Table 1. Generalized Linear Model (GLM) Regression: Predicting COVID-19 deaths, at t + 38 days.

Regression table under a Negative Binomial model. See Table C and Fig D in S1 Text for descriptions of variables. Standard errors were adjusted for clustering at the county level. Coefficients in bold are statistically significant at the 95% confidence level.

Dep. Variable:	new deaths per 100k, at t + 38 days	No. Observations:	55842
Model:	GLM	Df Residuals:	55830
Model Family:	NegativeBinomial	Df Model:	11
Link Function:	log	Scale:	1.0000
Method:	IRLS	Log-Likelihood:	-62440.
No. Iterations:	8	Deviance:	31331.
Covariance Type	cluster (county)	Pearson chi2:	4.09e+04