Teaching an intelligent guy about a basic statistics concept

[chezlaw]

Its not really about statistics. Does your friend believe the coin or the universe keeps track of past results in a way that influences future results?

If he doesn't then he must immediately realise that he must be wrong. If he does believe the above then only experiments can hope to persuade him otherwise.

I'd guess his just confused about regressing to the mean. Pointing out to him that that doesn't mean 'making up' for the past but just means that the long term swamps the short term.

chez