Not a statistician, but I don't believe this is true. You need ~1000 individuals to find statistically significant phenomena in a population the size of the U.S.. Since the population of rich people is so much smaller, you'd need a smaller number of individuals to draw statistical inferences from it.
Anyone know the actual formula for statistical significance, and able to work out how big a sample needs to be for, say, a population of 100k?
Not trying to be harsh, but you apparently haven't been taught this key idea about statistical significance: degree of confidence depends only on the size of the sample and the sample selection mechanism, not the size of the total population. This is a really unintuitive idea. The dependence is something like
confidence = (signal/noise)*sqrt(sample size)
(One caveat: if your population is very small, you may be able to get away with a smaller sample size if you are sampling without replacement. In other words, to make statements about a group of 10 people at any desired level of confidence, you never need to sample more than 10 people. This caveat is definitely ignorable for groups like "the number of families with $10 million.)
You're right (and my follow up comment is wrong) but the core of my comment holds - you still probably need 1,000+ samples to get a statistically significant result for a phenomena like this and I really doubt the OP has any knowledge on that order of things.
There's huge noise in terms of the lifetime income / career success earned by any sample population regardless of background and the phenomena we'd be looking for is probably on the order of a single-digit difference.
You'd need something like a twins study to ever really know if this was true.
Do rich kids really outperform at work because of how they behave / think? Or do their parents have better connections? Or do they just have more money to afford better colleges? The OP has no evidence that the perceived better results are actually because of the reasons he cites, or other phenomena.
If point of the post is just "rich kids have more resources so they do better at life than poor kids", well, that's kind of uninteresting and obvious. If it's "rich kids are treated different" or "rich kids act different at work" then that needs to be substantiated.
The funny thing about sample sizes is that they don't scale with population size. [Edited the part where I said they don't scale "much"... they don't scale.]
If you're studying a phenomena with less than 5% impact, you need 1000+ data points to reach 95% significance.
Looks like we just replied to nostrademons at the same time, but we slightly disagree. You say that the dependence on population size is slow (sqrt) but I say there is no dependence for most cases. Are you sure you aren't confusing the dependence of confidence on sample size as opposed to population size? See, e.g.,
Anyone know the actual formula for statistical significance, and able to work out how big a sample needs to be for, say, a population of 100k?