Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
NCTM or The Math Forum.


Math Forum
»
Discussions
»
sci.math.*
»
sci.stat.math
Notice: We are no longer accepting new posts, but the forums will continue to be readable.
Topic:
527 heads out of 1,000 coin flips redux...
Replies:
9
Last Post:
Jul 2, 2012 4:59 PM



Douglas 73
Posts:
52
From:
Pacific northwest, USA
Registered:
1/15/11


527 heads out of 1,000 coin flips redux...
Posted:
Jun 26, 2012 6:42 PM


Referencing:
http://www.nytimes.com/2011/01/11/science/11esp.html
My apologies for taking so long to answer to this subject, but I plead to being old, slow thinking, and generally thorough.
Lately I have succeeded in creating a number of basic standard probability scales as usually defined: more than zero, through to, and including, 1. When I took Stat 101, someone forgot to tell me that these are merely midpoint interval scales for all points except for the 1.
I have always taken an answer like 527 heads resulting from 1,000 coin tosses as an actual 0.043852515 onetail probability occurrence in the infinite scheme of the universe. It turns out this probability amount is merely a midpoint scale amount. The actual comparable onetail probability of 527 heads occurring is 0.005874295. This is a difference of almost 7 1/2 times. May I be allowed to call this a significant difference?
Now this is mostly statistics talk so far. I think us ordinary humans would better understand these results in the form of odds against. In this example, the generally accepted scale amount translates to almost 22:1 odds against being by mere chance. Since I am an ordinary human, I take that as being pretty chancy, but maybe possible. I think I would ask for the coin flips to be repeated to see what happens for the next 1,000.
But the actual odds are 169:1. You have little chance convincing me these 527 heads are an actual fair result.
Douglas



