[R] Outlier Problem in Survreg Function
Hi Everyone, I have recently started using r and working on survival analysis using the function survreg. I am facing a trange problem. One of the covariates in my analysis has outliers because of which survreg is giving incorrect results. Howevere when I am removing the outliers or scaling down the values of the covariate by a factor of 2 it is giving correct results. Below is a ditribution of the ariable and the results Min. 1st Qu. MedianMean 3rd Qu.Max. 0 3 54500 95450 123000 165 Survreg Resuts survreg(formula = Surv(TIME_TO_FAILURE, CENSOR_DEFAULT) ~ ADVANCE, data = data) Coefficients: (Intercept) ADVANCE 0.00 -6.385336 Scale= 0.9785933 Loglik(model)= -40227366 Loglik(intercept only)= -914141 Chisq= -78626451 on 1 degrees of freedom, p= 1 n=198099 (885 observations deleted due to missingness) Survreg Results after scaling down the variable by 10 survreg(formula = Surv(TIME_TO_FAILURE, CENSOR_DEFAULT) ~ ADVANCE_SCALED, data = data) Coefficients: (Intercept) ADVANCE_SCALED 4.132962e+00 -2.181577e-05 Scale= 0.9428758 Loglik(model)= -909139.4 Loglik(intercept only)= -914141 Chisq= 10003.19 on 1 degrees of freedom, p= 0 n=198099 (885 observations deleted due to missingness) Survreg Results Afte removing the outliers(5% of the obs) data - subset(data,data$ADVANCE = 20) survreg(Surv(TIME_TO_FAILURE,CENSOR_DEFAULT) ~ ADVANCE , data = data ) Call: survreg(formula = Surv(TIME_TO_FAILURE, CENSOR_DEFAULT) ~ ADVANCE, data = data) Coefficients: (Intercept) ADVANCE 4.224298e+00 -3.727171e-06 Scale= 0.9601186 Loglik(model)= -822521.9 Loglik(intercept only)= -825137.1 Chisq= 5230.49 on 1 degrees of freedom, p= 0 n=177332 (444 observations deleted due to missingness) Please let me know if someone else has faced the same problem and what is the way around to deal with it ? Should I scale down the variable or remove the outliers? -- View this message in context: http://r.789695.n4.nabble.com/Outlier-Problem-in-Survreg-Function-tp2301422p2301422.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Equivalent to go-to statement
On Sun, Jul 25, 2010 at 1:57 AM, Michael Haenlein haenl...@escpeurope.eu wrote: Dear all, I'm working with a code that consists of two parts: In Part 1 I'm generating a random graph using the igraph library (which represents the relationships between different nodes) and a vector (which represents a certain characteristic for each node): library(igraph) g - watts.strogatz.game(1,100,5,0.05) z - rlnorm(100,0,1) In Part 2 I'm iteratively changing the elements of z in order to reach a certain value of a certain target variable. I'm doing this using a while statement: while (target_variable threshold) {## adapt z} The problem is that in some rare cases this iterative procedure can take very long (a couple of million of iterations), depending on the specific structure of the graph generated in Part 1. I therefore would like to change Part 2 of my code in the sense that once a certain threshold number of iterations has been achieved, the iterative process in Part 2 stops and goes back to Part 1 to generate a new graph structure. So my idea is as follows: - Run Part 1 and generate g and z - Run Part 2 and iteratively modify z to maximize the target variable - If Part 2 can be obtained in less than X steps, then go to Part 3 - If Part 2 takes more than X steps then go back to Part 1 and start again I think that R does not have a function like go-to or go-back. Does anybody know of a convenient way of doing this? Thanks very much for your help, goto's can be replaced with loops. In this case create a double loop such that the outer loop does not repeat if the inner loop finished due to reaching the target: target_variable - -Inf while(target_variable threshold) { ... iter - 0 while(target_variable threshold iter max_iter) { ... update iter and target_variable ... } } __ 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] UseR! 2010 - my impressions
On 07/23/2010 06:50 PM, Ravi Varadhan wrote: Dear UseRs!, Everything about UseR! 2010 was terrific! I really mean everything - the tutorials, invited talks, kaleidoscope sessions, focus sessions, breakfast, snacks, lunch, conference dinner, shuttle services, and the participants. The organization was fabulous. NIST were gracious hosts, and provided top notch facilities. The rousing speech by Antonio Possolo, who is the chief of Statistical Engineering Division at NIST, set the tempo for the entire conference. Excellent invited lectures by Luke Tierney, Frank Harrell, Mark Handcock, Diethelm Wurtz, Uwe Ligges, and Fritz Leisch. All the sessions that I attended had many interesting ideas and useful contributions. During the whole time that I was there, I could not help but get the feeling that I am a part of something great. Before I end, let me add a few words about a special person. This conference would not have been as great as it was without the tireless efforts of Kate Mullen. The great thing about Kate is that she did so much without ever hogging the limelight. Thank you, Kate and thank you NIST! I cannot wait for UseR!2011! Best, Ravi. Ravi Varadhan, Ph.D. Assistant Professor, Division of Geriatric Medicine and Gerontology School of Medicine Johns Hopkins University Ph. (410) 502-2619 email: rvarad...@jhmi.edu I want to echo what Ravi said. The talks were terrific (thanks to the program committee and the speakers) and Kate Mullen and her team did an extraordinary job in putting the conference together and running it. I am proud to have been a part of it. Thank you all! Yes. I fully agree and can only thank Kate and the rest of the NIST team again and again for the great job they did. Hope everybody ha[sd] a safe trip home (mine will be in a few hours). Best, Fritz Leisch -- Prof. Dr. Friedrich Leisch Institut für Statistik Ludwig-Maximilians-Universität Ludwigstraße 33, D-80539 München Tel: (+49 89) 2180 3165 Fax: (+49 89) 2180 5308 http://www.stat.uni-muenchen.de/~leisch __ 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] Discrepancy in help for object.size() and question on how to round object sizes
I think there is a discrepancy In the help for object.size(). In the usage section there is the comment: ## S3 method for class 'object_size': while in the value section there is the text: An object of class ‘object.size’ ... And R itself says: class(object.size(letters)) [1] object_size Also, I was trying to print out object sizes in Kb, but rounded to whole number of units, but I could not figure out how to do that without having to replicate the math in the print method for object.size. tmp-numeric(10) object.size(tmp) 800024 bytes print(object.size(tmp), units=Kb) 781.3 Kb What I want is 781 Kb, but it wasn't obvious how to get there. The following seemed wrong, and didn't work: print(signif(object.size(tmp),1), units=Kb) 781.2 Kb print(round(object.size(tmp)), units=Kb) 781.3 Kb I know I can just get the result in bytes and divide by 1024, and then round, but it seemed like there should be a more straightforward way, so any suggestions are welcome. Thanks! Jen sessionInfo() R version 2.11.1 (2010-05-31) i686-pc-linux-gnu locale: [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C [3] LC_TIME=en_US.UTF-8LC_COLLATE=en_US.UTF-8 [5] LC_MONETARY=C LC_MESSAGES=en_US.UTF-8 [7] LC_PAPER=en_US.UTF-8 LC_NAME=C [9] LC_ADDRESS=C LC_TELEPHONE=C [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C attached base packages: [1] stats graphics utils datasets grDevices methods base other attached packages: [1] RColorBrewer_1.0-2 loaded via a namespace (and not attached): [1] tools_2.11.1 __ 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] error using predict
Hi I am very new to R (so excuse me in advance if this is pretty trivial) I am using the predict function to get prediction on a dataset from another dataset using the follwoing command: newpredT2003 = predict( object=out.model_T2003, newdata=aodmc_2003 , level = 0 ) yet i get this error: Error in na.fail.default(list(AOD = c(0.092, 0.081, 0.086, 0.085, 0.09, : missing values in object Calls: predict ... model.frame.default - Anonymous - na.fail.default i think its something simple but cant find any info when googling..can anyone point me in the right direction on what needs to be done to fix the errors? thx Ethan __ 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] Discrepancy in help for object.size() and question on how to round object sizes
On 25/07/2010 7:58 AM, Jennifer Lyon wrote: I think there is a discrepancy In the help for object.size(). In the usage section there is the comment: ## S3 method for class 'object_size': while in the value section there is the text: An object of class ‘object.size’ ... And R itself says: class(object.size(letters)) [1] object_size Thanks, I'll fix the typo. Also, I was trying to print out object sizes in Kb, but rounded to whole number of units, but I could not figure out how to do that without having to replicate the math in the print method for object.size. I don't think there's any simple way to do it. You can see the print method using utils:::print.object_size and it has one decimal point hard coded into the calls to round(). So you could copy that print method and change the rounding, or if you don't mind sloppy truncating rather than proper rounding, you could do a hack like this: wholesize - function(x, units=b) { size - capture.output(print(object.size(x), units=units)) cat( sub(\\.[[:digit:]], , size), \n ) } We could add a decimals argument to the version in R, but I'd rather not: it just introduces another point for people to confuse formatting with rounding, e.g. if the size is exactly 1000 Kb, should it be printed as 1000.0 Kb if you ask for 1 decimal? (Currently it will print as 1000 Kb.) Duncan Murdoch tmp-numeric(10) object.size(tmp) 800024 bytes print(object.size(tmp), units=Kb) 781.3 Kb What I want is 781 Kb, but it wasn't obvious how to get there. The following seemed wrong, and didn't work: print(signif(object.size(tmp),1), units=Kb) 781.2 Kb print(round(object.size(tmp)), units=Kb) 781.3 Kb I know I can just get the result in bytes and divide by 1024, and then round, but it seemed like there should be a more straightforward way, so any suggestions are welcome. Thanks! Jen sessionInfo() R version 2.11.1 (2010-05-31) i686-pc-linux-gnu locale: [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C [3] LC_TIME=en_US.UTF-8LC_COLLATE=en_US.UTF-8 [5] LC_MONETARY=C LC_MESSAGES=en_US.UTF-8 [7] LC_PAPER=en_US.UTF-8 LC_NAME=C [9] LC_ADDRESS=C LC_TELEPHONE=C [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C attached base packages: [1] stats graphics utils datasets grDevices methods base other attached packages: [1] RColorBrewer_1.0-2 loaded via a namespace (and not attached): [1] tools_2.11.1 __ 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] Manage several graphical devices in interactive mode
Dear R-users, Does anybody know a good way to create and use several graphical devices at the same time in interactive mode? Ideally, I'd like to open 2 to 3 devices and assign names to them. This way, I could make any addition/modification/update to a particular device using its name. I did not see anything like a name argument in ?X11. Is there an alternative? Thanks in advance for your feeback. Sebastien [[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] R equivalent of SAS proc freq
Dear R-users, I am looking for a R function that would be the equivalent of the SAS proc freq ( http://support.sas.com/documentation/cdl/en/procstat/63104/HTML/default/viewer.htm#/documentation/cdl/en/procstat/63104/HTML/default/procstat_freq_sect006.htm). The table, ftable, xtabs functions are close but do not quite offer the same capabilities (e.g. they just return counts and no %ages as far as I could tell). I wanted to check with the group if there would already be such a function in base or in a contribution package, before I start coding my own function. Thanks for your feedback. [[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 equivalent of SAS proc freq
On Jul 25, 2010, at 9:32 AM, Sébastien Bihorel wrote: Dear R-users, I am looking for a R function that would be the equivalent of the SAS proc freq ( http://support.sas.com/documentation/cdl/en/procstat/63104/HTML/default/viewer.htm#/ documentation/cdl/en/procstat/63104/HTML/default/ procstat_freq_sect006.htm). The table, ftable, xtabs functions are close but do not quite offer the same capabilities (e.g. they just return counts and no %ages as far as I could tell). I wanted to check with the group if there would already be such a function in base or in a contribution package, before I start coding my own function. There are a couple of efforts to imitate the Proc FREQ output in the archives. If you use one of the several search facilities (e.g. RSeek, the RSiteSearch function or the ??? function in the sos library) you will get links to those: (A test of this theory with RSeek pointed to the CrossTable function in gmodels.) Try also with... ?RsiteSearch RSiteSearch() Or with ... require(sos) ???proc freq sas -- David Winsemius, MD 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] Manage several graphical devices in interactive mode
On 25-Jul-10 13:22:11, Sébastien Bihorel wrote: Dear R-users, Does anybody know a good way to create and use several graphical devices at the same time in interactive mode? Ideally, I'd like to open 2 to 3 devices and assign names to them. This way, I could make any addition/modification/update to a particular device using its name. I did not see anything like a name argument in ?X11. Is there an alternative? Thanks in advance for your feeback. Sebastien You can certainly do this by hand. The basic R terminal is device number 1. If you do X11() (or invoke it implicitly by using a 'plot' command) this will be device number 2. With just this one open, any 'plot' (or plot-related) commands will re-use it. However, having opened device #2, you can do X11() again and get a second graphics device which will be number 3. And so on, for as many additional devices as you like. By default, the device that the results of any 'plot' command are sent to will be the most recently opened one. However, you can select the device using the command dev.set(n) where n ( = 2,3,... ) is the device you want to use. The device which is active will be shown by the word (ACTIVE) attached to its display. All other devices will show (inactive). You could name your devices by indexing a vector (2:n) by names. Try the following, Starting with no graphics devices open: X11() # dev 2 X11() # dev 3 X11() # dev 4 ## This one is currently active ## Arange these so that you can see all their top bars devN - c(plotA=2,plotB=3,plotC=4) dev.set(devN[plotA]) # dev 2 is active dev.set(devN[plotC]) # dev 4 is active dev.set(devN[plotB]) # dev 3 is active dev.set(devN[plotA]) # dev 2 is active dev.set(devN[plotC]) # dev 4 is active Hoping this helps, Ted. E-Mail: (Ted Harding) ted.hard...@manchester.ac.uk Fax-to-email: +44 (0)870 094 0861 Date: 25-Jul-10 Time: 15:03:14 -- XFMail -- __ 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 equivalent of SAS proc freq
you can use prop.tables() on a table() object to get %ages, does this do what you need? - Corey Sparks, PhD Assistant Professor Department of Demography and Organization Studies University of Texas at San Antonio 501 West Durango Blvd Monterey Building 2.270C San Antonio, TX 78207 210-458-3166 corey.sparks 'at' utsa.edu https://rowdyspace.utsa.edu/users/ozd504/www/index.htm -- View this message in context: http://r.789695.n4.nabble.com/R-equivalent-of-SAS-proc-freq-tp2301547p2301607.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Manage several graphical devices in interactive mode
On 25/07/2010 10:03 AM, (Ted Harding) wrote: On 25-Jul-10 13:22:11, Sébastien Bihorel wrote: Dear R-users, Does anybody know a good way to create and use several graphical devices at the same time in interactive mode? Ideally, I'd like to open 2 to 3 devices and assign names to them. This way, I could make any addition/modification/update to a particular device using its name. I did not see anything like a name argument in ?X11. Is there an alternative? Thanks in advance for your feeback. Sebastien You can certainly do this by hand. The basic R terminal is device number 1. If you do X11() (or invoke it implicitly by using a 'plot' command) this will be device number 2. With just this one open, any 'plot' (or plot-related) commands will re-use it. However, having opened device #2, you can do X11() again and get a second graphics device which will be number 3. And so on, for as many additional devices as you like. By default, the device that the results of any 'plot' command are sent to will be the most recently opened one. However, you can select the device using the command dev.set(n) where n ( = 2,3,... ) is the device you want to use. The device which is active will be shown by the word (ACTIVE) attached to its display. All other devices will show (inactive). You could name your devices by indexing a vector (2:n) by names. Try the following, Starting with no graphics devices open: X11() # dev 2 X11() # dev 3 X11() # dev 4 ## This one is currently active That's the right idea, but I wouldn't count on the numbers coming out 2, 3, 4: what if another device was already opened? Better to use dev.cur() just after you open a new device to find out what its number was. So do something like X11() plotA - dev.cur() X11() plotB - dev.cur() X11() plotC - dev.cur() dev.set(plotA) # first one is active etc. Duncan Murdoch ## Arange these so that you can see all their top bars devN - c(plotA=2,plotB=3,plotC=4) dev.set(devN[plotA]) # dev 2 is active dev.set(devN[plotC]) # dev 4 is active dev.set(devN[plotB]) # dev 3 is active dev.set(devN[plotA]) # dev 2 is active dev.set(devN[plotC]) # dev 4 is active Hoping this helps, Ted. E-Mail: (Ted Harding) ted.hard...@manchester.ac.uk Fax-to-email: +44 (0)870 094 0861 Date: 25-Jul-10 Time: 15:03:14 -- XFMail -- __ 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] Optmatch
Hello , i want to work with the optmatch-package (http://cran.r-project.org/web/packages/optmatch/index.html).. Like many other packages , the information-window opens after the library()-command. How can i stop this? The Information-Window must not open a single time! How can i handle this problem? regards Nero -- View this message in context: http://r.789695.n4.nabble.com/Optmatch-tp2301676p2301676.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] Mask grid in R
Hi all, I want to cut a grid (Interpolation) with a Polygon in R, one knows how to do it... I hope I can help, as they always do. from now, thank you very much. Regards... Saludos Cordiales... Agustín Muñoz M. [[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] Left Outer Join 2 DF's on Multiple Conditions
Hi, I am trying to execute the following SQL statement using two data frames: tab1, tab2 : Two Tables Select tab1.*, tab2.*, tab1.tobiiTime - tab2.ruiTime as timeDiff, IFNULL(n-m, -999) as alwaysIncrement FROM tab1 LEFT OUTER JOIN tab2 On tab1.data1 - tab2.mouseX = 0 And tab1.data2 - tab2.mouseY = 0 I am trying to do the following in R:- *#Getting error here:* data - merge(tab1,tab2, all.x=TRUE, by=(data$data1 - data$mouseX == 0), by=(data$data2 - data$mouseY == 0)) data - cbind(data, data[, tobiiTime] - data[, ruiTime], data[, n] - data[, m]) #Change name of column tobiiTime-ruiTime to timeDiff, for convenience data - rename(data, c(tobiiTime-ruiTime=timeDiff)) #Change name of column n-m to alwaysIncrement, for convenience data - rename(data, c(n-m=alwaysIncrement)) *In the merge step, I want to include the following condition of merging:-* tab1.data1 - tab2.mouseX = 0 And tab1.data2 - tab2.mouseY = 0 Any ideas how this could be done. Thanks in advance. Regards, Harsh Yadav [[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] 3d topographic map
Hi All- I would like to create a 3d topographic map using lat/lon and z(height). I have been scouring the R help pages and have not located the package I am looking for. Does anyone have a suggestion of package that will work for this? thanks- sherri __ 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] 3d topographic map
On Jul 25, 2010, at 6:31 PM, sh...@ucar.edu wrote: Hi All- I would like to create a 3d topographic map using lat/lon and z(height). I have been scouring the R help pages and have not located the package I am looking for. Does anyone have a suggestion of package that will work for this? thanks- I suspect most viewers of this message are going to be puzzled. If wireframe and contourplot are not doing it for you, what are the problems? Surely you found references to Lattice and wireframe. The Lattice system has a worked example in Figure 6.11 from this page: http://lmdvr.r-forge.r-project.org/figures/figures.html A search for topographic in one of the r searching facilities is sure to bring multiple hits, . including the usual starting point: https://svn.r-project.org/R/trunk/src/library/graphics/demo/graphics.R So there must be details and issues that you have not chosen to disclose. -- David. __ 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] Left Outer Join 2 DF's on Multiple Conditions
Look at sqldf package, it is easier to do sql like statements with it. Nikhil Kaza Asst. Professor, City and Regional Planning University of North Carolina nikhil.l...@gmail.com On Jul 25, 2010, at 6:10 PM, harsh yadav wrote: Hi, I am trying to execute the following SQL statement using two data frames: tab1, tab2 : Two Tables Select tab1.*, tab2.*, tab1.tobiiTime - tab2.ruiTime as timeDiff, IFNULL(n-m, -999) as alwaysIncrement FROM tab1 LEFT OUTER JOIN tab2 On tab1.data1 - tab2.mouseX = 0 And tab1.data2 - tab2.mouseY = 0 I am trying to do the following in R:- *#Getting error here:* data - merge(tab1,tab2, all.x=TRUE, by=(data$data1 - data$mouseX == 0), by=(data$data2 - data$mouseY == 0)) data - cbind(data, data[, tobiiTime] - data[, ruiTime], data[, n] - data[, m]) #Change name of column tobiiTime-ruiTime to timeDiff, for convenience data - rename(data, c(tobiiTime-ruiTime=timeDiff)) #Change name of column n-m to alwaysIncrement, for convenience data - rename(data, c(n-m=alwaysIncrement)) *In the merge step, I want to include the following condition of merging:-* tab1.data1 - tab2.mouseX = 0 And tab1.data2 - tab2.mouseY = 0 Any ideas how this could be done. Thanks in advance. Regards, Harsh Yadav [[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] CRAN (and crantastic) updates this week
CRAN (and crantastic) updates this week New packages * evaluate (0.1) Hadley Wickham http://crantastic.org/packages/evaluate Parsing and evaluation tools that make it easy to recreate the command line behaviour of R. * multitaper (0.1-1) Karim Rahim http://crantastic.org/packages/multitaper * operator.tools (1.0.0) Christopher Brown http://crantastic.org/packages/operator-tools Utilities for working with R's operators * pglm (0.1-0) Yves Croissant http://crantastic.org/packages/pglm Estimation of panel models for glm-like models: this includes binomial models (logit and probit) count models (poisson and negbin) and ordered models (logit and probit) * rvgtest (0.5.0) Josef Leydold http://crantastic.org/packages/rvgtest Test suite for non-uniform pseudo-random number generators. * sigclust (1.0.0) Hanwen Huang http://crantastic.org/packages/sigclust SigClust is a statistical method for testing the significance of clustering results. SigClust can be applied to assess the statistical significance of splitting a data set into two clusters. For more than two clusters, SigClust can be used iteratively. * SII (1.0.0) Gregory R. Warnes http://crantastic.org/packages/SII This package calculates ANSI S3.5-1997 Speech Intelligibility Index (SII), a standard method for computing the intelligibility of speech from acoustical measurements of speech, noise, and hearing thresholds. This package includes data frames corresponding to Tables 1 - 4 in the ANSI standard as well as a function utilizing these tables and user-provided hearing threshold and noise level measurements to compute the SII score. The methods implemented here extend the standard computations to allow calculation of SII when the measured frequencies do not match those required by the standard by applying interpolation to obtain values for the required frequencies -- Development of this package was funded by the Center for Bioscience Education and Technology (CBET) of the Rochester Institute of Technology (RIT). * someMTP (1.0) Unknown http://crantastic.org/packages/someMTP It is a collection of functions for Multiplicty Correction and Multiple Testing. Updated packages actuar (1.1-1), AnalyzeFMRI (1.1-12), aqp (0.90), asbio (0.3-12), BAS (0.90), bibtex (0.2-1), bigtabulate (1.0.13), binGroup (1.0-6), caret (4.44), CHNOSZ (0.9-1), cmaes (1.0-9), COZIGAM (2.0-3), cxxPack (7.0.6), dcemriS4 (0.32), distrMod (2.2.2), DoseFinding (0.2-2), DOSim (1.2), dplR (1.3.6), dti (0.9-2.1), dynaTree (1.0-1), epiR (0.9-26), ergm (2.2-5), eVenn (1.21), FAMT (2.1), flashClust (1.00-2), forensim (1.1-7), GEOmap (1.5-8), gridExtra (0.6.5), hergm (1.2-6), hmm.discnp (0.1-3), hts (1.2), HWEintrinsic (1.1), JM (0.6-2), lqa (1.0-3), mclust (3.4.5), MCPMod (1.0-7), memisc (0.95-31), miniGUI (0.7.0), minqa (1.1.9), mixsmsn (0.2-5), mlogit (0.1-8), mokken (2.4), mondate (0.9.6), MplusAutomation (0.3-3), mra (2.6), np (0.40-3), ordinal (2010.07-06), pamctdp (0.1.5), pcaPP (1.8-2), pgirmess (1.4.7), phylobase (0.6.0), picante (1.2-0), plm (1.2-5), plspm (0.1-7), plyr (1.1), PolynomF (0.94), PowerTOST (0.6-2), psych (1.0-90), PtProcess (3.2-5), R.filesets (0.8.3), r4ss (1.07), raster (1.3-1), rattle (2.5.36), rbugs (0.4-4), Rcgmin (0.8), RFLPtools (1.3), rgdal (0.6-28), RMySQL (0.7-5), RpgSQL (0.1-3.1), rredis (1.4), RSEIS (2.4-1), RSQLite (0.9-2), Rvmmin (0.95), rwm (1.49), saws (0.9-3.3), SensoMineR (1.11), simPopulation (0.1.3), soil.spec (1.4), sp (0.9-66), sparr (0.2-1), spdep (0.5-16), spgrass6 (0.6-19), stratigraph (0.62), SV (1.3.0), TeachingSampling (1.7.9), tgp (2.3-4), traitr (0.9), TripleR (0.4), vegdata (0.1.8), x12 (0.0-7), xlsx (0.2.2), YieldCurve (3.0) This email provided as a service for the R community by http://crantastic.org. Like it? Hate it? Please let us know: crana...@gmail.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] Is there a function to interdigitate two columns?
Hello List Inhabitants: I don¹t know what this operation is called or if there is a function that does it automatically, hence I seek your help! If I divide a large data collection tasks between two students, and I have a master list of samples, but one student records some of the values, and the other student the remainder, I need to get the two sets of student measurements into one column. Here¹s an example: samp - LETTERS[1:10] # sample names student1 - c(NA, NA, 22, 34.3, NA, 10.5, 19.7, 20.22, NA, 12.9) student2 - c(25.5,29.4, NA, NA, 13.6, NA, NA, NA, 17.0, NA) merged - c(25.5,29.4, 22, 34.3, 13.6, 10.5, 19.7, 20.22, 17.0, 12.9) df1 - data.frame(samp, student1) df2 - data.frame(samp, student2) merge(df1, df2) # these don't quite do what I want join(df1, df2) # in latest release of plyr What I need is to take the two columns of student data and merge them into one that contains a single value for each sample, that is, I want to generate a 2-column data frame containing samp and merged as shown above I can write a function to do this (maybe not a great one) but I'd like to know if it already exists. Seems like it ought to be a common process, but as I'm not sure what it's called I'm having trouble searching. Thanks as always, Bryan * Bryan Hanson Acting Chair Professor of Chemistry Biochemistry DePauw University, Greencastle IN USA __ 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] Is there a function to interdigitate two columns?
result - data.frame(samp=samp, merged=ifelse(is.na(student2), student1, student2)) result samp merged 1 A 25.50 2 B 29.40 3 C 22.00 4 D 34.30 5 E 13.60 6 F 10.50 7 G 19.70 8 H 20.22 9 I 17.00 10J 12.90 Rich [[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] Loading Rdata files in a Package
I have an .Rdata file saved in my data folder in a package I created. However, when I use the data() function it doesn't recognize that there any dataset exists within the package. Is there anything specific I need to do such that the data() function will load my dataset? Thanks in advance, Andrew [[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] package for rank ordered logit
You may want to try a multinomial logit, mlogit{mlogit}. Hope this helps. On Fri, Jul 16, 2010 at 11:42 AM, Suresh Singh-2 [via R] ml-node+2291644-2038081369-246...@n4.nabble.comml-node%2b2291644-2038081369-246...@n4.nabble.com wrote: My understanding is that polr will do ordered logit but I am not sure if it is also suited for rank ordered logit (or is there no such distinction) I am thinking of following two situations 1. there is an ordered response (say small,medium,large coffee) and each individual selects one of these options. the order is predetermined i.e we know which one is small, medium or large and interested in knowing which option is selected. in this case each choice is independent because different individuals choose them 2. an individual ranks some or all the options (say three different types of coffee). We do not know apriori what the order is beforehand - these ranks are dependent because the same individual selects them I am calling the 1st situation - ordered logit and 2nd situation - rank ordered logit. Are these equivalent situations and is polr suited for both? Suresh On Fri, Jul 16, 2010 at 11:41 AM, Tal Galili [hidden email]http://user/SendEmail.jtp?type=nodenode=2291644i=0 wrote: Did you try: library(MASS) ?polr ? Contact Details:--- Contact me: [hidden email]http://user/SendEmail.jtp?type=nodenode=2291644i=1| 972-52-7275845 Read me: www.talgalili.com (Hebrew) | www.biostatistics.co.il (Hebrew) | www.r-statistics.com (English) -- On Fri, Jul 16, 2010 at 6:15 PM, Suresh Singh [hidden email]http://user/SendEmail.jtp?type=nodenode=2291644i=2 wrote: Is there a package in R that can run rank-ordered logit? Thanks, Suresh __ [hidden email] http://user/SendEmail.jtp?type=nodenode=2291644i=3mailing 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]] __ [hidden email] http://user/SendEmail.jtp?type=nodenode=2291644i=4mailing 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. -- View message @ http://r.789695.n4.nabble.com/package-for-rank-ordered-logit-tp2291526p2291644.html To unsubscribe from R, click here (link removed) ==. -- Department of Public Administration University of Kansas 4060 Wesco Hall Office W Lawrence KS 66045-3177 Phone: (785) 813-1384 Email: zachm...@gmail.com -- View this message in context: http://r.789695.n4.nabble.com/package-for-rank-ordered-logit-tp2291526p2301834.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] Loading Rdata files in a Package
On Sun, 25 Jul 2010, Andrew Leeser wrote: I have an .Rdata file saved in my data folder in a package I created. However, when I use the data() function it doesn't recognize that there any dataset exists within the package. Is there anything specific I need to do such that the data() function will load my dataset? No reproducible example was provided. Did you provide a name for the .Rdata file? e.g. mydat.RData Run example( package.skeleton ) then edit the 'mypkg' Rd files to put add dummy \title{} entries. Then INSTALL, then run R, library(mypkg) data(d) str(d) . . . Emulate what you see in mypkg/* Or use package.skeleton() to get you started. HTH, Chuck Thanks in advance, Andrew [[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. Charles C. Berry(858) 534-2098 Dept of Family/Preventive Medicine E mailto:cbe...@tajo.ucsd.edu UC San Diego http://famprevmed.ucsd.edu/faculty/cberry/ La Jolla, San Diego 92093-0901 __ 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] Marginal effects from interaction regression model
Dear all, I'd like to plot the marginal effect of a variable in a multiplicative interaction regression, that is, the effect of a variable conditional on the values of another variable. As an illustration, given model lm1 lm1 - lm(y ~ x*z) I'd like to get the effects of x on y conditional on the values of z, with the corresponding confidence intervals if possible. Does anyone know of any package or simple way to do this? Thanks -- View this message in context: http://r.789695.n4.nabble.com/Marginal-effects-from-interaction-regression-model-tp2301858p2301858.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] hatching posibility in Panel.Polygon
Hatching with lines can be done in polygon function using density and angle arguments. Is similar possibility of hatching polygons available when using panel.polygon while trying to plot in panels using lattice? Many thanks in advance for your help. HC -- View this message in context: http://r.789695.n4.nabble.com/hatching-posibility-in-Panel-Polygon-tp2301863p2301863.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Marginal effects from interaction regression model
On Jul 25, 2010, at 10:24 PM, Guillem R. wrote: Dear all, I'd like to plot the marginal effect of a variable in a multiplicative interaction regression, that is, the effect of a variable conditional on the values of another variable. As an illustration, given model lm1 lm1 - lm(y ~ x*z) ? predict Perhaps: predict(lm1, newdata=data.frame(x=1:10, z=5), interval=confidence) I'd like to get the effects of x on y conditional on the values of z, with the corresponding confidence intervals if possible. Does anyone know of any package or simple way to do this? Thanks -- David Winsemius, MD 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] Marginal effects from interaction regression model
As far as I know, the predict command gives the predicted values (and intervals) of y, but what I'm looking for is the conditional effects (betas) of x on y conditional on values of z. I'm trying to produce a plot similar to the first shown in this link: http://homepages.nyu.edu/~mrg217/interaction.html#code Thanks again David Winsemius wrote: On Jul 25, 2010, at 10:24 PM, Guillem R. wrote: Dear all, I'd like to plot the marginal effect of a variable in a multiplicative interaction regression, that is, the effect of a variable conditional on the values of another variable. As an illustration, given model lm1 lm1 - lm(y ~ x*z) ? predict Perhaps: predict(lm1, newdata=data.frame(x=1:10, z=5), interval=confidence) I'd like to get the effects of x on y conditional on the values of z, with the corresponding confidence intervals if possible. Does anyone know of any package or simple way to do this? Thanks -- David Winsemius, MD 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. -- View this message in context: http://r.789695.n4.nabble.com/Marginal-effects-from-interaction-regression-model-tp2301858p2301884.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] hatching posibility in Panel.Polygon
On Sun, Jul 25, 2010 at 7:40 PM, HC hca...@yahoo.co.in wrote: Hatching with lines can be done in polygon function using density and angle arguments. Is similar possibility of hatching polygons available when using panel.polygon while trying to plot in panels using lattice? No. -Deepayan __ 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] Specification Testing in Binary Choice Models
Hi, First of all I'm sorry if my question is repeated. I could not find an answer to it after searching the mail archive or the whole net. I have estimated a binary choice (probit, to be specific) model using 'glm' function in R, and now I want to perform some diagnostic tests, among which testing for heteroscedasticty is most important for my work. My question is if there are any packages/functions in R which can perform these tests for glm's. I know that we have the 'lmtest' package which includes several tests of specifications, but, as the lmtest package is for *l*inear *m*odels, I am not sure if its results are also valid for non-linear glm's. Specifically, functions that could perform Logit and Probit specification tests described in Davidson and McKinnon (1984) would be most helpful. Thank you, Amirreza [[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] data arranged by p-values
Id cat1locationitem_values p-valuessequence a1111 3002737 0.196504377 0.011 a1121 3017821 0.196504377 0.052 a1131 3027730 0.196504377 0.023 a1141 3036220 0.196504377 0.044 a1151 3053984 0.196504377 0.035 a1161 3063892 0.196504377 0.076 a1171 3076333 0.196504377 0.087 a1181 3090500 0.196504377 0.028 a1191 3103304 0.196504377 0.039 a1201 3119350 0.196504377 0.0510 a1211 3129884 0.196504377 0.0111 a1221 3154598 0.196504377 0.0312 a1231 3170910 0.196504377 0.0513 a1241 3180712 0.196504377 0.0614 a1251 3186519 0.196504377 0.0715 a1261 3192256 0.196504377 0.0916 a1271 3198441 0.196504377 0.0117 a1281 3205784 0.196504377 0.0218 a1291 3210685 0.196504377 0.0319 a1301 3218542 0.196504377 0.0420 a1311 3234318 0.196504377 0.0521 a1321 3239972 0.196504377 0.0922 a1331 3245663 0.196504377 0.0523 a1341 3257997 0.196504377 0.0224 a1351 3273226 0.196504377 0.0326 a1361 3285404 0.196504377 0.0427 a1371 3290332 0.196504377 0.0528 a1381 3300679 0.196504377 0.0329 a1391 3310164 0.196504377 0.0930 first of all, please pay attention to the P -values, all the rows with the p-value 0.05 will be considered as one region until the p-value 0.05 identified. for instance: REGION 1 is the rows from id a111 to id A115 . REGION 2 is the rows from id a118 to a123, etc. what i am going to accomplish is to pick the start and end location, and the peak value from the item_values for each region. option 1: loop through each row until the p-value0.05 identified then start_location=the first location value end_location=the location value before the p0.05 peak_value of the item_values=the maximum one option 2 create a sequence number for each row; subset the raw dataframe by p0.05; the p-value regions will be identified by the gapped sequence number. for instance from sequence 1 to 5 will be considering one region. Id cat1locationitem_values p-valuessequence a1111 3002737 0.196504377 0.011 a1121 3017821 0.196504377 0.052 a1131 3027730 0.196504377 0.023 a1141 3036220 0.196504377 0.044 a1151 3053984 0.196504377 0.035 a1181 3090500 0.196504377 0.028 a1191 3103304 0.196504377 0.039 I need your recommendation on the different approach to implement this? Thanks, -- View this message in context: http://r.789695.n4.nabble.com/data-arranged-by-p-values-tp2301909p2301909.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] p-values calculation
Id cat1locationitem_values p-valuessequence a1111 3002737 0.196504377 0.011 a1121 3017821 0.196504377 0.052 a1131 3027730 0.196504377 0.023 a1141 3036220 0.196504377 0.044 a1151 3053984 0.196504377 0.035 a1161 3063892 0.196504377 0.076 a1171 3076333 0.196504377 0.087 a1181 3090500 0.196504377 0.028 a1191 3103304 0.196504377 0.039 a1201 3119350 0.196504377 0.0510 a1211 3129884 0.196504377 0.0111 a1221 3154598 0.196504377 0.0312 a1231 3170910 0.196504377 0.0513 a1241 3180712 0.196504377 0.0614 a1251 3186519 0.196504377 0.0715 a1261 3192256 0.196504377 0.0916 a1271 3198441 0.196504377 0.0117 a1281 3205784 0.196504377 0.0218 a1291 3210685 0.196504377 0.0319 a1301 3218542 0.196504377 0.0420 a1311 3234318 0.196504377 0.0521 a1321 3239972 0.196504377 0.0922 a1331 3245663 0.196504377 0.0523 a1341 3257997 0.196504377 0.0224 a1351 3273226 0.196504377 0.0326 a1361 3285404 0.196504377 0.0427 a1371 3290332 0.196504377 0.0528 a1381 3300679 0.196504377 0.0329 a1391 3310164 0.196504377 0.0930 I would like to calculate the p values for the item_values above. option 1: z score based wData - within(wData, { + z - (values - mean(values))/sd(values) + p-value - 2*pnorm(-abs(z)) ## 2-sided + rm(z) }) wData option 2: t distibution based p_value-2*pt(-abs(t),df=n-1) my questions: what R function can assist the distribution analysis to the item_values column above? for instance: normal distribution analysis? how to calculate the p values if the distribution of the item_values is no-parameter distribution? -- View this message in context: http://r.789695.n4.nabble.com/p-values-calculation-tp2301917p2301917.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Loading Rdata files in a Package
From ?data 2. files ending ‘.RData’ or ‘.rda’ are ‘load()’ed. '.Rdata' (l/c 'd') files are not supported (although on case-insensitive file systems they will work in _some_ circumstances, but only some. Without the sessionInfo() output we asked for in the posting guide, we can only guess if this such a file system.). On Sun, 25 Jul 2010, Charles C. Berry wrote: On Sun, 25 Jul 2010, Andrew Leeser wrote: I have an .Rdata file saved in my data folder in a package I created. However, when I use the data() function it doesn't recognize that there any dataset exists within the package. Is there anything specific I need to do such that the data() function will load my dataset? No reproducible example was provided. Did you provide a name for the .Rdata file? e.g. mydat.RData Run example( package.skeleton ) then edit the 'mypkg' Rd files to put add dummy \title{} entries. Then INSTALL, then run R, library(mypkg) data(d) str(d) . . . Emulate what you see in mypkg/* Or use package.skeleton() to get you started. HTH, Chuck Thanks in advance, Andrew Charles C. Berry(858) 534-2098 Dept of Family/Preventive Medicine E mailto:cbe...@tajo.ucsd.edu UC San Diego http://famprevmed.ucsd.edu/faculty/cberry/ La Jolla, San Diego 92093-0901 -- 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] NULL
hi, I have a simple problem. how can I test whether a variable is NULL? a = NULL if (a == NULL){ ... } it seems not work thanks YU [[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] NULL
Tena koe Yu ?is.null HTH ... Peter Alspach -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r- project.org] On Behalf Of Yuan Jian Sent: Monday, 26 July 2010 5:05 p.m. To: r-help@r-project.org Subject: [R] NULL hi, I have a simple problem. how can I test whether a variable is NULL? a = NULL if (a == NULL){ ... } it seems not work thanks YU [[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.