# An extreme quantile of the geometric distribution

4 messages
Open this post in threaded view
|
Report Content as Inappropriate

## An extreme quantile of the geometric distribution

 Hi,  With R version 2.10.0 (2009-10-26) on Windows, I computed the p=1.e-20  quantile of the geometric distribution with parameter prob=0.1. > qgeom(1.e-20,0.1)  [1] -1  But this is not possible, since X=0,1,2,...  I guess that this might be a bug in the quantile function, which should  use the log1p function, instead of the naive formula.  Am I correct ?  Best regards,  Michaël ______________________________________________ [hidden email] mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
Open this post in threaded view
|
Report Content as Inappropriate

## Re: An extreme quantile of the geometric distribution

 On Jun 28, 2012, at 22:49 , <[hidden email]> <[hidden email]> wrote: > Hi, > > With R version 2.10.0 (2009-10-26) on Windows, I computed the p=1.e-20 quantile of the geometric distribution with parameter prob=0.1. > >> qgeom(1.e-20,0.1) > [1] -1 > > But this is not possible, since X=0,1,2,... > > I guess that this might be a bug in the quantile function, which should use the log1p function, instead of the naive formula. > > Am I correct ? Nope. (The source is availably, you know....). The problem is that a slight fuzz is subtracted inside ceil(....), but there's no check that the result is positive. qnbinom(...., size=1) is equivalent and does get right, by the way.   -pd > > Best regards, > > Michaël > > ______________________________________________ > [hidden email] mailing list > https://stat.ethz.ch/mailman/listinfo/r-devel-- Peter Dalgaard, Professor, Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: [hidden email]  Priv: [hidden email] ______________________________________________ [hidden email] mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
Open this post in threaded view
|
Report Content as Inappropriate

## Re: An extreme quantile of the geometric distribution

 Hi,  I'm sorry, I do not clearly understand.  I'm aware that the source is available at :  http://svn.r-project.org/R/trunk/src/nmath/qgeom.c But a good source does not mean a correct result, because of  compilation issues. Moreover, I do not fully understand why the 1e-7  coefficient in the formula was put there. The comment "add a fuzz to  ensure left continuity" is not obvious to me.  Best regards,  Michaël  On Fri, 29 Jun 2012 14:21:50 +0200, peter dalgaard <[hidden email]>  wrote: > On Jun 28, 2012, at 22:49 , <[hidden email]> > <[hidden email]> wrote: > >> Hi, >> >> With R version 2.10.0 (2009-10-26) on Windows, I computed the >> p=1.e-20 quantile of the geometric distribution with parameter >> prob=0.1. >> >>> qgeom(1.e-20,0.1) >> [1] -1 >> >> But this is not possible, since X=0,1,2,... >> >> I guess that this might be a bug in the quantile function, which >> should use the log1p function, instead of the naive formula. >> >> Am I correct ? > > Nope. (The source is availably, you know....). > > The problem is that a slight fuzz is subtracted inside ceil(....), > but there's no check that the result is positive. > > qnbinom(...., size=1) is equivalent and does get right, by the way. > > -pd > >> >> Best regards, >> >> Michaël >> >> ______________________________________________ >> [hidden email] mailing list >> https://stat.ethz.ch/mailman/listinfo/r-devel______________________________________________ [hidden email] mailing list https://stat.ethz.ch/mailman/listinfo/r-devel