Tuesday, November 10, 2015

Checking it twice (GDP and GDI)

Jérémie Cohen-Setton links to a new Fed report [pdf] about how some published results change if you use NGDI instead of NGDP; they find:
Estimating models using GDI, both with the GDI data originally available to the authors and with revised GDI, instead of GDP generates larger differences in results than those obtained with revised GDP. For 3 of 23 papers (13%), the results we obtain with GDI are qualitatively different than the original published results.

So I thought it would be good to check some IT model results using this method. I checked this post, and I basically get the same result:

And I checked this post:

It checks out so far. I'll continue to check these two independent measures of nominal output in the future.


  1. O/T: Jason, I seem to recall you doing a post that included some commentary on a figure very much like the 2nd figure in Sumner's post here:
    Am I correct?

    1. Yes, here:


      The spike at zero only represents 12% of wage changes (so 88% of wages change by up to 20%) and during a recession it goes up to 16% (so 84% of wages change by up to 20%). That doesn't say to me 'sticky micro wages'. However, the distributions do not change very much. That says to me 'sticky macro wages'.

      Everyone could have different wages, but if the distribution is the same, then there's no aggregate difference between being in a recession and not being in a recession.

    2. To me the spike at zero says sticky micro wages, and considering the distribution of the non-sticky wages, sticky wages are depressed. I know that some economists say that if only wages were not sticky during recessions, they would come down, but it does not look that way to me.

    3. But the spike at zero only represents a small fraction of all wages and only slightly changes during a recession. That 4 percentage point change from 12% to 16% in the zero-change bin is responsible for recessions?

      I would make the claim that you would not even notice a difference if I stimulated two stochastic processes with those two empirical distributions.

      Which I will do.

    4. No, I say the opposite of the economists, namely that the spike at 0 indicates that wages are depressed, recession or no.


Comments are welcome. Please see the Moderation and comment policy.

Also, try to avoid the use of dollar signs as they interfere with my setup of mathjax. I left it set up that way because I think this is funny for an economics blog. You can use € or £ instead.