Once again, Alan Reynolds has asserted that Paul Krugman's claims about the top-coding of Census data are in error. Paul Krugman sends an email with his response:
Here's what I'd say about Reynolds on all this:
Here's what the CBO says: "CBO's adjustments have the biggest impact on high-income households, substantially increasing the income of that group above the levels reported by the Census Bureau." That is, the CBO explicitly states that the income share numbers reported by the Census are lower than those they estimate using their method in part because the Census data are top-coded. End of story.
Reynolds has now made two stabs at this. The first time he started yelling CBO! CBO! without, apparently, noting that the reason I pulled the quote was not to defend the CBO procedures but to show that the people at CBO - who do, presumably, know how the Census numbers are constructed - say that top-coding does reduce the reported high-income share. So, by the way, do the people at EPI (see here). EPI actually does a lot of work trying to correct for the top-coding problem that Reynolds says doesn't exist. Does Reynolds really want to claim that these people don't know what the Census data contain?
On the second stab, Reynolds still does not, as far as I can tell, address the issue of whether I was right to say that top-coding reduces estimates of top incomes. Instead, he tells us that some researchers have access to the full data. That doesn't change the fact that he made a false accusation.
I think the best way to understand what's going on is that Reynolds, rather than admit that he was wrong, is engaging in the Chewbacca defense.
On the broader issue: Reynolds says that various statistical issues have created a false impression of rising inequality. Now, serious researchers, from CBO to the IRS to Piketty and Saez, have looked at those issues, acknowledged them, but concluded that they don't make enough difference to change the picture in any fundamental way. How are those who aren't experts on these data to judge these competing claims?
Well, here's where Reynolds's personal history becomes relevant. Over the years he has repeatedly made demonstrably false accusations about the unreliability of data indicating growing inequality. In each of the cases documented by Brad and others, he did exactly what he did in his first response to my note on top-coding: yelled about how the thing was all wrong without even reading the material he was criticizing. At a certain point you just have to dismiss him as not worth paying attention to.
One last point: we have a number of indicators other than government data on what's happening to very top incomes and wealth - things like estimates of executive compensation. All these indicators point to a continuing rapid rise at the top compared with the middle. So any claim that the rising inequality we see in both Census data and in tax returns is some kind of statistical illusion faces an additional credibility problem.