ADP private nonfarm has a blowout upside surprise of +497K vs. consensus +228K. For context, the m/m standard deviation of log first differences is 0.0028, vs. June reading of 0.0039.

Using the correlation between log first differences for BLS nonfarm payroll employment and ADP, I get the following prediction or “nowcast” for the BLS number to be released tomorrow, taken literally, a 486K employment increase (ignoring revisions to previous months):

Figure 1: BLS nonfarm payroll employment series (black), and predicted (light blue), +/- 1 std error (gray +), and Bloomberg consensus of 7/6 (red square), all s.a. Source: BLS, ADP via FRED, Bloomberg and author’s calculations.

I estimate this specification over the 2021M06-2023M05 period :

Δ pnfp_bls_t = 0.001 + 0.643 Δ pnfp_adp_t + u_t

Adj. R² = 0.66 SER = 0.0010, n = 21, DW = 2.24. (Coefficients significant at 5% msl using HAC robust standard errors bold ital.)

Notice a simple autoregression of first differenced private NFP (i.e., an ARIMA(1,1,0) of log NFP) yields a considerably lower adjusted R2 (0.30). Lagged private NFP from BLS does not enter significantly if entered into the above equation.

That being said, the ADP-based prediction has outpaced actual BLS changes for the past four months. GS argues that ADP seasonal estimations have distorted that number, and has an estimate for 225K (Bloomberg consensus is 218K for private NFP).

More By This Author:

On The Reliability Of Non-Renewables Energy Production: Texas, June 18, 2023
Two Quarters Of Negative GDP Growth Do Not (Necessarily) A Recession Make, Part MMXXVI
Wind, Solar Help Texas Meet Record Power Demand During Heat Wave