Fitting a geometric distribution
in [Matlab]
|
From: Erik on 10 Apr 2010 22:24 Hi, I have some data that looks like it follows a geometric distribution. I am attempting to best estimate the parameter, p, of the distribution but there doesn't appear to be any matlab command that does this directly; I would have thought it would be under geofit or something, but no such function exists. This is easy with the poisson distribution, where I can just use the command poissfit(X) to get the best estimate of lambda for my data X. Is there a command that best estimates the parameter of a geometric distribution given the data? Thanks
From: Frederic Moisy on 11 Apr 2010 19:14 Hi, you can use the Ezyfit toolbox: http://www.mathworks.com/matlabcentral/fileexchange/10176 The geometric distribution can be fitted using the function showfit('(1-p)^x*p; p=0.5'); or f = ezfit('(1-p)^x*p; p=0.5'); I hope this helps, Fred "Erik" <emiehling(a)gmail.com> wrote in message <hprbs8$5qf$1(a)fred.mathworks.com>... > Hi, > > I have some data that looks like it follows a geometric distribution. I am attempting to best estimate the parameter, p, of the distribution but there doesn't appear to be any matlab command that does this directly; I would have thought it would be under geofit or something, but no such function exists. This is easy with the poisson distribution, where I can just use the command poissfit(X) to get the best estimate of lambda for my data X. > > Is there a command that best estimates the parameter of a geometric distribution given the data? > > Thanks
|
Pages: 1 Prev: Simple concept eye tracking HELP! Next: request for Matlab coding |