Quantifying the spatial spillover effects of non-pharmaceutical interventions on pandemic risk

Table 2 The coefficients of different NPI estimates from the spatial econometric model

Phase	Phase A			Phase B
Variables	Coef.	S.D	\(95\%\) CI	Coef.	S.D	\(95\%\) CI
Spatial effect	0.6830	0.0360	[0.6142, 0.7464]	0.7790	0.0280	[0.7241, 0.8329]
School closures	− 0.0002	0.0001	[− 0.0005, 0.0001]	0.0004	0.0001	[0.0003, 0.0006]
Workplace closures	0.0005	0.0001	[0.0003, 0.0007]	0.0001	0.0001	[0.0000, 0.0002]
Cancellation of public events	0.0004	0.0001	[0.0001, 0.0006]	0.0001	0.0000	[0.0001, 0.0002]
Restrictions on gatherings	− 0.0002	0.0001	[− 0.0004, − 0.0001]	− 0.0001	0.0000	[− 0.0002, − 0.0000]
Public transport closures	− 0.0000	0.0001	[− 0.0001,0.0001]	− 0.0002	0.0001	[− 0.0003, − 0.0001]
Stay-at-home orders	0.0003	0.0001	[0.0001, 0.0005]	0.0002	0.0001	[0.0001, 0.0003]
Restrictions on internal movements	0.0001	0.0001	[0.0000, 0.0003]	− 0.0001	0.0000	[− 0.0001, 0.0000]
Obs.	784			686
\(R^2\)	0.9690			0.9740

Our data includes 48 states (regions) and Washington D.C. Coef.: Posterior mean of coefficients. S.D.: Standard Deviation. We run a Markov chain of 50,000 iterations with a \(50\%\) burn-in ratio. We treat the posterior mean of parameters as their Bayesian point estimates. We rely on the Bayesian \(95\%\) CI to judge the significance of parameters. Bolded color indicates significance

ISSN: 1476-072X