GENEALOGY-DNA-L Archives

Archiver > GENEALOGY-DNA > 2007-07 > 1183945758

From: "Eric Olson" <>
Subject: Re: [DNA] General Probability Question
Date: Sun, 8 Jul 2007 18:49:18 -0700

And thus independent of population size... Cool...

Eric

> [Original Message]
> From: < (John Chandler)>
> To: <>
> Date: 7/8/2007 12:50:37 PM
> Subject: Re: [DNA] General Probability Question
>
> Eric wrote:
> > What are the chances these are the same person? I find that surname
> > Carroll runs at about 1/5000 of surnames in America. The two exact
> > birth dates seems compelling, but is there a formal way to calculate
> > the probability they are the same person?
>
> You can make a start by assuming that the frequency of the forename
> Margaret is (or was) independent of surname and birthday. I couldn't
> say offhand when the feast of St. Margaret is, but if it isn't Aug 20,
> then the assumption is pretty reasonable. So, just multiply 1/5000
> by 1/25000 (the reciprocal mean lifetime in inverse days) and 1/200
> (or whatever you think the frequency of Margaret was), and you get
> 1/25,000,000,000 as the probability that a randomly chosen person
> would have that combination of forename, surname, and birth date.
> Then, just multiply by the number of data records you scanned to find
> the obituary in question (counting all records, not just obituaries),
> and you'll have an estimate of the probability of finding such a
> coincidence by chance.
>
> John Chandler
>
> -------------------------------
> To unsubscribe from the list, please send an email to
with the word 'unsubscribe' without the
quotes in the subject and the body of the message