Re: WeibullDistribution
- To: mathgroup at smc.vnet.net
- Subject: [mg42449] Re: WeibullDistribution
- From: bobhanlon at aol.com (Bob Hanlon)
- Date: Wed, 9 Jul 2003 08:24:25 -0400 (EDT)
- References: <bee0f9$fhd$1@smc.vnet.net>
- Sender: owner-wri-mathgroup at wolfram.com
Needs["Statistics`ContinuousDistributions`"];
data=RandomArray[WeibullDistribution[5, 2],{100}];
To get an initial estimate of the parameters
est = FindRoot[{
Mean[WeibullDistribution[a, b]]==Mean[data],
Variance[WeibullDistribution[a, b]]==Variance[data]},
{a,1},{b,1}]
{a -> 4.882178679882784, b -> 1.9493985547665071}
You want to maximize the log likelihood function given by
llf = Simplify[Plus @@ (Log[PDF[WeibullDistribution[a,b],#]]& /@ data)];
The MLE estimates of the parameters are then
FindRoot[Evaluate[{D[llf,a]==0,D[llf,b]==0}],
{a,est[[1,2]]}, {b, est[[2,2]]}]
{a -> 4.923904837274986, b -> 1.9483453144994602}
Bob Hanlon
In article <bee0f9$fhd$1 at smc.vnet.net>, ce.choa.phen.kee at philips.com wrote:
<< I have a set of data, but how can I find out the A and B in
WeibullDistribution[ A , B ] ?
There isn't much informaion regarding the WeibullDistribution provided in
the Help Browser. Anyone pls help???