But r = 0.23 means the percent of variance explained is 0.23^2 = ~5%. If some Social Darwinist organization were to announce that they had evidence that who your parents were only determined 5% of the variance in wealth, it would sound like such overblown strong evidence for their position that everyone would assume they were making it up.
His point is that some pundits have used a recent study to claim that inherited wealth is really, really important, even though numerically the study fails to show that.
Suppose we define mathiness as people making misleading, ideologically loaded claims about what their theorems prove. It seems fair to suggest that statisticiness is a similar problem.
I’d like to kick these people right in statisticals.
This seems to be a persistent problem. I recommend Darrell Huff as required reading for just about everyone – as a possible remedy. I’ve given quite a few copies to friends and acquaintances – who desperately needed it – over the years.
The downside of the remedy, of course, would be that so many folks currently attempting to pass themselves off as “scientists”, “economists”, “journalists”, and “policy-makers” would have to find other work in an already collapsing low-skill labor market.
Technical correction: R-squared gives the ratio or percent of explained to total variation (variation = sum of squares), not a ratio or percent of variances (variance = su of squares divided by degrees of freedom). (However, the post’s broader point is unaffected by this correction.)