Re: [Rd] apparently incorrect p-values from 2-sided Kolmogorov-Smirnov (PR#14178)
Dear Thomas, Thank you, yes, that sounds good, and I take the point about integer overflow. Various questions: (a) Is there some way I can try out the routine with this modification? (I am on a Linux system where I am just a user - I cannot install new versions of software myself) ? (b) Is there a reference you can give me to a published paper where the method being used to compute the p-values is described? Many thanks, David. -- On Fri, 18 Dec 2009, tlum...@u.washington.edu wrote: > > > I've fixed this by adding 0.5/mn to q. The problem (at least in principle) > with multiplying them all up is integer overflow. > > By the time 0.5/mn underflows to zero, missing one value in the distribution > won't matter. > > -thomas > > > On Fri, 18 Dec 2009, David John Allwright wrote: > >> Dear Thomas, Right, thank you. Yes, I haven't looked at the source code >> (because I don't know C) but something like what you mention could well >> cause the kind of problems I am seeing: a loop being exectued one too few >> or one too many times. And yes, I think those quantities should be >> multiplied up by m*n to all become integers so we escape rounding error >> problems. David. >> >> -- >> On Wed, 16 Dec 2009, tlum...@u.washington.edu wrote: >> >>> On Tue, 15 Dec 2009, allwr...@maths.ox.ac.uk wrote; (in part) >>> x<-1:5 y<-c(2.5,4.5) ks.test(x,y) The value of the D_2,5 statistic is calculated as 0.4 correctly, but the p-value is stated by R as 1, though in fact it should be 20/21=0.9524 >>> >>> >>> What we seem to have here is a rounding error problem. >>> >>> In ks.c:psmirnov2x, there is a double loop including >>> if(fabs(i / md - j / nd) > q) >>> u[j] = 0; >>> >>> where md=2, nd=5, and q=3/10. >>> >>> Now, to full precision abs(1/2 - 4/5) > 3/10 is false, but at least on >>> my MacBook it is true in C double precision. >>> >>> I'm not sure why the loop is working with doubles, since multiplying by >>> m*n should make everything an integer. >>> >>> -thomas >>> >>> Thomas Lumley Assoc. Professor, Biostatistics >>> tlum...@u.washington.eduUniversity of Washington, Seattle >>> >>> >>> >> > > Thomas Lumley Assoc. Professor, Biostatistics > tlum...@u.washington.edu University of Washington, Seattle > > > __ R-devel@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
Re: [Rd] apparently incorrect p-values from 2-sided Kolmogorov-Smirnov test (PR#14145)
Dear Thomas, Thank you, yes, that sounds good, and I take the point about integer overflow. Various questions: (a) Is there some way I can try out the routine with this modification? (I am on a Linux system where I am just a user - I cannot install new versions of software myself) ? (b) Is there a reference you can give me to a published paper where the method being used to compute the p-values is described? Many thanks, David. -- On Fri, 18 Dec 2009, tlum...@u.washington.edu wrote: I've fixed this by adding 0.5/mn to q. The problem (at least in principle) with multiplying them all up is integer overflow. By the time 0.5/mn underflows to zero, missing one value in the distribution won't matter. -thomas On Fri, 18 Dec 2009, David John Allwright wrote: Dear Thomas, Right, thank you. Yes, I haven't looked at the source code (because I don't know C) but something like what you mention could well cause the kind of problems I am seeing: a loop being exectued one too few or one too many times. And yes, I think those quantities should be multiplied up by m*n to all become integers so we escape rounding error problems. David. -- On Wed, 16 Dec 2009, tlum...@u.washington.edu wrote: On Tue, 15 Dec 2009, allwr...@maths.ox.ac.uk wrote; (in part) x<-1:5 y<-c(2.5,4.5) ks.test(x,y) The value of the D_2,5 statistic is calculated as 0.4 correctly, but the p-value is stated by R as 1, though in fact it should be 20/21=0.9524 What we seem to have here is a rounding error problem. In ks.c:psmirnov2x, there is a double loop including if(fabs(i / md - j / nd) > q) u[j] = 0; where md=2, nd=5, and q=3/10. Now, to full precision abs(1/2 - 4/5) > 3/10 is false, but at least on my MacBook it is true in C double precision. I'm not sure why the loop is working with doubles, since multiplying by m*n should make everything an integer. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-devel@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
[Rd] "Human-style" sort() of alphanum strings?
I know it is fairly easy to implement (though not always well defined), but is there an existing sort function out there that takes alphanum strings and sort them in a "human" fashion? For example, instead of: z1.doc z10.doc z100.doc z101.doc z11.doc z2.doc it should out put: z1.doc z2.doc z10.doc z11.doc z100.doc z101.doc (from http://www.davekoelle.com/alphanum.html). /Henrik __ R-devel@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
Re: [Rd] "Human-style" sort() of alphanum strings?
See mixedsort in gtools. Also on http://gsubfn.googlecode.com see mixsort example in the section starting ### more examples On Tue, Jan 5, 2010 at 6:34 PM, Henrik Bengtsson wrote: > I know it is fairly easy to implement (though not always well > defined), but is there an existing sort function out there that takes > alphanum strings and sort them in a "human" fashion? For example, > instead of: > > z1.doc z10.doc z100.doc z101.doc z11.doc z2.doc > > it should out put: > > z1.doc z2.doc z10.doc z11.doc z100.doc z101.doc > > (from http://www.davekoelle.com/alphanum.html). > > /Henrik > > __ > R-devel@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-devel > __ R-devel@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
[Rd] the source code and tool-chain for R64-win64 uploaded
I uploaded the whole R 64 for win64 using MINGW64, include the source code, bin and tool-chain. the source code and bin can download at: http://download.cos.name/incoming/r64-src-and-bin-for-win64.zip (attention: the source code may be contain error,you are welcome report bugs to me) the tool-chain can download at: http://download.cos.name/incoming/Rtools64.zip (attention: the gcc included in the tool-chain is a native gcc 4.5.0 for win64(20091231), I download from http://www.equation.com/servlet/equation.cmd?fa=fortran and I think it's free and GPLed,so we can use it,and if you have any question about gcc ,pls write a mail to the webmaster of equation.com ) best wishs. Gong Yu 2010/1/6 __ R-devel@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
