A Funny Forecasting Story

Last night, I knew I was on tap to talk about Wisconsin GDP numbers today (Wisconsin Public Radio report here). I wondered what a naive forecast would imply, so I regressed first difference of log Wisconsin GDP on first difference of log US GDP and a lagged Wisconsin GDP first difference, to obtain this forecast…(red square)


Figure 1: Wisconsin GDP, latest release (black), and previous vintage (gray-red), and forecast based on previous vintage (red square) and 95% confidence interval (gray +), all in millions of Ch.2012$, SAAR. BEA, and author’s calculations.

Using the data in plotted as the gray-red line, I forecasted out-of-sample Wisconsin GDP for 2020Q2 shown as the red square. The 2020Q2 forecast error was -0.0015 (-0.15%), or 419 million Ch.2012$ SAAR — barely anything!

But the annual benchmark revisions moved upward the level of the 2018-19 GDP by about 0.8% (log terms), so it’s surprising that the forecast was actually so close. I guess it goes to show that one can forecast the outcome just right by accident.

More discussion of the specifics of the Wisconsin GDP numbers in this post.


Econometric details:

The forecast is based on this regression, estimated over the 2005Q3-2020Q1 period. Let y be real GDP.

Δywit = -0.0016 0.1312Δywit-1 + 1.0710Δyust

Adj-R2=0.65, SER = 0.0047, N = 59. Significance at 5% msl using HAC robust standard errors denoted by bold face. Q-stat 8 lags, 8.451 [p-value = 0.391]

The data are here (XLSX).



11 thoughts on “A Funny Forecasting Story

    1. pgl

      I bet you were playing on a putt putt golf course, which of course is no where near 100 yards. Now where you wearing a mask?

      1. Bruce Hall

        Hey, this is MIchigan where there are trees and open land, not NYC where people think Central Park is the wilderness.

        NYC where people think table tennis is real tennis.

        1. pgl

          Golf? In my city we play basketball. And we play it hard. You would not last 2 minutes before your fragile bones would be broken. BTW – where do you think they play the US Open? Certainly not in your ugly state.

        2. pgl

          BTW I hate golf but I do have a friend at Yelp who says anyone in Brooklyn could go here for a list of all the open public golf courses nearby:


          Lots of good choices but that one at Ferry Point with Trump’s name on it has some really bad reviews. Go figure. But maybe Bruce should go there and wear his stupid MAGA hat. He’d fit right in. But do bring a mask as even the Trumpian morons here get angry at irresponsible dumba$$es like Brucie boy.

  1. Moses Herzog

    I’m glad you expressed that as a percentage of GDP Menzie, or I might want to take up with you what you thought barely anything is. I’m joshing on you Menzie, hope you know that.

  2. Moses Herzog

    Recommend a good film, for anyone who has a tolerance for slow paced films with maybe a tinge of melancholy in the story. “First Cow” is a really good film and deserves a rental or a stream. The acting is superb, and the story is well done. I think even though the movie is dark and slow-paced, the over-arching message of the film is the importance of friendship, so I like this film a lot.

  3. AS

    Professor Chinn,
    Here is an ignorant question: Why the need to use “HAC robust standard errors”? The residuals appear to be uncorrelated. Is it due to the use of the lag of Wisconsin GDP?

  4. Moses Herzog

    Thanks for sharing how you did your regression and the raw data Menzie, it is appreciated. I think I remember you don’t like the phrase “raw data” but you know what I mean.

Comments are closed.