97), families=BCCG, method.pb=GAIC, k=log(1455)) fittedPlot(m1, x=adatok_fiu$age) m1 - lms(BMI,age,data=adatok_fiu, cent=c(3,10,25,50,75,90,97), families=BCCG, method.pb=GAIC) fittedPlot(m1, x=adatok_fiu$age) m2 - lms(BMI,age,data=adatok_lany, cent=c(3,10,25,50,75,90,97), families=BCCG) m2 - lms(BMI,age,data=adatok_lany, cent=c(3,10,25,50,75,90,97), families=BCCG, method.pb=GAIC, k=log(1144)) m2 - lms(BMI,age,data=adatok_lany, cent=c(3,10,25,50,75,90,97), families=BCCG, method.pb=GAIC) m3 - gamlss(BMI~age, family=BCT, data=adatok_fiu) centiles(m3,xvar=adatok_fiu$age, cent=c(3,10,25,50,75,90,97)) newx - seq(12,20,.5) centiles.pred(m1, xname=age, xvalues=newx) centiles.pred(m3, xname=age, xvalues=newx) centiles(m1,adatok_fiu$age) #VGAM library(foreign) library(VGAM) library(VGAMdata) adatok - read.spss(MDSZ adatok.sav, to.data.frame=TRUE) adatok_fiu - subset(adatok, adatok$gender == Fiúk) adatok_lany - subset(adatok, adatok$gender == L÷nyok) fit1 - vgam(BMI ~ s(age), lms.bcn(percentiles = c(3, 10, 25, 50, 75, 90, 97)), adatok_fiu) fit2 - vgam(BMI ~ s(age), lms.bcn(percentiles = c(3, 10, 25, 50, 75, 90, 97)), adatok_lany) qtplot(fit1, percentiles = c(3, 10, 25
[R] growth curve estimation
Dear Community, I am struggling with a growth curve estimation problem. It is a classic BMI change with age calculation. I am not an expert of this field but have some statistical experience in other fields. Of course I started reading classical papers related to the topic and understood the concept of the LMS method. After that I thought it will be a piece of cake, R must have a package related to the topic, so I just need the data and I am just a few lines of code from the results. I encountered some problems: - found at least three packages related to LMS: gamlss, VGAM and an old one lmsqreg (I did not try this because it does not support my R version (3.0.1.)) - it was relatively easy to get plots of percentiles in both packages, although they were far not the same (I also tried an other software, LMSchartmaker it gave different results from the previous ones) - I tried to get tables of predicted values (with the predict function in VGAM and with centiles.pre in gamlss) but without any success. - I tried to use the function gamlss() instead of lms() in gamlss but I could not force them to give the same (or very similar results), but the centiles.pred() function did work as expected for the model resulted from galmss() - lms gives really different results if k is specified different ways, which is best? Also I have a general question: some publications state they estimated the centiles so that aroun 18 years of age the curves pass through certain points. How is that possible? Thank you for any suggestions or insights about the methods or preferred package! Here is my code (without data): #gamlss library(gamlss) library(VGAM) library(foreign) adatok - read.spss(MDSZ adatok.sav, to.data.frame=TRUE) adatok_fiu - subset(adatok, adatok$gender == Fiúk)[,2:3] row.names(adatok_fiu) - NULL adatok_lany - subset(adatok, adatok$gender == L÷nyok)[,2:3] row.names(adatok_lany) - NULL m1 - lms(BMI,age,data=adatok_fiu, cent=c(3,10,25,50,75,90,97), families=BCCG) fittedPlot(m1, x=adatok_fiu$age) m1 - lms(BMI,age,data=adatok_fiu, cent=c(3,10,25,50,75,90,97), families=BCCG, method.pb=GAIC, k=log(1455)) fittedPlot(m1, x=adatok_fiu$age) m1 - lms(BMI,age,data=adatok_fiu, cent=c(3,10,25,50,75,90,97), families=BCCG, method.pb=GAIC) fittedPlot(m1, x=adatok_fiu$age) m2 - lms(BMI,age,data=adatok_lany, cent=c(3,10,25,50,75,90,97), families=BCCG) m2 - lms(BMI,age,data=adatok_lany, cent=c(3,10,25,50,75,90,97), families=BCCG, method.pb=GAIC, k=log(1144)) m2 - lms(BMI,age,data=adatok_lany, cent=c(3,10,25,50,75,90,97), families=BCCG, method.pb=GAIC) m3 - gamlss(BMI~age, family=BCT, data=adatok_fiu) centiles(m3,xvar=adatok_fiu$age, cent=c(3,10,25,50,75,90,97)) newx - seq(12,20,.5) centiles.pred(m1, xname=age, xvalues=newx) centiles.pred(m3, xname=age, xvalues=newx) centiles(m1,adatok_fiu$age) #VGAM library(foreign) library(VGAM) library(VGAMdata) adatok - read.spss(MDSZ adatok.sav, to.data.frame=TRUE) adatok_fiu - subset(adatok, adatok$gender == Fiúk) adatok_lany - subset(adatok, adatok$gender == L÷nyok) fit1 - vgam(BMI ~ s(age), lms.bcn(percentiles = c(3, 10, 25, 50, 75, 90, 97)), adatok_fiu) fit2 - vgam(BMI ~ s(age), lms.bcn(percentiles = c(3, 10, 25, 50, 75, 90, 97)), adatok_lany) qtplot(fit1, percentiles = c(3, 10, 25, 50, 75, 90, 97), xlim = c(10.5, 20.5), ylim=c(13,34), las = 1, ylab = BMI, lcol = 4, pch=NA) qtplot(fit2, percentiles = c(3, 10, 25, 50, 75, 90, 97), xlim = c(10.5, 20.5), ylim=c(13,34), las = 1, ylab = BMI, lcol = 3, add=TRUE, pch=NA, label=FALSE) Thank you: Daniel [[alternative HTML version deleted]] __ 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] polr?
Dear R users, I have a dataset with two ordered variables, tr_x1 and tr_y1. A crosstable of them can bee seen below. tr_x1 tr_y1 -101 -1 629 100 629 0 1396 4353 1443 1 668 126 655 It is clear that if tr_x1 is 0, it has an effect on tr_y1. A chi-square statistic is clearly showing this with a low p-value. Is there a regression-based method you would offer? I tried polr from MASS package but without finding a significant coefficient, because the columns for tr_x1 and tr_y1 are similar. Thank you for your help! daniel [[alternative HTML version deleted]] __ 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] polr?
Dear Prof Ripley, could you be just a little more specific? Thanks a lot daniel Feladó: Prof Brian Ripley [rip...@stats.ox.ac.uk] Küldve: 2013. július 4. 14:14 To: Dániel Kehl Cc: r-help Tárgy: Re: [R] polr? On 04/07/2013 12:59, Dániel Kehl wrote: Dear R users, I have a dataset with two ordered variables, tr_x1 and tr_y1. A crosstable of them can bee seen below. tr_x1 tr_y1 -101 -1 629 100 629 0 1396 4353 1443 1 668 126 655 It is clear that if tr_x1 is 0, it has an effect on tr_y1. A chi-square statistic is clearly showing this with a low p-value. Is there a regression-based method you would offer? I tried polr from MASS package but without finding a significant coefficient, because the columns for tr_x1 and tr_y1 are similar. Your mistake is testing coefficients, not overall fit. Thank you for your help! daniel [[alternative HTML version deleted]] __ 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. -- Brian D. Ripley, rip...@stats.ox.ac.uk Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ 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] R Commander and FactoMineR
Dear Users, I helped to install R Commander and FactoMineR to one of my collegaues. He wanted to do an MCA. Selecting three variables and using the default settings results in only one graph, the variables representation, where he gets three points for the three variables (which is totally fine). Running the code (output of the point-and-click method) EuTop100.MCA-EuTop100[, c(ország, szektor, székhely)] res-MCA(EuTop100.MCA, ncp=5, graph = FALSE) plot.MCA(res, axes=c(1, 2), col.ind=black, col.ind.sup=blue, col.var=darkred, col.quali.sup=darkgreen, label=c(ind, ind.sup, quali.sup, var, quanti.sup), invisible=c(, new.plot=TRUE)) plot.MCA(res, axes=c(1, 2), choix=var, col.var=darkred, col.quali.sup=darkgreen, label=c(var, quali.sup), invisible=c(, new.plot=TRUE)) plot.MCA(res, axes=c(1, 2), choix=quanti.sup, col.quanti.sup=blue, label=c(quanti.sup, new.plot=TRUE)) remove(EuTop100.MCA) however should result in three graphs. What went wrong? MCA(EuTop100.MCA) just works fine. Thank you and best wishes: Daniel [[alternative HTML version deleted]] __ 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] R Commander and FactoMineR
Hello, well yes, I see that it should be ... ,invisible=c(none), new.plot=TRUE) or something similar. I can correct this by hand The point was more like a bug-report. Maybe not the best place to mention a bug, but I couldn't find a better one. I do not know how to change the output of the point-and-click method. Best regards: daniel Feladó: Pascal Oettli [kri...@ymail.com] Küldve: 2013. április 2. 11:18 To: Dániel Kehl Cc: r-help@r-project.org Tárgy: Re: [R] R Commander and FactoMineR Hello, Did you check the position of the brackets, for example for invisible argument? Regards, Pascal On 04/02/2013 06:09 PM, Dániel Kehl wrote: Dear Users, I helped to install R Commander and FactoMineR to one of my collegaues. He wanted to do an MCA. Selecting three variables and using the default settings results in only one graph, the variables representation, where he gets three points for the three variables (which is totally fine). Running the code (output of the point-and-click method) EuTop100.MCA-EuTop100[, c(ország, szektor, székhely)] res-MCA(EuTop100.MCA, ncp=5, graph = FALSE) plot.MCA(res, axes=c(1, 2), col.ind=black, col.ind.sup=blue, col.var=darkred, col.quali.sup=darkgreen, label=c(ind, ind.sup, quali.sup, var, quanti.sup), invisible=c(, new.plot=TRUE)) plot.MCA(res, axes=c(1, 2), choix=var, col.var=darkred, col.quali.sup=darkgreen, label=c(var, quali.sup), invisible=c(, new.plot=TRUE)) plot.MCA(res, axes=c(1, 2), choix=quanti.sup, col.quanti.sup=blue, label=c(quanti.sup, new.plot=TRUE)) remove(EuTop100.MCA) however should result in three graphs. What went wrong? MCA(EuTop100.MCA) just works fine. Thank you and best wishes: Daniel [[alternative HTML version deleted]] __ 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-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] FactoMineR
Dear Users, I installed R Commander and the FactoMineR plug-in. Everything is fine, I can see the new menu, I can import datasets, but if I want to use any of the items in the FactoMineR menu, i get the following error: Error in get(.activeDataSet) : object '.activeDataSet' not found even if there is an active dataset (if there is none, all the menu items are grey of course). I have R version 2.15.2 using Windows 7 but experienced the same on other machines. Please let me know if you have any idea! Thanks a lot daniel __ 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] FactoMineR
Dear John, great news, thank you for your kind answer and quick response. I am sure that the author is going to do his best as well. An other good experience why I love R! :) Have a nice day, daniel Feladó: John Fox [j...@mcmaster.ca] Küldve: 2013. január 22. 13:39 To: Dániel Kehl Cc: R-help Tárgy: Re: [R] FactoMineR Dear Daniel, There were changes to the new version 1.9-3 of the Rcmdr so that it conforms to CRAN policies. These changes can break plug-ins that haven't been modified for compatibility. One change is that the environment in which the Rcmdr stores state information is no longer put on the search path. That's apparently preventing the FactoMineR plug-in from finding the active data set. The solution is for the author to replace get(.activeDataSet) with something like get(getRcmdr(.activeDataSet)). I'll correspond with the package author to suggest this. I apologize for the difficulties introduced by these changes. John John Fox Sen. William McMaster Prof. of Social Statistics Department of Sociology McMaster University Hamilton, Ontario, Canada http://socserv.mcmaster.ca/jfox/ On Tue, 22 Jan 2013 10:34:28 + Dániel Kehl ke...@ktk.pte.hu wrote: Dear Users, I installed R Commander and the FactoMineR plug-in. Everything is fine, I can see the new menu, I can import datasets, but if I want to use any of the items in the FactoMineR menu, i get the following error: Error in get(.activeDataSet) : object '.activeDataSet' not found even if there is an active dataset (if there is none, all the menu items are grey of course). I have R version 2.15.2 using Windows 7 but experienced the same on other machines. Please let me know if you have any idea! Thanks a lot daniel __ 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-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] slider control questions
DeaR UseRs, I have the following code (see below). It is working as expected although I have two problems/questions: - how can I set the size of the graph? It may sound silly, but I couldnt figure that out - is it possible to export this small interactive aplication to html or a latex document, or maybe pdf? Thank you for your attentions. Best wishes: Daniel the code: library(tkrplot) library(relax) dirfelulet - function (a1 = 1, a2 = 1, a3 = 1){ x1 - x2 - seq(0, 1, by=.01) dirf - function(x1, x2){ term1 - gamma(a1+a2+a3)/(gamma(a1)*gamma(a2)*gamma(a3)) term2 - x1^(a1-1)*x2^(a2-1)*(1-x1-x2)^(a3-1) term3 - (x1 + x2 1) term1 * term2 * term3 } f - outer(x1, x2, dirf) f[f=0] - NA f[is.infinite(f)] - NA persp(x1, x2, f, zlim = c(0, max(f, na.rm = TRUE)+1), main = bquote(paste(Dirichlet eloszlás, , alpha ,=(,.(a1),,,.(a2),,,.(a3),))), col = lightblue, theta = 50, phi = 20, r = 50, d = 0.1, expand = 0.5, ltheta = 90, lphi = 180, shade = 0.75, ticktype = detailed, nticks = 5) } plot.dirichlet-function(){ refresh.code-function(...){ a1-slider(no=1); a2-slider(no=2); a3-slider(no=3) type= slider(obj.name=type) dirfelulet(a1,a2,a3) } slider(obj.name=type,obj.value=l) gslider(refresh.code,sl.names=c(a1,a2,a3), sl.mins=c(1,1,1),sl.maxs=c(10,10,10),sl.deltas=c(.1,.1,.1),sl.defaults=c(1,1,1)) } plot.dirichlet() [[alternative HTML version deleted]] __ 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.