Talk:Independent and identically-distributed random variables

From a practical point of view, an important implication of this is that if the roulette ball lands on 'red', for example, 20 times in a row, the next spin is no more or less likely to be 'black' than on any other spin.

I disagree with the above statement. The sequence is IID by definition, so it does not matter whether or not the previous 20 rolls resulted in red. —Preceding unsigned comment added by 199.43.48.131 (talk • contribs)


 * So what do you disagree with? You say it doesn't matter; the statement you say you disagree with also says it doesn't matter. Michael Hardy 22:50, 29 October 2007 (UTC)


 * The uninlogged IP 199.43.48.131 has been blocked for vandalism a number of times, and has not been able to explain their criticism to this page in a sensible manner. I therefore remove the  tag put on the page by said IP.-JoergenB (talk) 14:03, 19 January 2008 (UTC)

<< central limit theorem, which states that the probability distribution of the sum (or average) of i.i.d. variables with finite variance approaches a normal distribution, becoming acceptably close when sample size n \geq 30. >>

What is n? If it's the number of variables added, this statement is obviously false in general: just take a very heavy-tailed distribution. It might be true if you restrict it to uniform distributions, though. Guslacerda (talk) 05:35, 18 February 2008 (UTC)
 * Better?-JoergenB (talk) 02:43, 19 February 2008 (UTC)