Monday, 5 January 2015

Streaky coin tosses

In the previous post we looked at how the data distribution gets closer to the real probability as the number of samples increase.   And we showed this happened in our excel generated random coin tosses.   What we didn't look at was how streaky the coin tosses were?

A streak is considered as the same coin toss in a row i.e. Heads, Heads, Heads, Heads.   Would be a streak of 4 heads.

So what happened in our 20,000 coin tosses?



As we can see above, we get lots of long streaks.   Actually we get 14 tosses of the same side in a row.    That's quite a streak.   

And that curve looks quite appropriate.  It's a binomial distribution and one that looks like it should for a 50/50 probability.

At another time, we'll discuss binomial distributions and the probability of coin tosses.   But for now, lets just say, a streak of 14 is quite normal.   :)

Loss Recovery betting plans aren't looking so good now.

Do we really wanna talk about Martingale / loss recovery betting patterns?   Really?  Ummm ok, we can.   Are you sure you're expecting a black just because the last color was a red?   Are you sure you're owed a black.   Are you sure 10 reds in a row is unusual?  Looks pretty normal to me.


5 comments:

  1. So for the little less knowledgeable, why is 10 in a row enough to count Martingale out of plausible?

    ReplyDelete
  2. Because for £10 initial stakes, you're gonna need over £5,000 to win that back. Have a look at this post
    http://gamblingmath.blogspot.co.uk/2015/01/why-playing-red-or-black-in-roulette.html

    ReplyDelete
  3. probability of observing 10, 11, 12 ,13, 14 in a row is determined by how often you observe. If you don't watch very often the probability is quite low. If you use bet recovery (chase your bet) seldom and only when the starting position is deep into the streak say 5 blacks in a row, then you start chasing your bet placed within a table limit which allows you to attempt recovery eight times, 5+8=13.
    You probably will always recover your bet, because the distribution of wagers is very small. Perhaps six wagers in a busy casino over six hours. No one likes to gamble like this, but it does increase the probability of winning dramatically.

    ReplyDelete
  4. This is my first time i visit here. I found so many interesting stuff in your blog especially its discussion. From the tons of comments on your articles, I guess I am not the only one having all the enjoyment here! keep up the good work Continue Read more

    ReplyDelete