Re: Coin flipping

daniel_nordlund_1982@xxxxxxxxxxx wrote:
I have flipped a coin 1000 times and written down the results (heads or
tails for each flip).

Oh, your poor thumb.

Now, I'm being told that at one point, and for an
unknown number of flips, the coin was switched from an unbiased to a
biased one (let's say resulting in 67% tails instead of 50%). For
example, maybe flips 725 to 780 were with the biased coin, and all
other with the unbiased. Since I don't know this, I wish to find which
range is the most probable to be biased given the list of flips. How
can I do this?

Oh, it was hypothetical!

There are change-point models you could try, but you could probably get a pretty good idea by using a GAM (generalised additive model) to smooth the probability of a head (i.e. you plot H or T against the run number, and smooth that). Depending on what you're doing, that might be enough.

If you don't want to go into GAMs, then plot a moving average, and look for the change (actually, the MA is GAM as well).

Bob

--
Bob O'Hara

Dept. of Mathematics and Statistics
P.O. Box 68 (Gustaf Hällströmin katu 2b)
FIN-00014 University of Helsinki
Finland

Telephone: +358-9-191 51479
Mobile: +358 50 599 0540
Fax: +358-9-191 51400
WWW: http://www.RNI.Helsinki.FI/~boh/
Journal of Negative Results - EEB: http://www.jnr-eeb.org
.

Relevant Pages

  • Re: Coin flipping
    ... Oh, your poor thumb. ... biased one (let's say resulting in 67% tails instead of 50%). ... range is the most probable to be biased given the list of flips. ... the MA is GAM as well). ...
    (sci.stat.math)
  • Re: The Philosophy of War
    ... might be where the conclusion is: "the nature of the philosophy of war ... In a set of flips of a fair coin (defined as heads and tails each having ...
    (rec.martial-arts)
  • Re: Casus Belli
    ... In a set of flips of a fair coin (defined as heads and tails each having ... equal chances of coming up with an exactly 0 chance of any other ...
    (rec.martial-arts)
  • Re: Martial law comes to New Orleans.
    ... Two flips, four possible combinations ... 50% of the outcomes are 1 head, ... 37.5% of the outcomes are 2 heads, 2 tails. ...
    (rec.martial-arts)
  • Re: marginal expectation
    ... back and forth neither heads nor tails more than 2 ahead or behind. ... tails receives a fortunate 3rd std. ... So we stay heads up for some time but after a couple hundred flips ...
    (sci.math)