I see a lot of economists (many on the right, see here) saying that we are in a recession, or soon will be together. What are predictive models?
Miller (2019) showed an advanced AUROC probit model for forecasting recessions in 3 months over the period 1954-2018 using the 10yr-Fed funds spread. He reviews his decline, not assuming inflation since August:
Figure 1: 10 years – Fed funds spread, % (blue scale, left scale), relative probability of recession (red, right scale). August interest rate data through 8/20. Source: Treasury, Fed via FRED, and author’s calculations.
The McFadden R2 from this regression is 0.15, and puts the probability of a recession in November at 35%. (Adding the Chicago Financial Conditions Index increases the McFadden R2 to 0.31, but yields a 0.07 probability of a recession in November).
Note that this is not a collective analysis (we in the middle recession now?), but looking ahead.
Source link