Table 5.

Model 3: dynamic regression model predicting the Gini index with ARIMA^a error term (1, 0, 2).

Measures				Gini index		P value
Predictors of the Gini index, estimate of effect (95% CI)
	Intercept			23.90 (23.60 to 24.20)		<.001
	Statutory holidays (1 for holidays, 0 for nonholidays)			0.44 (0.08 to 0.81)		.02
	Business closure			0.11 (0.05 to 0.17)		<.001
	Regional differences in lockdown
		Regions are in the same stage of lockdown	Reference group		N/Ab
		Regions are in different stages of lockdown	–0.738 (–1.19 to –0.28)		.001
		Regions are not under lockdown	0.16 (–0.89 to 1.22)		.77
	New COVID-19 case counts in Canada, excluding Ontario (in hundreds of cases)			–0.01 (–0.04 to 0.01)		.31
	New COVID-19 case counts (in hundreds of cases)			0.00 (–0.07 to 0.07)		.99
	Regions are in different stages of lockdown × new cases			0.11 (0.01 to 0.21)		.02
	Regions are not under lockdown × new cases			–1.98 (–5.06 to 1.10)		.21
Goodness of fit
	With covariates, AICc			461.82		N/A
	Without covariates, AIC			573.98		N/A

^aARIMA: autoregressive integrated moving average.

^bN/A: not applicable.

^cAIC: Akaike information criterion.