GENEALOGY-DNA-L Archives

Archiver > GENEALOGY-DNA > 2003-03 > 1047090164


From: Roy Hutchinson <>
Subject: RE: [DNA] Probability question
Date: Fri, 07 Mar 2003 20:22:44 -0600
In-Reply-To: <2449F3F867FBD211936600C04F68569E029CBC6A@SMHRIMSX>


Maybe we can put the two together and go from a door to a hallway.

If on the graph of MRCA as the generations get higher the probability approaches
99.9%.

So, for the first generation, the probability is say .01%, 2nd .05% .... And the
7th 48%. Since as Ann suggests the first half would still have to add up to 50%.

Your thoughts?
Roy

-----Original Message-----
From: Bonner, Gregg [mailto:]
Sent: Friday, March 07, 2003 8:02 PM
To:
Subject: RE: [DNA] Probability question


I don't believe this can be the case. I think the assumption is in error on at
least two counts, but I will just note that the principle factor is that the
probability works at the "group level" and has little significance on his
particular case.

If you were to believe this to be a generalizable state, then to say you could
exclude generations 6 onwards would leave you to have a 50% chance of relation
in the FIRST generation. This is not the case.

The case is rather more like dice I think. What is your chance of rolling a "6"
twice in a row? How does your probability of rolling a "6" change if someone can
make it impossible for a 3, 4, or 5 to come up on the NEXT roll? The first roll
is still the same, at it needn't make the two try-two outcome model fit overall
for the single particular case.

I realize this isn't dice, but I think it is not a door either.

Cheers,

Gregg


> -----Original Message-----
> From: [mailto:]
> Sent: 07 March, 2003 6:24 PM
> To:
> Subject: Re: [DNA] Probability question
>
>
> In a message dated 03/07/03 1:35:17 PM Pacific Standard Time,
> writes:
>
> > If I have a 50% probability of being related to another
> person within 7
> > generations. And we know for certain that our MRCA can not
> possibly be
> > within
> > the first four generations. So those generations are
> eliminated from the
> > scope.
> > Then is the probability of being related in the remaining 3
> generations
> > increased? If so, by how much?
>
> I'm almost afraid to tackle this one, as it reminds me of the
> infamous
> Marilyn Vos Savant "Three Doors" problem. (I didn't get that
> right at first,
> but I ended up believing her solution. Those of you who don't
> recall it can
> Google on those words.) But here goes: the probabilities must
> always add up
> to one. The chances of being related more than 7 generations
> ago are 50%.
> That is still the case, so the probability of being related
> in generations 5,
> 6 or 7 is now 50%.
>
> Ann Turner - GENEALOGY-DNA List Administrator
> Search or Browse the archives, Subscribe or Unsubscribe at
> >http://lists.rootsweb.com/index/other/Miscellaneous/GENEALOGY
-DNA.html
DNA preservation kits: http://www.dnafiler.com


==============================
To join Ancestry.com and access our 1.2 billion online genealogy records, go
to: http://www.ancestry.com/rd/redir.asp?targetid=571&sourceid=1237


==============================
To join Ancestry.com and access our 1.2 billion online genealogy records, go to:
http://www.ancestry.com/rd/redir.asp?targetid=571&sourceid=1237




This thread: