Table 6:

Heterogeneous effects of NPI speed on COVID-19 deaths per 100,000 residents

Column	(1)	(2)	(3)	(4)	(5)	(6)	(7)
County characteristic (CC)	Majority republican	% over 65	% uninsured	% unemployed	% below FPL	Comorbidity index	Population density
Postct × NPI Speedc	−0.0031***	−0.0025***	−0.0014***	−0.0012***	−0.0011***	−0.0013***	−0.0009***
	(0.0006)	(0.0006)	(0.0003)	(0.0003)	(0.0004)	(0.0002)	(0.0003)
Postct × NPI Speedc × CC	0.0020***	0.0001**	0.00002	−0.0001	−0.00001	−0.00004	−0.000005
	(0.0006)	(0.0000)	(0.00005)	(0.0002)	(0.00004)	(0.0001)	(0.000004)
State-level tests per 100,000	0.0003***	0.0003***	0.0003***	0.0003***	0.0003***	0.0003***	0.0002***
	(0.0000)	(0.0000)	(0.0000)	(0.0000)	(0.0000)	(0.0000)	(0.0000)
Postct × Other NPI speedc	−0.0016***	−0.0016***	−0.0016***	−0.0016***	−0.0016***	−0.0016***	−0.0015***
	(0.0001)	(0.0001)	(0.0001)	(0.0001)	(0.0001)	(0.0001)	(0.0001)
Observations	213,141	215,073	215,004	215,004	215,004	215,073	214,935
R-squared	0.084	0.084	0.084	0.084	0.084	0.084	0.089
Dependent variable mean	0.071	0.070	0.070	0.070	0.070	0.070	0.070

Notes: *** p<0.01, ** p<0.05, * p<0.1. All regressions include a constant term, date, and county fixed effects. Standard errors are in parentheses and clustered at the county level. Observations vary across specifications due to missing data. Column (1) uses a dummy variable to indicate counties where the Republican vote share in the 2016 presidential election exceeded 50%. We rely on information from 3089 counties because 28 were missing information on election returns. Columns (3), (4), and (5) use information from 3116 counties because one county was missing information on the number of residents without health insurance, unemployed, or living below the federal poverty level. In column (7), we use information from 3115 counties because two counties were missing land area information required to calculate the number of residents per square mile