[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
## Re: [Help-gsl] Re: Random number generation

**From**: |
Carl Boettiger |

**Subject**: |
Re: [Help-gsl] Re: Random number generation |

**Date**: |
Tue, 5 May 2009 17:43:17 -0700 |

The number shouldn't be close to zero. Divide by 600 and you'll have
the mean, which will be close to zero. Just sum a bunch of gaussian
random numbers of standard deviation sigma and you expect a
displacement of sqrt(2 sigma T), i.e. sqrt(1200) approx 34 -- you're
simulating Brownian motion.
-Carl
On Tue, May 5, 2009 at 2:10 PM, Rodney Sparapani <address@hidden> wrote:
>* Vibhuti Dave wrote:*
>*>*
>*> Hello,*
>*>*
>*> I have attached the code that I am using to generate random numbers that*
>*> have a Gaussian distribution with a mean value of 0.*
>*> Ideally, if I generate these numbers and sum them up, the sum should be*
>*> very*
>*> close to 0 since it is a gaussian ditribution. I am using the function*
>*> gsl_ran_gaussian to generate them. However, the mean value seems to be way*
>*> off 0 when I run the program.*
>*> Any idea why that might be happening?*
>*> Thanks*
>*> Vibhuti*
>
>* What happens if you set mu = 0.?*
>
>
>
>* _______________________________________________*
>* Help-gsl mailing list*
>* address@hidden*
>* http://lists.gnu.org/mailman/listinfo/help-gsl*
>
--
Carl Boettiger
Population Biology, UC Davis
http://two.ucdavis.edu/~cboettig