Comment Re:Don't Count Your Chickens (Score 1) 372
Hi, statistician here. That's not what "regression to the mean" is.
Regression to the mean applies when you have a pair of comparable measurements, the first one of which is high (or low) when compared to similar quantities. So a father and sons' heights, for example. High measurements tend to be a combination of nature + luck. Looking at the other of the pair, the luck component isn't likely to be as good, so on average you're left with just nature. Hence, really big regresses back to big.
You are, however, likely correct that the hype is what is at play. Or that there was pent up demand. Or that people love sales. Or whatever. Kind of hard to imagine a good experiment on introducing Steam to Linux over and over again that we could analyze.