MLE for Beta distribution?

Article View: cmu.ece.general

Article #491

#491

From: Charles Robert Yount
Date: Thu, 11 Mar 1993 19:29

14 lines
1321 bytes

I have 90 data points which I think follow a beta distribution, i.e.,
they are in the range [0..1], and the distribution has a nice hump
centered around 0.97.  Can someone point me to a way to calculate the
maximum likelihood estimators for the two shape parameters?  I derived
a pair of functions with two digamma functions each, but I'm not sure
what to do then.

Also, I need to test the hypothesis that it really is from a beta.
Should I find the MLEs first, or is there a better way?  Or is this a
chicken-and-egg problem?

Thanks,
Chuck Yount

Technical Details

Message-ID: <YOUNT.93Mar11142943@fox.ece.cmu.edu>

Path:

arc1-ca.pugleaf.net!sparky!uunet!destroyer!caen!zaphod.mps.ohio-state.edu!pacific.mps.ohio-state.edu!cis.ohio-state.edu!news.sei.cmu.edu!fs7.ece.cmu.edu!fs7!yount

Show Full Headers

Complete Article Headers

X-Google-Language: ENGLISH,ASCII-7-bit
X-Google-Thread: fa720,848e1d446410532,start
X-Google-Attributes: gidfa720,public
X-Google-Thread: f8fde,848e1d446410532,start
X-Google-Attributes: gidf8fde,public
X-Google-ArrivalTime: 1993-03-11 12:21:12 PST
Newsgroups: cmu.ece.general,sci.math.stat
Path: arc1-ca.pugleaf.net!sparky!uunet!destroyer!caen!zaphod.mps.ohio-state.edu!pacific.mps.ohio-state.edu!cis.ohio-state.edu!news.sei.cmu.edu!fs7.ece.cmu.edu!fs7!yount
From: yount@fox.ece.cmu.edu (Charles Robert Yount)
Subject: MLE for Beta distribution?
Message-ID: <YOUNT.93Mar11142943@fox.ece.cmu.edu>
Sender: news@fs7.ece.cmu.edu (USENET News System)
Organization: Electrical and Computer Engineering, Carnegie Mellon
Date: Thu, 11 Mar 1993 19:29:43 GMT
Lines: 14