Re: [R] as.numeric looses precision
Hi Roger, I think it does! Try multiplying with 100 or similar. It is just a matter of displaying your result. best d Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Bos, Roger [roger@rothschild.com] Küldve: 2015. július 2. 15:54 To: r-help@r-project.org Tárgy: [R] as.numeric looses precision I have a string that contains a number and when I convert it to a number I loose precision and I would like to know if there is a way to avoid that. Here is my example: p - 1087.003489 as.numeric(p, digits=6) R gives me 1087.003: p - 1087.003489 as.numeric(p, digits=6) [1] 1087.003 I would be nice if I could keep all the decimal places after the conversion. Thanks, Roger *** This message and any attachments are for the intended recipient's use only. This message may contain confidential, proprietary or legally privileged information. No right to confidential or privileged treatment of this message is waived or lost by an error in transmission. If you have received this message in error, please immediately notify the sender by e-mail, delete the message, any attachments and all copies from your system and destroy any hard copies. You must not, directly or indirectly, use, disclose, distribute, print or copy any part of this message or any attachments if you are not the intended recipient. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Problem with apply list to function: numerical expression has 4 elements: only the first used
Dear Narua, Others might suggest other things but here are some of my points. In general it is not a good idea to call a function F as it is an abbreviation for FALSE. Also it might be a good idea to write your functions in a way that they check the length of the arguments and behave accordingly (if nothing else, with loops). It is really nice to take a look at the family of apply functions (although I also have problems with them sometimes). I did not check, but you can try something like this ff - function(m,k)((1/(sum(sqrt(1:m*sqrt(k)) FF - function(m,i)(sum(ff(m,1:i))) x - 1:4 sapply(x, ff, m=4) sapply(x, FF, m=4) Keep up with using R! :) Best, kd Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Narua [maria@gmx.de] Küldve: 2015. május 24. 0:21 To: r-help@r-project.org Tárgy: [R] Problem with apply list to function: numerical expression has 4 elements: only the first used Hello , I want to try R for statistics. Therefore, I defined a function f with parameters m and k, which calculates a to sqrt(x) proportional density function: f - function(m,k)((1/(sum(sqrt(1:m*sqrt(k)) A function F sums the results in order to get a distribution function: F - function(m,i)(sum(f(m,1:i))) It works e.g. for m=4: F(4,1) [1] 0.1627005 F(4,4) [1] 1 If I want to see all results for m=4, I write F(4,1:4) [1] 0.1627005 Warning message: In 1:i : numerical expression has 4 elements: only the first used what does the error message mean? and how can I solve it? I've already tried rapply but I get the same error and googled for a while but there is nowhere a satisfying answer Can someone help me here? many thanks in advance, Narua -- View this message in context: http://r.789695.n4.nabble.com/Problem-with-apply-list-to-function-numerical-expression-has-4-elements-only-the-first-used-tp4707588.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Reading access file
Hi Silvano, your attachment did not go through (only a couple of formats are supported). Please try to give your code next time and what error you get but first read this, it might help: http://www.statmethods.net/input/dbinterface.html best, daniel Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: silvano [silv...@uel.br] Küldve: 2015. május 14. 13:31 To: R Tárgy: [R] Reading access file Hello everybody. I have a access file to read in R but I can’t to do this. I used Hmisc package, but it doesn’t work. Someone has the commands to read this kind of file? I attached the access file. Thanks. Silvano. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Reading a tiff image
Hello, please set your mailing program to plain text instead of HTML if you post to this list. If you google read tiff in R you end up with the package called 'tiff'. (http://cran.r-project.org/web/packages/tiff/tiff.pdf) In case you do not know how to install and load a package, please consult the intro to R pdf which comes with your installation. Good luck with R, daniel Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Preethi Balaji [preet.balaj...@gmail.com] Küldve: 2015. május 14. 12:50 To: r-help@r-project.org Tárgy: [R] Reading a tiff image Dear R users, I am new to R and trying to learn raster image processing in R. I have a tiff image with pixel values and I am trying to read this image in R so that I can make some calculations and process the image. Could you please tell me how to read a tiff image in R? Thanks! -- Regards, *Preethi Malur Balaji* | PhD Student University College Cork | Cork, Ireland. [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Not able to submit work assignment4 with submitscript3.R
Hi there, this is not a Coursera Forum. Please ask your question there or search the Forums, these are quite regular problems there. PS: do you really have a user name and a password in your e-mail? Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Sonia Marin [s.marin...@gmail.com] Küldve: 2015. május 6. 23:27 To: r-help@r-project.org Tárgy: [R] Not able to submit work assignment4 with submitscript3.R Hi, I tried to submit the work assignment4 with submitscript3.R and i got an error message: Error in assign(.CourseraLogin, r, globalenv()) : unused arguments (r, globalenv()) I tryied to do it manually, but the files that I got to upload was empty. Please, let me know, how can i do to send the work assignment4. Thanks, for your attention. Best regard Sonia Marin rprog-013 TNWpNjGERh [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Need Help!
Hi, type res #ENTER (now it contains your results as a vector) or head(res) #so you only see the first couple of values or plot(res) #to see a basic plot (you could set axis labels etc, but I suggets you to go ahead and read a tutorial on R! Best, have a great time with R, kd Felad�: dawood ahmad [dawoodma...@hotmail.com] K�ldve: 2015. m�jus 5. 17:05 To: Kehl D�niel; r-help@R-project.org T�rgy: RE: [R] Need Help! Dear Daniel, Thank you very much for such a kind reply. Actually, I couldn't understand well the criteria of help list, I am sorry for that. I tried you method, unfortunately I couldn't get the output. It may be due to my lack of expertise in programming. At this point I need your help which will mean a lot to me. Moreover, if I use single value it gives the output. I am sending you two image files of the outputs. I will be really grateful to you if you guide me. Thanking in advance, With Best Regards, Dawood From: ke...@ktk.pte.hu To: dawoodma...@hotmail.com; r-help@r-project.org Subject: RE: [R] Need Help! Date: Mon, 4 May 2015 20:17:48 + Dear Dawood, it is not a really good idea to open a new email with the same problem you already posted earlier. I see you accepted some suggestions (HTML, seq) but not others (pi is a defined constant in R, do not change it, type pi ENTER to see this.). I would like to add one more, c is a function, do not use it as a variable name (I used cc instead of c). I tried to figure out what you want here. The following code might do what you want. It gives you a feeling about how you would create a basic loop. There are nicer ways to do that in R. Note the [i]-s in the for loop! cc - 0.5 xc - 2 s - 6 Hc2 - 30 H - 1 ep-seq(0.01, 0.49, by=0.001) res - numeric(length=length(ep)) for (i in 1:length(ep)){ f-function(k) 1.211*10^(-6)*Hc2/H*(trigamma( ((ep[i] + H/Hc2 + (2*xc/s)^2*(1 - cos(k*s))/2)/2*Hc2/H)) - trigamma(((cc + H/Hc2 + (2*xc/s)^2*(1 - cos(k*s))/2)/2*Hc2/H))) res[i] - integrate(f,-pi/s,pi/s)$value } Best, daniel Felad�: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: dawood ahmad [dawoodma...@hotmail.com] K�ldve: 2015. m�jus 4. 10:29 To: r-help@R-project.org T�rgy: [R] Need Help! Dear Sir/Madam, I hope you will be fine. I am new to R language. Recently, I am trying to fit my data with one model. I am sending you the code and image file on which you can see the error I am receiving instead of executing. If I give a single value to parameter ep, it executes well, but if I make a loop/seq for getting a range of data it shows error.I need you help in solving this problem. Thanking in advance, With Best Regards, Dawood [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Need Help!
Dear Dawood, it is not a really good idea to open a new email with the same problem you already posted earlier. I see you accepted some suggestions (HTML, seq) but not others (pi is a defined constant in R, do not change it, type pi ENTER to see this.). I would like to add one more, c is a function, do not use it as a variable name (I used cc instead of c). I tried to figure out what you want here. The following code might do what you want. It gives you a feeling about how you would create a basic loop. There are nicer ways to do that in R. Note the [i]-s in the for loop! cc - 0.5 xc - 2 s - 6 Hc2 - 30 H - 1 ep-seq(0.01, 0.49, by=0.001) res - numeric(length=length(ep)) for (i in 1:length(ep)){ f-function(k) 1.211*10^(-6)*Hc2/H*(trigamma( ((ep[i] + H/Hc2 + (2*xc/s)^2*(1 - cos(k*s))/2)/2*Hc2/H)) - trigamma(((cc + H/Hc2 + (2*xc/s)^2*(1 - cos(k*s))/2)/2*Hc2/H))) res[i] - integrate(f,-pi/s,pi/s)$value } Best, daniel Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: dawood ahmad [dawoodma...@hotmail.com] Küldve: 2015. május 4. 10:29 To: r-help@R-project.org Tárgy: [R] Need Help! Dear Sir/Madam, I hope you will be fine. I am new to R language. Recently, I am trying to fit my data with one model. I am sending you the code and image file on which you can see the error I am receiving instead of executing. If I give a single value to parameter ep, it executes well, but if I make a loop/seq for getting a range of data it shows error.I need you help in solving this problem. Thanking in advance, With Best Regards, Dawood __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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] Plotting Confidence Intervals
Hi Andre, I think you'll have to give some more information about what you want to see on your plot. The 4 intervals with labels? A bar with an interval maybe? Four bars with the intervals? Only two showing differences between conf and pred intervals? Also you do miss a 1 here I guess: p_conf1- predict(ines,interval=confidence,NJ,level=0.99) p_conf1 #Intervalo de confiança para o estado NJ e para um nivel de 99% round(p_conf, digits=3) last line should read p_conf1 here? Best, d Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Andre Roldao [andre.rafael.rol...@gmail.com] Küldve: 2015. május 2. 4:49 To: r-help@r-project.org Tárgy: [R] Plotting Confidence Intervals Hi Guys, It's the first time i use R-Help and i hope you can help me. How can i plot conffidence intervals? with the data bellow: #Package Austria library(car) #head(States) States1=data.frame(States) ines=lm(SATM ~ log2(pop) + SATV , data=States1) summary(ines) NJ=as.data.frame(States[NJ,c(4,2,3)]) #Identificação do estado NJ p_conf- predict(ines,interval=confidence,NJ,level=0.95) p_conf #Intervalo de confiança para o estado NJ e para um nivel de 95% round(p_conf, digits=3) p_conf1- predict(ines,interval=confidence,NJ,level=0.99) p_conf1 #Intervalo de confiança para o estado NJ e para um nivel de 99% round(p_conf, digits=3) p_pred2- predict(ines,interval=prediction,NJ,level=0.95) p_pred2 #Intervalo de perdição para o estado NJ e para um nivel de 95% round(p_pred2,digits=3) p_pred3- predict(ines,interval=prediction,NJ,level=0.99) p_pred3 #Intervalo de perdição para o estado NJ e para um nivel de 99% round(p_pred3,digits=3) Thanks [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] (no subject)
hi, did you try this? http://lmgtfy.com/?q=runs+test+in+r best, d Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Hosesin Nezami [hosseinnezami1...@yahoo.com] Küldve: 2015. május 2. 9:48 To: R-help@r-project.org Tárgy: [R] (no subject) Is there a package that contains Wald Wolfowitze runs test for two sample independentortwo sample Runs test? Thank's [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] cbind question, please
Hello, I am not sure what you mean by a matrix. If you want to have a matrix, use the function matrix, (matrix(c(dog,cat,tree),3)) but I have the feeling you really want a data frame as you are talking about variables. In that case simply use mydataframe - data.frame(dog,cat,tree) If you are not sure what you want, please read the intro to R pdf which is included in your installed R library. Best regards, daniel Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Erin Hodgess [erinm.hodg...@gmail.com] Küldve: 2015. április 24. 0:41 To: R help Tárgy: [R] cbind question, please Hello! I have a cbind type question, please: Suppose I have the following: dog - 1:3 cat - 2:4 tree - 5:7 and a character vector big.char - c(dog,cat,tree) I want to end up with a matrix that is a cbind of dog, cat, and tree. This is a toy example. There will be a bunch of variables. I experimented with do.call, but all I got was 1 2 3 Any suggestions would be much appreciated. I still think that do.call might be the key, but I'm not sure. R Version 3-1.3, Windows 7. Thanks, Erin -- Erin Hodgess Associate Professor Department of Mathematical and Statistics University of Houston - Downtown mailto: erinm.hodg...@gmail.com [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Simulate values
Hi Mike, please keep conversation on the list. Your code looks wy better now. I would not name the variable variances2 but that is just a matter of taste. What you could also do as a one-liner is something like n - 40 REPS - 5 mu - 10 sigma - 5 chisq - replicate(REPS,(n-1)*var(rnorm(n,mu,sigma))/sigma^2) Try to draw a histogram of the variances2 or chisq values and superimpose the theoratical distribution. ?hist and ?curve might help. Best, kd Felad�: Mike Brechb�hler [osiri...@gmx.ch] K�ldve: 2015. �prilis 8. 0:28 To: Kehl D�niel T�rgy: Aw: RE: [R] Simulate values Hey Daniel, Thanks for your answer. I changed my commands and ended up with: matrix - matrix(rnorm(500 * 40, 10, 5), ncol = 40, nrow = 500) variances1 - apply(matrix, 1, var) variances2 -(40 - 1) * variances1 / 25 What do you think about it? Does that work and was more or less what you expected to see? Best wishes, Mike Gesendet: Dienstag, 07. April 2015 um 05:39 Uhr Von: Kehl D�niel ke...@ktk.pte.hu An: Osiris10101 osiri...@gmx.ch, r-help@r-project.org r-help@r-project.org Betreff: RE: [R] Simulate values People do not usually do homework stuff here but I do not see the point in repeating the same sample 500 times. You might want to simulate 40x500 independent samples and put those in a matrix (see ?matrix) with lets say 40 rows and 500 columns. Once done, you can apply calculate the 500 sample standard deviations (or the chi-square values) where the ?apply function might help you. Lets start with that and lets see where you get. kd Felad�: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Osiris10101 [osiri...@gmx.ch] K�ldve: 2015. �prilis 7. 0:52 To: r-help@r-project.org T�rgy: [R] Simulate values Hello, I'm facing the following task: Simulate 500 values of the statistic (n-1)s^2/sigma^2 based on taking 500 samples of size n=40 from the N(mu=10; sigma^2 = 25) distribution. I think with the following command: rep(rnorm(40,10,25),times=500) I was able to simulate the samples but how I now can simulate the values of the chi-square-distribution is a mystery to me... I hope anyone can help me, shouldn't be a big problem... Thanks in advance! Reason for posting: I started a course at the University of Manchester and had to catch up with R, which I never used back in Switzerland. Now I'm solving some exercises to get more practice and this is one of them. -- View this message in context: http://r.789695.n4.nabble.com/Simulate-values-tp4705574.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Simulate values
People do not usually do homework stuff here but I do not see the point in repeating the same sample 500 times. You might want to simulate 40x500 independent samples and put those in a matrix (see ?matrix) with lets say 40 rows and 500 columns. Once done, you can apply calculate the 500 sample standard deviations (or the chi-square values) where the ?apply function might help you. Lets start with that and lets see where you get. kd Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Osiris10101 [osiri...@gmx.ch] Küldve: 2015. április 7. 0:52 To: r-help@r-project.org Tárgy: [R] Simulate values Hello, I'm facing the following task: Simulate 500 values of the statistic (n-1)s^2/sigma^2 based on taking 500 samples of size n=40 from the N(mu=10; sigma^2 = 25) distribution. I think with the following command: rep(rnorm(40,10,25),times=500) I was able to simulate the samples but how I now can simulate the values of the chi-square-distribution is a mystery to me... I hope anyone can help me, shouldn't be a big problem... Thanks in advance! Reason for posting: I started a course at the University of Manchester and had to catch up with R, which I never used back in Switzerland. Now I'm solving some exercises to get more practice and this is one of them. -- View this message in context: http://r.789695.n4.nabble.com/Simulate-values-tp4705574.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Correlation question
Hi, try cor(fitted.right,fitted.wrong) should give 1 as both are a linear function of speed! Hence cor(cars$dist,fitted.right)^2 and cor(x=cars$dist,y=fitted.wrong)^2 must be the same. HTH d Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Jonathan Thayn [jth...@ilstu.edu] Küldve: 2015. február 21. 22:42 To: r-help@r-project.org Tárgy: [R] Correlation question I recently compared two different approaches to calculating the correlation of two variables, and I cannot explain the different results: data(cars) model - lm(dist~speed,data=cars) coef(model) fitted.right - model$fitted fitted.wrong - -17+5*cars$speed When using the OLS fitted values, the lines below all return the same R2 value: 1-sum((cars$dist-fitted.right)^2)/sum((cars$dist-mean(cars$dist))^2) cor(cars$dist,fitted.right)^2 (sum((cars$dist-mean(cars$dist))*(fitted.right-mean(fitted.right)))/(49*sd(cars$dist)*sd(fitted.right)))^2 However, when I use my estimated parameters to find the fitted values, fitted.wrong, the first equation returns a much lower R2 value, which I would expect since the fit is worse, but the other lines return the same R2 that I get when using the OLS fitted values. 1-sum((cars$dist-fitted.wrong)^2)/sum((cars$dist-mean(cars$dist))^2) cor(x=cars$dist,y=fitted.wrong)^2 (sum((cars$dist-mean(cars$dist))*(fitted.wrong-mean(fitted.wrong)))/(49*sd(cars$dist)*sd(fitted.wrong)))^2 I'm sure I'm missing something simple, but can someone explain the difference between these two methods of finding R2? Thanks. Jon [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] simple question - mean of a row of a data.frame
Hi, rock[2,] is a data frame and you should not use sum() on a data frame, first google hit for the error message gives http://stackoverflow.com/questions/19697498/r-beginner-argument-is-not-numeric-or-logical-returning-na Otherwise I think you should use ?rowSums and ?rowMeans if you have numeric data frames. HTH, daniel Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Matthew Keller [mckellerc...@gmail.com] Küldve: 2015. február 11. 23:49 To: r help Tárgy: [R] simple question - mean of a row of a data.frame Hi all, Simple question I should know: I'm unclear on the logic of why the sum of a row of a data.frame returns a valid sum but the mean of a row of a data.frame returns NA: sum(rock[2,]) [1] 10901.05 mean(rock[2,],trim=0) [1] NA Warning message: In mean.default(rock[2, ], trim = 0) : argument is not numeric or logical: returning NA I get that rock[2,] is itself a data.frame of mode list, but why the inconsistency between functions? How can you figure this out from, e.g., ?mean ?sum Thanks in advance, Matt -- Matthew C Keller Asst. Professor of Psychology University of Colorado at Boulder www.matthewckeller.com [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] plot circles where z values are circles radius
Hi, see the help and especially the argument inches: Argument inches controls the sizes of the symbols. If TRUE (the default), the symbols are scaled so that the largest dimension of any symbol is one inch. If a positive number is given the symbols are scaled to make largest dimension this size in inches (so TRUE and 1 are equivalent). If inches is FALSE, the units are taken to be those of the appropriate axes. (For circles, squares and stars the units of the x axis are used. For boxplots, the lengths of the whiskers are regarded as dimensions alongside width and height when scaling by inches, and are otherwise interpreted in the units of the y axis.) Try scale=5000 xlims =c(min(x),max(x)) ylims =c(min(y),max(y)) z=convertToRadius(z)*scale symbols(x,y, circles=z, fg='red', inches=FALSE) HTH kd Feladó: R-help [r-help-boun...@r-project.org] ; meghatalmaz#243;: Dr. Alireza Zolfaghari [ali.zolfagh...@gmail.com] Küldve: 2015. január 23. 22:12 To: R-help; r-help-requ...@r-project.org Tárgy: [R] plot circles where z values are circles radius Hi there, I am trying to plot z values using Circle symbol. Each x and y has a value which will be plotted using a circle where circle's radius is corrlated with the value of z. I wrote the code , but unable to change the size of circle no matter what I chose for Scale. Any help please? x=c(84390255386 ,84390255386, 78028317380 ,53594648044,422) y=c(949849442 ,941645043, 840135292, 74, 821632939) z=c(0.005641896, 0.005641896 ,0.005641896, 0.007978846,0.007978846) convertToRadius-function(x){return(sqrt(x/pi))} scale=0.3 xlims =c(min(x),max(x)) ylims =c(min(y),max(y)) z=convertToRadius(z)*scale symbols(x,y, circles=z, fg='red') thanks Alireza [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see 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 -- To UNSUBSCRIBE and more, see 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] Making several plots using a loop function
Hi, try something like main=paste(plot,i) in the plot command. HTH, kd Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: li li [hannah@gmail.com] Küldve: 2014. június 24. 15:17 To: r-help Tárgy: [R] Making several plots using a loop function Hi all, When making a bunch of plots using a loop function, how to add title to reflect different plots. Specifically, for the code below, I generated 9 plots. I would like to add a title to each plot. For example, the titles will be respectively, plot1, plot 2, ⌠plot 9. Thank you very much! Hanna par(mfrow=c(3,3), pty=s, pch=16, col=blue) for ( i in 1:9) { lm1 - lm(log(run_res[2:11, i]) ~ log(level)) plot(log(level), log(run_res[2:11, i]), xlab=dllution levels, ylab=%PS-80) abline(lm1)} [[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] how to add a table under a plot?
Hi, the function is in the plotrix package, so you have to install and call that package first. After installing see example(addtable2plot). HTH, daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Helen Gao [helengao...@gmail.com] Küldve: 2014. május 23. 16:38 To: r-help@r-project.org Tárgy: [R] how to add a table under a plot? Dear all, If you know how to add a table under a plot, could you please send me your code? In R documentation, there is a function addtable2plot{}, do you know where to download the function? Thank you in advance, Helen [[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] bin a vector of continuous variables
Hi, you might try writing your own function, something like roundDown - function(x) floor(x/100)*100 roundDown(c(2282,174,273,432)) [1] 2200 100 200 400 and than apply it to your column. Please use ?dput next time to present your data, and post in plain text, instead of HTML. best, daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Assa Yeroslaviz [fry...@gmail.com] Küldve: 2014. május 15. 11:54 To: R help forum Tárgy: [R] bin a vector of continuous variables Hi all, I have a data.frame of three columns: partner1 partner2 Substract 1_5000_5001_1 1 5001 2282.3435 1_5000_10001_15000110001 174.1275 1_5000_15001_2115001 273.822 1_5000_20001_25000120001 546.27 1_5000_25001_3125001 701.299 1_5000_30001_35000130001 189.2345 ... I would like to create a new column for this data, but to bin the variable into separate bin of 0-100, 100-200, 200-300, 300-400, etc. so that the new data will look like that partner1 partner2 SubstractbinnedData 1_5000_5001_1 1 5001 2282.34352200 1_5000_10001_15000110001 174.1275100 1_5000_15001_2115001 273.822 200 1_5000_20001_25000120001 546.27 500 1_5000_25001_3125001 701.299 700 1_5000_30001_35000130001 189.2345100 ... Can someone give me a hint how to achieve this conversion? thanks Assa [[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] uniform number
Maybe you thought the binomial distribution? see ?rbinom best, kd Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Rolf Turner [r.tur...@auckland.ac.nz] Küldve: 2014. május 5. 9:27 To: Ragia Ibrahim Cc: r-help@r-project.org Tárgy: Re: [R] uniform number On 05/05/14 17:05, Ragia Ibrahim wrote: Dear group, How to generate uniform probability choosing p to be 2% and 5%, in separate trials for 100 times. No idea WTF you are talking about. Can you formulate a question that is comprehensible to the human mind? cheers, Rolf Turner __ 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] locating a data value in 3-dimensional data set
Dear Mamuash Bukana, is this a data frame with variable names you indicated? you will need something like which(dataframename$variablename == x) but if you have more you might use HTH kd Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: mamuash bukana [mamushbuk...@gmail.com] Küldve: 2014. április 8. 15:50 To: r-help@r-project.org Tárgy: [R] locating a data value in 3-dimensional data set I have a 3-dimentional data set with dimensions longitude, latitude, and time. Unfortunately, when I look at the range of values in the data set, I noticed some very extremely large(positive and negative) values which are unexpected to be there. So I wanted to point-out the location (lon, lat and time) which these extreme values correspond to in order to see what is happening there. But I could not point-out these grid points and time. I tried: which(3ddata==x) # 3ddata is name of data set, x is the observed extreme value But this couldn't help me. Any suggestion please? Thanks B __ 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] continuous time AR - predict/interpolate
Dear Members, I have a dataset that is similar to the first example in the car function, cts package data(V22174) fit - car(V22174,scale=0.2,order=7, ctrl=car_control(trace=TRUE)) summary(fit) I would like to ask if there is a way to get the predicted/fitted values for all the timepoints 1:784 not just for the timepoints when there are observations (which is pre2). I tried to read through car and car_control, tried predict(fit, newdata), but without success. I am not really into cont time ar, a friend of mine asked me to help him out with the R code, so sorry if there is a conceptual error in the question, not my fault! :) thanks a lot kd __ 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] Computing predictive values
Hi Tom, I think you are going to get better answers if you include some code which helps reproducing what you are doing for other users (posting guide). Exporting regression outputs to Excel does not seem to be the way to go. Aren't you just looking for ?predict. I am sure R can do the job for you but give an example please! best kd Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: steve tom [selli...@uoguelph.ca] Küldve: 2014. március 30. 3:22 To: r-help@r-project.org Tárgy: [R] Computing predictive values Hi All, I was unable to find help in search history. I have all my regression outputs in my environment tab, and wish to run them against my data, so that instead of having to export regression outputs to excel, and manually connect data-regression. I have predictive regressions that forecast 5 days ahead and whose rolling windows are 200 days trailing. I want to compute the daily predictions in R, using my regression outputs logged in my environment. Thanks so much for your time, been using R help for a year but this is the first time I've needed to post. -- View this message in context: http://r.789695.n4.nabble.com/Computing-predictive-values-tp4687832.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-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] Determine breaks based on a break type...
Hi, you possibly know that there are a lot of methods to determine the number of bins. As a default R has the Sturges method. I think it does something like x - runif(100) mybreaks - hist(runif(x))$breaks r - max(x)-min(x) br - nclass.Sturges(x) #note this is a really simple approach and see edit(nclass.Sturges) brn - 0:br pretty(min(x)+brn*r/br, n=br) I tried to make the steps clear, the pretty function does the job in the end. Hope that helps (although I do not know if it is faster, but you can try it on your own), best daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Jonathan Greenberg [j...@illinois.edu] Küldve: 2014. március 22. 17:15 To: r-help Tárgy: [R] Determine breaks based on a break type... R-helpers: I was wondering, given a vector of data, if there is a way to calculate the break points based on the breaks= parameter from histogram, but skipping all the other calculations (all I want is the breakpoints, not the frequencies). I can, of course, simply run the histogram and extract the break component: mybreaks - hist(runif(100))$breaks But is there a faster way to do this, if this is all I want? --j -- Jonathan A. Greenberg, PhD Assistant Professor Global Environmental Analysis and Remote Sensing (GEARS) Laboratory Department of Geography and Geographic Information Science University of Illinois at Urbana-Champaign 259 Computing Applications Building, MC-150 605 East Springfield Avenue Champaign, IL 61820-6371 Phone: 217-300-1924 http://www.geog.illinois.edu/~jgrn/ AIM: jgrn307, MSN: jgrn...@hotmail.com, Gchat: jgrn307, Skype: jgrn3007 __ 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] Assign numbers in R
Hi, is this homework? Try d - c(8,7,5,5,3,3,2,1,1,1) r - rep(1,length(d)) for (i in 2:length(d)) { if (d[i] != d[i-1]) { r[i]=r[i-1]+1; } else { r[i] = r[i-1]; } } Although I am sure there are better solutions! HTH daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: T Bal [studentt...@gmail.com] Küldve: 2014. március 12. 10:13 To: r-help@r-project.org Tárgy: [R] Assign numbers in R Hi, I have the following numbers: d - c(8,7,5,5,3,3,2,1,1,1) I want to convert these into the following numbers: r: 1,2,3,3,4,4,5,6,6,6 So if two numbers are different increment it if they are same then assign the same number: r - NULL for (i in 1:length(d)) { if (d[i] != d[i+1]) { r[i] =i+1; } else { r[i] = i; } } But this is not correct. How can I solve this problem? or how can I solve it in a different way? Thanks a lot! [[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] Fwd: Using comma as decimal mark in plots
Hi, take a look at this old conversation. I do not know about an other workaround, but maybe somebody else will know something. As we also use commas in Hungary, I am also affected by this. https://stat.ethz.ch/pipermail/r-help/2002-January/018030.html HTH daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Lotharster [lothars...@gmail.com] Küldve: 2014. március 7. 15:51 To: r-h...@stat.math.ethz.ch Tárgy: [R] Fwd: Using comma as decimal mark in plots Hi, I am preparing plots for a german publication. Therefore, I would like to use a comma as decimal mark instead of a point. How do I change this default in R? I could not find anything in the help pages, maybe you can help me out. Thanks, Lothar __ 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] fitting a time series into a GARCH model using fGarch
Dear Charles, see the help file and the examples at http://cran.r-project.org/web/packages/fGarch/fGarch.pdf or use ?garchFit in the examples you will see for example: garchFit(~ garch(1,1), data = x.vec, trace = FALSE) Try something like that. Make sure you provide the package of the function next time! HTH daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Charles Thuo [tcmui...@gmail.com] Küldve: 2014. február 25. 8:36 To: r-help@r-project.org Tárgy: [R] fitting a time series into a GARCH model using fGarch I have been trying to fit a time series object using the garchFit() function. However am getting the results below class(v.ts) [1] ts fit=garchFit(v.ts) Error in if (allVarsTest != 1) { : missing value where TRUE/FALSE needed I do not understand the error. Which missing value is required. Kindly assist. Charles. [[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] I am new to R
Dear Shikami, R comes with excellent material, look for it in your /doc/manual folder, start with R-intro.pdf. Have fun on your hopfully long journey with R! daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Shikami Kennedy [shika...@gmail.com] Küldve: 2014. február 13. 21:16 To: r-help@r-project.org Tárgy: [R] I am new to R Hello there, I am new to R and have no previous experience using any other statistics software. Can someone send me basic R notes to help me start off for the very first time? *With Kind regards,* * God bless you* * Shikami K. Akweyu Manager; Fisheries ComponentKenya Coastal Development Project (KCDP) State Department of Fisheries: Ministry of Agriculture, Livestock and Fisheries Phone: +254-0722 887 838 / 0736 887 838 Mombasa* [[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] match - returns a vector of the positions of (first) matches - looking for All positions.
Dear Witold, as a first hint: read posting guide please! People are answering in their free time, so please try to be polite! For your first problem: what are you expecting? You have a dataset where most of the values is missing, the others all 0's most of the time, and some Inf values as well... For the second problem: give a reproducible example, please. daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Witold E Wolski [wewol...@gmail.com] Küldve: 2014. február 3. 11:18 To: r-help@r-project.org Tárgy: [R] match - returns a vector of the positions of (first) matches - looking for All positions. Looking for a build in function which returns a vector of the positions of _ALL_ matches. -- Witold Eryk Wolski __ 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] Error Help only 0's may be mixed with negative subscripts
Dear Agapitus, we do not know what your variables look like but I assume ((zlim[2] - z_invDist)/zlen) * 7 produces a vector with both positive and negative numbert and you are using these numbers to extract elements of an other vector. If the numbers were all positive or negative, it would work, in this case R does not understand what you want. Try x - 1:5 x[1] x[-1] x[-1:1] #gives the same error Before posting again you should read an Intro to R at http://cran.r-project.org/doc/manuals/R-intro.pdf best wishes daniel ps: Gandhi instead of Gadhi? Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Agapitus Kato [agapitusk...@gmail.com] Küldve: 2014. január 31. 10:01 To: r-help@r-project.org Tárgy: [R] Error Help only 0's may be mixed with negative subscripts Help Please. Iam drawing a plot i R_Studio but consistently get this error: Error in colorlut2[((zlim[2] - z_invDist)/zlen) * 7] : only 0's may be mixed with negative subscripts-- *Whenever you are confronted with an opponent. Conquer him with love. Mahatma Gadhi* [[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] Markov chain simulation
Hi, see inline Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: Armel KAPTUE [armel.kap...@sdstate.edu] Küldve: 2014. január 28. 8:16 To: R-help@r-project.org Tárgy: [R] Markov chain simulation Hi there, I'm wonder if in R there is a way to simulate a discrete Markov chains with a specific number of occurence of state knowing the transition matrixway. Indeed there are many ways to do that in R! For example, how to simualte a markov chain of length n with p occurences (pn) of the sate '0' for a transition matrix defined by: I am not sure what you mean here?! If you give the length of the chain, depending on the transition matrix you are going to get some occurences of state '0', I do not think you can specify n, p and the transition matrix all at once! TransitionMatrix- matrix(c(0.7, 0.3, 0.4, 0.6),byrow=TRUE, nrow=2) colnames(TransitionMatrix) - c('0','1') row.names(TransitionMatrix) - c('0','1') Please try googling first, there are a lot of good examples on your problem, among the first ones: http://stackoverflow.com/questions/2754469/r-library-for-discrete-markov-chain-simulation Best daniel Thanks, -- Armel [[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] how to replace NA values
Dear Kinsly, try http://bit.ly/1mhXOfH Although values are usually missing for some good reason. Changing them to 0 might be very dangerous, R is going to think that ID3, 6 and 8 are all newborn babies! best daniel Feladó: r-help-boun...@r-project.org [r-help-boun...@r-project.org] ; meghatalmaz#243;: kingsly [ecoking...@yahoo.co.in] Küldve: 2014. január 19. 20:39 To: r-help@r-project.org Tárgy: [R] how to replace NA values Dear R community I have a large data set contain some empty cells. Because of that, may be I am wrong, NA values are produced. Now I want replace both empty and NA values with zero. Elder1 - data.frame( ID=c(ID1,ID2,ID3,ID6,ID8), age=c(38,35,,NA,NA)) Output I am expecting ID age ID1 38 ID2 35 ID3 0 ID6 0 ID8 0 In advance I thank your help. -- View this message in context: http://r.789695.n4.nabble.com/how-to-replace-NA-values-tp4683831.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.
Re: [R] Figure title
Try ?bquote HTH kd 2012.06.20. 10:36 keltezéssel, Joaquim J.S. Ramalho írta: Hi, I created several figures and their titles should appear like this: Figure 1: Monte Carlo results for alternative estimators of structural parameters (N = 100, T = 5) Because N and T change across figures, my code includes the following lines: N.set- 100 T.set- 5 mtext(?Figure 1: Monte Carlo results for alternative estimators of structural parameters,side=3,outer=T,line=4,cex=0.8) mtext(as.expression(substitute(list(N==p1,T==p2),list(p1=N.set[1],p2=T.set[1 ]))),side=3,outer=T,line=2,cex=0.8) However, I do not know how to merge the two last command lines in order to the title appear in a single line. Is it possible to do that? Thanks, José Santos [[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.
Re: [R] Smoothing a persp graph
Take a look at the kde2d function in the MASS package, maybe it helps. Best kd 2012.06.19. 14:26 keltezéssel, Guillaume Chapron írta: Hi, I'm unable to find a way to smooth data for a persp() graph. Example, suppose that I have data x,y,z like this: x- 1:10 y- 1:10 k- 20 z- outer(x, y, *) + matrix( k*runif(100, -1, 1), 10, 10) persp(x, y, z, theta = 35, phi = 25) The graph is not very nice. Is there a way to smooth the z data so that at the end the graph would look more like something like that: k- 2 z- outer(x, y, *) + matrix( k*runif(100, -1, 1), 10, 10) persp(x, y, z, theta = 35, phi = 25) There seems to be many smoothing functions in R (e.g. loess) but I have not been able to find one for a 3D graph. Thanks! Guillaume __ 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.
Re: [R] R matrix help
If you have your data in x, you can try something like matrix(x,length(x)/4,4) hth kd 2012.06.14. 14:51 keltezéssel, karthicklakshman írta: Dear R experts, I am interested in getting the dimensions for the matrix dynamically, based on the the number of elements in a matrix for example. if the number is 12, I should get dim= 3X4, if it is 20, dim=5X4. please help me do this. Thank you Regards karthick -- View this message in context: http://r.789695.n4.nabble.com/R-matrix-help-tp4633372.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-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] Rank a numerical variable
hi, read an Introduction to R. ?rank is what you are looking for? kd 2012.05.28. 20:17 keltezéssel, gaiarrido írta: hello, Is there any function in R to transform a numerical continuos variable in a ranked variable? Thanks - Mario Garrido Escudero PhD student Dpto. de Biología Animal, Ecología, Parasitología, Edafología y Qca. Agrícola Universidad de Salamanca -- View this message in context: http://r.789695.n4.nabble.com/Rank-a-numerical-variable-tp4631627.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-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] estimation problem
Dear Petr, thank you for your input. I tried to experiment with (probably somewhat biased) truncated means like in the following code. How I got the 225 as a truncation limit is a good question. :) REPS1 - REPS2 - 1000 N1 - 10 N2 - 3 N - N1+N2 x1 - rep(0,N1) x2 - rnorm(N2,300,100) x - c(x1,x2) n - 1000 for (i in 1:REPS1){ x_sample - sort(sample(x,n,replace=FALSE),TRUE) x_trunc - x_sample[1:225] REPS1[i] - mean(x_sample)*N REPS2[i] - sum(x_trunc)/n*N } sum(x2) mean(REPS1) mean(REPS2) sd(REPS1) sd(REPS2) sd(REPS2)/sd(REPS1) Best, daniel 2012.05.03. 17:45 keltezéssel, Petr Savicky írta: On Thu, May 03, 2012 at 03:08:00PM +0200, Kehl Dániel wrote: Dear List-members, I have a problem where I have to estimate a mean, or a sum of a population but for some reason it contains a huge amount of zeros. I cannot give real data but I constructed a toy example as follows N1- 10 N2- 3000 x1- rep(0,N1) x2- rnorm(N2,300,100) x- c(x1,x2) n- 1000 x_sample- sample(x,n,replace=FALSE) I want to estimate the sum of x based on x_sample (not knowing N1 and N2 but their sum (N) only). The sample mean has a huge standard deviation I am looking for a better estimator. Hi. I do not know the exact answer, but let me formulate the following observation. If the question is redefined to estimate the mean of nonzero numbers, then an estimate is mean(x_sample[x_sample != 0]). Its standard deviation in your situation may be estimated as res- rep(NA, times=1000) for (i in seq.int(along=res)) { x_sample- sample(x,n,replace=FALSE) res[i]- mean(x_sample[x_sample != 0]) } sd(res) [1] 18.72677 # this varies with the seed a bit The observation is that this cannot be improved much, since the estimate is based on a very small sample. The average size of the sample of nonzero values is N2/(N1+N2)*n = 29.1. So, the standard deviation should be something close to 100/sqrt(29.1) = 18.5376. Petr Savicky. __ 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] estimation problem
Dear List-members, I have a problem where I have to estimate a mean, or a sum of a population but for some reason it contains a huge amount of zeros. I cannot give real data but I constructed a toy example as follows N1 - 10 N2 - 3000 x1 - rep(0,N1) x2 - rnorm(N2,300,100) x - c(x1,x2) n - 1000 x_sample - sample(x,n,replace=FALSE) I want to estimate the sum of x based on x_sample (not knowing N1 and N2 but their sum (N) only). The sample mean has a huge standard deviation I am looking for a better estimator. I was thinking about trimmed (or left trimmed as my numbers are all positive) means or something similar, but if I calculate trimmed mean I do not know N2 to multiply with. Do you have any idea or could you give me some insight? 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] estimation problem
Dear Jeff, thank you for the response. Of course I know this is a theory question still I hope to get some comments on it (if somebody already dealt with alike problems might suggest a package and it would not take longer than saying this is a theoretical question) The values are counts, so 0 means those cases do not have this item, they have 0, as such it means a real zero, they are valid members. thanks, daniel 2012.05.03. 16:42 keltezéssel, Jeff Newmiller írta: Although you have provided R code to illustrate your problem, it is fundamentally a statistics theory question, and belongs somewhere else like stats.stackexchange.net. When you post there, I recommend that you spend more effort to identify why the zeros are present. If they are indicators of unknown values, that will be very different than if zeros are valid members of the population. --- Jeff NewmillerThe . . Go Live... DCN:jdnew...@dcn.davis.ca.us Basics: ##.#. ##.#. Live Go... Live: OO#.. Dead: OO#.. Playing Research Engineer (Solar/BatteriesO.O#. #.O#. with /Software/Embedded Controllers) .OO#. .OO#. rocks...1k --- Sent from my phone. Please excuse my brevity. Kehl Dánielke...@ktk.pte.hu wrote: Dear List-members, I have a problem where I have to estimate a mean, or a sum of a population but for some reason it contains a huge amount of zeros. I cannot give real data but I constructed a toy example as follows N1- 10 N2- 3000 x1- rep(0,N1) x2- rnorm(N2,300,100) x- c(x1,x2) n- 1000 x_sample- sample(x,n,replace=FALSE) I want to estimate the sum of x based on x_sample (not knowing N1 and N2 but their sum (N) only). The sample mean has a huge standard deviation I am looking for a better estimator. I was thinking about trimmed (or left trimmed as my numbers are all positive) means or something similar, but if I calculate trimmed mean I do not know N2 to multiply with. Do you have any idea or could you give me some insight? 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] compare two matrices
Dear Members, I have two estimated transition matrices and I want to compare them. In fact I want to check the hypothesis if they come from the same process. I tried to look for some test but all I found was independence test of contingency tables. The following code shows that the usual chi-squared test statistic does not follow chisq distribution. MCRepl - 5000 khi12 - rep(0,MCRepl) for (i in 1:MCRepl){ n - 1 M1 - matrix(table(sample(1:9, size = n, replace = TRUE)),3,3) M1 - M1/rowSums(M1) M2 - matrix(table(sample(1:9, size = n, replace = TRUE)),3,3) M2 - M2/rowSums(M2) khi12[i] - sum((M1-M2)^2/M2) } plot(density(khi12)) Is there a procedure implemented in R to make this comparison? If not, what could be a nice test statistic? Thank you so much, 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] simple matrix calculation
Dear David, Ted, Kjetil, Petr, thank you, you guys did a great job, I'll use your ideas in the future for sure. After I sent the question I figured a way, see below. x - 1:81 b - 1:3 Q - matrix(x,9,9) result - matrix(matrix(colSums(matrix(t(Q),3)),,3,TRUE) %*% b,3,3) I hope there is no error in this solution and you can use this idea sometime! Thank you again, have a great day Daniel 2012.03.29. 8:48 keltezéssel, Petr Savicky írta: On Wed, Mar 28, 2012 at 10:46:11PM +0200, Kehl Dániel wrote: Dear list-members, I have a 9-by-9 matrix lets call it A with first row a11, a12, a13,..., a19 etc. I also have a vector of length 3 (B). I want to construct a matrix of size 3x3 in the following way: - divide matrix A to 9 3x3 blocks - first is a11, a12, a13 a21, a22, a23 a31, a32, a33 - I want to get rowSums of this A1 matrix - Multiply A1*B and get a scalar, the first element of my new 3x3 matrix. Hi. Try the following, which is based on the solution by Ted Harding. # some input A- matrix(1:81, nrow=9, ncol=9) B- 7:5 # compute the 3 x 3 matrix C- diag(3)[rep(1:3, each=3), ] D- cbind(rbind(B, 0, 0), rbind(0, B, 0), rbind(0, 0, B)) R1- D %*% A %*% C # compare with another approach E- A * matrix(B, nrow=9, ncol=9) # component wise product C- diag(3)[rep(1:3, each=3), ] R2- t(C) %*% E %*% C max(abs(R1 - R2)) # [1] 0 Hope this helps. Petr Savicky. __ 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] simple matrix calculation
Dear list-members, I have a 9-by-9 matrix lets call it A with first row a11, a12, a13,..., a19 etc. I also have a vector of length 3 (B). I want to construct a matrix of size 3x3 in the following way: - divide matrix A to 9 3x3 blocks - first is a11, a12, a13 a21, a22, a23 a31, a32, a33 - I want to get rowSums of this A1 matrix - Multiply A1*B and get a scalar, the first element of my new 3x3 matrix. I could do that with loop. Can you suggest something that is more elegant and faster? Thank you 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] lists everywhere
Dear list members, I have a really simple problem. I connected to a DB and have the following query adat - dbGetQuery(con, paste(select * from kmdata where SzeAZ=', szeazok[i], ' order by datum, sep=)) now I have the data in the adat variable which is a list. In fact the elements of the list are lists as well is.list(adat) [1] TRUE is.list(adat[10]) [1] TRUE is.list(adat[[10]]) [1] FALSE is.vector(adat[[10]]) [1] TRUE I simply want to use a function with sapply on the 13-76th columns of the original list. sapply(data[[13:76]], myfunc) does not work of course. I tried to define 13:76 in a vector, still no result. How is it possible? thanks a lot d __ 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] SOLVED, Re: lists everywhere
nevermind, typo (and some gray hair) sorry 12/5/2011 8:21 PM keltezéssel, Kehl Dániel írta: Dear list members, I have a really simple problem. I connected to a DB and have the following query adat - dbGetQuery(con, paste(select * from kmdata where SzeAZ=', szeazok[i], ' order by datum, sep=)) now I have the data in the adat variable which is a list. In fact the elements of the list are lists as well is.list(adat) [1] TRUE is.list(adat[10]) [1] TRUE is.list(adat[[10]]) [1] FALSE is.vector(adat[[10]]) [1] TRUE I simply want to use a function with sapply on the 13-76th columns of the original list. sapply(data[[13:76]], myfunc) does not work of course. I tried to define 13:76 in a vector, still no result. How is it possible? thanks a lot d __ 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] [SOLVED]looking for beta parameters
I managed to solve the problem myself without using this code. thx 2011-11-24 12:26 keltezéssel, Kehl Dániel írta: Dear Community, I am trying to write code for the following problem. Lets assume we have a beta distribution. I know one quantile, lets say, 10% of the mass lies above .8, that is between .8 and 1. In addition, I know that the average of this truncated tail is a given number, lets say .86. I have found the beta.select function in the LearnBayes package, which is as follows: function (quantile1, quantile2) { betaprior1 = function(K, x, p) { m.lo = 0 m.hi = 1 flag = 0 while (flag == 0) { m0 = (m.lo + m.hi)/2 p0 = pbeta(x, K * m0, K * (1 - m0)) if (p0 p) m.hi = m0 else m.lo = m0 if (abs(p0 - p) 1e-04) flag = 1 } return(m0) } p1 = quantile1$p x1 = quantile1$x p2 = quantile2$p x2 = quantile2$x logK = seq(-3, 8, length = 100) K = exp(logK) m = sapply(K, betaprior1, x1, p1) prob2 = pbeta(x2, K * m, K * (1 - m)) ind = ((prob2 0) (prob2 1)) app = approx(prob2[ind], logK[ind], p2) K0 = exp(app$y) m0 = betaprior1(K0, x1, p1) return(round(K0 * c(m0, (1 - m0)), 2)) } I assume one could change this code to get the results I need, but some parts of the function are not clear for me, any help would be greatly appreciated. Thanks a lot: 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] Why it is happeing?
Note that current implementations of*R*use 32-bit integers for integer vectors, so the range of representable integers is restricted to about/+/-2*10^9/:|double http://stat.ethz.ch/R-manual/R-patched/library/base/html/double.html|s can hold much larger integers exactly. hth d 2011-11-26 13:05 keltezéssel, Christofer Bogaso írta: Dear all, I had following calculations with R: x = vector(length = 4) x[1] = 1 x[2] = 3 x[3] = 123456789123456 x[4] = -9876543219876 as.integer(x) [1] 1 3 NA NA Warning message: NAs introduced by coercion What went wrong? Thanks and regards, __ 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] looking for beta parameters
Dear Community, I am trying to write (update) a code for the following problem. Lets assume we have a beta distribution. I know one quantile, lets say, 10% of the mass lies above .8, that is between .8 and 1. In addition, I know that the average of this truncated tail is a given number, lets say .86. I have found the beta.select function in the LearnBayes package, which is as follows: function (quantile1, quantile2) { betaprior1 = function(K, x, p) { m.lo = 0 m.hi = 1 flag = 0 while (flag == 0) { m0 = (m.lo + m.hi)/2 p0 = pbeta(x, K * m0, K * (1 - m0)) if (p0 p) m.hi = m0 else m.lo = m0 if (abs(p0 - p) 1e-04) flag = 1 } return(m0) } p1 = quantile1$p x1 = quantile1$x p2 = quantile2$p x2 = quantile2$x logK = seq(-3, 8, length = 100) K = exp(logK) m = sapply(K, betaprior1, x1, p1) prob2 = pbeta(x2, K * m, K * (1 - m)) ind = ((prob2 0) (prob2 1)) app = approx(prob2[ind], logK[ind], p2) K0 = exp(app$y) m0 = betaprior1(K0, x1, p1) return(round(K0 * c(m0, (1 - m0)), 2)) } I assume one could change this code to get the results I need, but some parts of the function are not clear for me, any help would be greatly appreciated. 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] sorry, [WinBUGS] question
Dear Community, I know this is not the place to ask WinBUGS questions, but I did not get any answers on other lists. I am rather new to the BUGS language and to bayesian modeling, excuse me for probably simple questions. I have to conduct a bayesian meta-analysis of some data. We have collected observational and randomized studies related to a certain field of interest. The idea is to analyse the randomized studies with two different priors. One is non-informative, the other is calculated from the observational ones. We also want to use a sceptical prior. The code I used for the non-informative prior analysis and to get the other prior is following: model { for( i in 1 : Num ) { rc[i] ~ dbin(pc[i], nc[i]) rt[i] ~ dbin(pt[i], nt[i]) log(pc[i]) - mu[i] log(pt[i]) - mu[i] + delta[i] mu[i] ~ dnorm(0,1.0E-5) delta[i] ~ dnorm(d, tau) } d ~ dnorm(0,1.0E-6) tau ~ dgamma(0.001,0.001) sigma - 1 / sqrt(tau) relr - exp(d) } which appears to work fine after loading data and initials. (there was a study with 0 treated and 0 control cases, I had to exclude that one for some reasons, is there a solution for this?) If I understand right, I can interpret the relr as bayesian estimate of relative risk, with credible interval etc. I have some questions in connection with the informative prior analysis: - after running this same code for the observational data, how do I change the specification of d and tau? - how can I get posterior probabilities like relr1? - usually how many iterations, thin etc. do we use? - can I get nice graphics with both priors and posteriors on it? I do have to learn everything on my own, so any help is greatly appreciated. I know R and the BUGS package are able to communicate, is anybody can help to solve the task through the R interface would be great. Thank you for you answer or any kind of help: 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] conditions simpler way
Dear All, I have a MCMC result in x1. I was wondering if there is a simpler, more elegant way of evaluating the estimate of an integral then this (I am pretty sure there is): Also if I want to count the x's say -1x2 but not the ones in the burn in period. [code] z - -2 burnin - 2000 int1 - length(x1$x[(burnin+1):length(x1$x)][x1$x[(burnin+1):length(x1$x)]z])/(length(x1$x)-burnin) [\code] Thank you: 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] Simple MC integration question
Dear Community, I try to compute the variance of a MC integral where I know the analytical solution. The function is exp(-x) integrated on the interval (2,4). (Rizzo example) The true value is exp(-2)-exp(-4)~.1170196 I have the following short code: code iter - 1 MCs - numeric(iter) n - 5000 a - 2; b - 4 for (i in 1:iter){ x - runif(n, a, b) MCs[i] - (b-a)*mean(exp(-x)) } hist(MCs, freq=FALSE) \code Which shows a nice normal distribution around the theoretical value, with a small variance. On the 125. page of the book the author says that the Var(theta_hat)=(b-a)^2/m*Var(g(X)). I try to compare the theoretical normal distribution with the simulated one, but the two normal distributions are far from each other. I thought Var(g(X)) was 1, because g(x) is exponential with lambda 1, but probably thats not true. Any help is appreciated, thanks: 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] Generalized Linear Model
Hi! Try to read about the glm function, type: ?glm in your R editor. It looks like you have contingency tables, maybe a loglin model would be good to start with. D 2011-04-25 12:28 keltezéssel, Megan írta: Hello, I am trying to run a generalized linear model but do not know where to begin. I have attached my data to R but do not know where to go from there. I have two independent variables (each has two factors associated with them) and two dependent variables, each with either a yes/no response which I've valued either 0 or 1 in the data set. Any input would be greatly appreciated. -- View this message in context: http://r.789695.n4.nabble.com/Generalized-Linear-Model-tp3473924p3473924.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-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] all combinations with replacement
Dear all, is there an easy way to get all possible combinations (?) with replacement. If n=6, k=3, i want something like 0 0 6 0 5 1 0 4 2 0 3 3 0 2 4 . . . 5 0 1 5 1 0 6 0 0 I tried to look at combn() but I could not get this done with it. Thank you in advance: 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] all combinations with replacement
Thank you. I only need those where the rowsum = n. I could choose those with code, but I dont think it is efficient that way. daniel 2011-04-21 12:33 keltezéssel, Dimitris Rizopoulos írta: expand.grid(rep(list(0:6), 3)) __ 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] What does the - operator mean?
maybe help (-) helps daniel 2011-04-21 12:14 keltezéssel, Cliff Clive írta: I should probably point out that in the example, ecov_xy and decay are scalars, and x and y are vectors. -- View this message in context: http://r.789695.n4.nabble.com/What-does-the-operator-mean-tp3466657p3466672.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-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] Merge matrix
?cbind should solve your problem 2011-04-12 07:54 keltezéssel, pankaj borah írta: I have two matrices A and B dim (A) [1] 30380 104 dim(Bt) [1] 3038063 I want to combine both A and B to matrix C where dim(C) [1] 30380 167 How do I do that ? Regards, Pankaj Barah Department of Biology, Norwegian University of Science Technology (NTNU) Realfagbygget, N-7491 [[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.
Re: [R] Dirichlet surface
Dear David, I think that is a small bug too, maybe because the function is constant? is there a nice way to put the c(0,2.1) argument optionally, only if all the parameters are 1? Should I post the problem somewhere else (developers maybe?) thanks: Daniel 2011-03-30 04:42 keltezéssel, David Winsemius írta: On Mar 29, 2011, at 4:45 PM, Kehl Dániel wrote: Dear list members, I want to draw surfaces of Dirichlet distributions with different parameter settings. My code is the following: #begin code a1 - a2 - a3 - 2 #a2 - .5 #a3 - .5 x1 - x2 - seq(0.01, .99, by=.01) f - 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 } z - outer(x1, x2, f) z[z=0] - NA persp(x1, x2, z, main = Dirichlet Distribution, 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) #end code It works fine (I guess), except for a1=a2=a3=1. In that case I get the error: Error in persp.default... invalid 'z' limits. The z matrix has only elements 2 and NA. Might be a buglet in persp. If you set the zlim argument to c(0,2.1), you get the expected constant plane at z=2 for those arguments. Any ideas are appreciated. Thank you: Daniel University of Pécs __ 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. David Winsemius, MD Heritage Laboratories West Hartford, CT __ 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] Dirichlet surface
It helped a lot indeed, thank you very much! Now I understand why it was a problem for persp! Daniel 2011-03-30 10:31 keltezéssel, Gavin Simpson írta: On Wed, 2011-03-30 at 09:55 -0700, Kehl Dániel wrote: Dear David, I think that is a small bug too, maybe because the function is constant? is there a nice way to put the c(0,2.1) argument optionally, only if all the parameters are 1? Should I post the problem somewhere else (developers maybe?) I don't think this is a bug really; the code is having to compute limits of the z axis and you supplied it one bit of information: a 2. If your data are so degenerate then it is not unreasonable to expect some user intervention. Admittedly, persp doesn't seem to work like other R plotting functions. You could do something like: persp(x1, x2, z, zlim = if(length(na.omit(unique(as.vector(z 2){ c(0,2.1) } else { NULL}) in your call to persp so it only uses user-defined limits if the number of numeric values in z is less than 2. HTH G thanks: Daniel 2011-03-30 04:42 keltezéssel, David Winsemius írta: On Mar 29, 2011, at 4:45 PM, Kehl Dániel wrote: Dear list members, I want to draw surfaces of Dirichlet distributions with different parameter settings. My code is the following: #begin code a1- a2- a3- 2 #a2- .5 #a3- .5 x1- x2- seq(0.01, .99, by=.01) f- 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 } z- outer(x1, x2, f) z[z=0]- NA persp(x1, x2, z, main = Dirichlet Distribution, 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) #end code It works fine (I guess), except for a1=a2=a3=1. In that case I get the error: Error in persp.default... invalid 'z' limits. The z matrix has only elements 2 and NA. Might be a buglet in persp. If you set the zlim argument to c(0,2.1), you get the expected constant plane at z=2 for those arguments. Any ideas are appreciated. Thank you: Daniel University of Pécs __ 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. David Winsemius, MD Heritage Laboratories West Hartford, CT __ 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] Dirichlet surface
Actually, it works for the a=1 case, not for the others. It still gives the invalid 'zlim argument' error. I'll try to work it out maybe instead of NULL giving a c which is dependent on the max(z). Daniel 2011-03-30 10:42 keltezéssel, Kehl Dániel írta: It helped a lot indeed, thank you very much! Now I understand why it was a problem for persp! Daniel 2011-03-30 10:31 keltezéssel, Gavin Simpson írta: On Wed, 2011-03-30 at 09:55 -0700, Kehl Dániel wrote: Dear David, I think that is a small bug too, maybe because the function is constant? is there a nice way to put the c(0,2.1) argument optionally, only if all the parameters are 1? Should I post the problem somewhere else (developers maybe?) I don't think this is a bug really; the code is having to compute limits of the z axis and you supplied it one bit of information: a 2. If your data are so degenerate then it is not unreasonable to expect some user intervention. Admittedly, persp doesn't seem to work like other R plotting functions. You could do something like: persp(x1, x2, z, zlim = if(length(na.omit(unique(as.vector(z 2){ c(0,2.1) } else { NULL}) in your call to persp so it only uses user-defined limits if the number of numeric values in z is less than 2. HTH G thanks: Daniel 2011-03-30 04:42 keltezéssel, David Winsemius írta: On Mar 29, 2011, at 4:45 PM, Kehl Dániel wrote: Dear list members, I want to draw surfaces of Dirichlet distributions with different parameter settings. My code is the following: #begin code a1- a2- a3- 2 #a2- .5 #a3- .5 x1- x2- seq(0.01, .99, by=.01) f- 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 } z- outer(x1, x2, f) z[z=0]- NA persp(x1, x2, z, main = Dirichlet Distribution, 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) #end code It works fine (I guess), except for a1=a2=a3=1. In that case I get the error: Error in persp.default... invalid 'z' limits. The z matrix has only elements 2 and NA. Might be a buglet in persp. If you set the zlim argument to c(0,2.1), you get the expected constant plane at z=2 for those arguments. Any ideas are appreciated. Thank you: Daniel University of Pécs __ 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. David Winsemius, MD Heritage Laboratories West Hartford, CT __ 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-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] Dirichlet surface
Dear list members, I want to draw surfaces of Dirichlet distributions with different parameter settings. My code is the following: #begin code a1 - a2 - a3 - 2 #a2 - .5 #a3 - .5 x1 - x2 - seq(0.01, .99, by=.01) f - 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 } z - outer(x1, x2, f) z[z=0] - NA persp(x1, x2, z, main = Dirichlet Distribution, 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) #end code It works fine (I guess), except for a1=a2=a3=1. In that case I get the error: Error in persp.default... invalid 'z' limits. The z matrix has only elements 2 and NA. Any ideas are appreciated. Thank you: Daniel University of Pécs __ 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.