Table 5.

The total effect of policies on case and death growth (PI→Y).

	Dependent variable:
	$\Delta log\Delta C_{it}$
	(1)	(2)	(3)	(4)
lag(masks for employees, 14)	$-0.083^{\ast \ast }$	$-0.081^{\ast \ast }$	$-0.103^{\ast \ast \ast }$	$-0.102^{\ast \ast \ast }$
	(0.038)	(0.040)	(0.033)	(0.035)
lag(closed K-12 schools, 14)	$-0.226^{\ast \ast }$	$-0.236^{\ast \ast }$	0.029	0.017
	(0.089)	(0.097)	(0.102)	(0.107)
lag(stay at home, 14)	$-0.127^{\ast \ast }$	$-0.121^{\ast \ast }$	$-0.115^{\ast \ast }$	$-0.103^{\ast \ast }$
	(0.057)	(0.054)	(0.054)	(0.052)
lag(business closure policies, 14)	$-$0.076		$-$0.001
	(0.068)		(0.061)
lag(closed movie theaters, 14)		0.027		0.062
		(0.051)		(0.046)
lag(closed restaurants, 14)		$-$0.041		$-$0.011
		(0.049)		(0.045)
lag(closed non-essent bus, 14)		$-$0.051		$-$0.038
		(0.050)		(0.043)
lag($\Delta log\Delta C_{it}$, 14)	0.040	0.041${}^{\ast }$	0.036	0.035
	(0.024)	(0.025)	(0.028)	(0.028)
lag($log\Delta C_{it}$, 14)	$-0.137^{\ast \ast \ast }$	$-0.137^{\ast \ast \ast }$	$-0.091^{\ast \ast \ast }$	$-0.090^{\ast \ast \ast }$
	(0.022)	(0.022)	(0.026)	(0.026)
lag($\Delta log\Delta C_{it}$.national, 14)			$-0.128^{\ast \ast \ast }$	$-0.123^{\ast \ast \ast }$
			(0.039)	(0.041)
lag($log\Delta C_{it}$.national, 14)			$-0.243^{\ast \ast \ast }$	$-0.245^{\ast \ast \ast }$
			(0.045)	(0.045)
$\Delta log{T}_{it}$	0.156${}^{\ast \ast \ast }$	0.157${}^{\ast \ast \ast }$	0.158${}^{\ast \ast \ast }$	0.160${}^{\ast \ast \ast }$
	(0.044)	(0.044)	(0.042)	(0.041)
state variables	Yes	Yes	Yes	Yes
Month ×state variables	Yes	Yes	Yes	Yes
${\sum }_j{\mathrm{Policy}}_j$	−0.512${}^{\ast \ast \ast }$	−0.504${}^{\ast \ast \ast }$	−0.190	−0.175
	(0.150)	(0.154)	(0.156)	(0.159)
Observations	3,825	3,825	3,825	3,825
R2	0.749	0.750	0.763	0.763
Adjusted R2	0.747	0.747	0.760	0.761

	Dependent variable:
	$\Delta log\Delta D_{it}$
	(1)	(2)	(3)	(4)
lag(masks for employees, 21)	$-0.134^{\ast \ast \ast }$	$-0.133^{\ast \ast }$	$-0.156^{\ast \ast \ast }$	$-0.155^{\ast \ast \ast }$
	(0.051)	(0.053)	(0.050)	(0.052)
lag(closed K-12 schools, 21)	$-0.610^{\ast \ast \ast }$	$-0.621^{\ast \ast \ast }$	$-0.234^{\ast \ast }$	$-0.248^{\ast \ast }$
	(0.115)	(0.121)	(0.111)	(0.109)
lag(stay at home, 21)	$-$0.082	$-$0.075	$-$0.068	$-$0.057
	(0.066)	(0.064)	(0.066)	(0.062)
lag(business closure policies, 21)	$-$0.059		0.059
	(0.086)		(0.086)
lag(closed movie theaters, 21)		$-$0.006		0.050
		(0.089)		(0.082)
lag(closed restaurants, 21)		$-$0.012		0.030
		(0.061)		(0.055)
lag(closed non-essent bus, 21)		$-$0.040		$-$0.016
		(0.066)		(0.063)
lag($\Delta log\Delta D_{it}$, 21)	$-$0.001	$-$0.001	0.017	0.016
	(0.033)	(0.033)	(0.036)	(0.037)
lag($log\Delta D_{it}$, 21)	$-0.078^{\ast \ast \ast }$	$-0.078^{\ast \ast \ast }$	$-0.064^{\ast \ast }$	$-0.063^{\ast \ast }$
	(0.026)	(0.027)	(0.027)	(0.027)
lag($\Delta log\Delta D_{it}$.national, 21)			$-0.147^{\ast \ast \ast }$	$-0.148^{\ast \ast }$
			(0.056)	(0.057)
lag($log\Delta D_{it}$.national, 21)			$-0.116^{\ast \ast \ast }$	$-0.117^{\ast \ast \ast }$
			(0.032)	(0.032)
state variables	Yes	Yes	Yes	Yes
Month ×state variables	Yes	Yes	Yes	Yes
${\sum }_j{\mathrm{Policy}}_j$	−0.885${}^{\ast \ast \ast }$	−0.887${}^{\ast \ast \ast }$	−0.399${}^{\ast \ast }$	−0.396${}^{\ast \ast }$
	(0.159)	(0.166)	(0.183)	(0.188)
Observations	3,468	3,468	3,468	3,468
R2	0.502	0.502	0.512	0.512
Adjusted R2	0.497	0.497	0.507	0.507

Note:${}^{\ast }$p$<$0.1; ${}^{\ast \ast }$p$<$0.05; ${}^{\ast \ast \ast }$p$<$0.01.

Dependent variable is the weekly growth rate of confirmed cases (in the upper panel) or deaths (in the lower panel) as defined in Eq. (4). The covariates include lagged policy variables, which are constructed as 7 day moving averages between $t$ to $t-7$ of corresponding daily measures. The row “${\sum }_j{\mathrm{Policies}}_j$” reports the sum of all policy coefficients. “business closure policies” is defined by the average of closed movie theaters, closed restaurants, and closed non-essential businesses. Standard errors are clustered at the state level.