Let’s say it’s late August, and someone wants to get the best estimate of Wisconsin’s real GDP for Q2. As of August, only Q1 Wisconsin GDP is available. What is the best estimate of Q2 GDP, bearing in mind the number of monthly indicators at the provincial level is much lower than that of the Nation. Here is my temporary answer.
Figure 1: Wisconsin GDP (bold black), random walk with forecast drift (green), error correction model (red), +/- one standard error band (gray lines), all in mn.Ch.2017$ SAAR. Source: BEA, author’s calculations.
A prediction based on this data, and this drop:
Figure 2: Wisconsin GDP to US GDP, in logs (blue, left scale), US GDP in log first difference (tan, right scale), Wisconsin NFP in log first difference (green, right scale), all 2024Q3 WI NFP observations are averages for July, August. Source: BEA, BLS, author’s statistics.
ΔyWIt= 0.720 + 1.130ΔyIn the USt – 0.268(yWIt-1-yIn the USt-1) + 1.428ΔnWIt
Adj-R2 = 0.78, SER = 0.0036, N=13, DW=1.85, sample 2021Q1-2024Q1. Bold faces indicate statistical significance at 10% msl, using Newey-West standard errors.
13 views looks like a thin thread to hang on to now. Unfortunately, this specification fails completely for the full sample of available data (2005Q1-2024Q1, where I split the real GDP series into Ch.2012$ and Ch.2017$). Before the epidemic, the principles of error correction have a positive sign; this is true, regardless of whether the pandemic recession and immediate effects (2020Q1-2020Q4) are excluded or not. Instead, one regressor dominates (US GDP growth). Here’s a comparison:
Figure 3: Wisconsin GDP (bold black), full sample US GDP based (blue), error correction model (red), Wisconsin DoR Economic Outlook forecast (chartreuse), all in mn.Ch.2017$ SAAR. Source: BEA, DoR, author’s calculations.
Although the difference between the two nowcasts appears to be small, the stated difference in q/q annual growth rates is noticeable: 2.1% vs. 1.9%.
The Wisconsin GDP release is scheduled for tomorrow.
Source link