Table 6. Comparative ITS analysis model parameters^a of population-standardized quarterly notification rates of all forms and bacteriologically confirmed TB cases for intervention versus control areas.

	Intervention Versus Control
	IRRb	95% CI	p-valuec
All Forms TB
Baseline rated (β0)	11.380	[10.933, 11.844]	<0.001
Pre-intervention trend, control (β1)	0.998	[0.993, 1.004]	0.526
Postintervention step change, control (β2)	1.040	[0.949, 1.139]	0.403
Postintervention trend, control (β3)	0.881	[0.836, 0.928]	<0.001
Difference in baseline (β4)	2.105	[2.010, 2.205]	<0.001
Difference in pre-intervention trends (β5)	1.006	[1.000, 1.013]	0.041
Difference in postintervention step change (β6)	1.078	[0.971, 1.195]	0.159
Difference in postintervention trends (β7)	1.136	[1.072, 1.204]	<0.001
Bacteriologically confirmed TB
Baseline rated (β0)	6.438	[6.074, 6.824]	<0.001
Pre-intervention trend, control (β1)	1.016	[1.009, 1.024]	<0.001
Postintervention step change, control (β2)	1.078	[0.949, 1.225]	0.247
Postintervention trend, control (β3)	0.881	[0.824, 0.941]	<0.001
Difference in baseline (β4)	1.486	[1.385, 1.595]	<0.001
Difference in pre-intervention trends (β5)	1.013	[1.004, 1.022]	0.005
Difference in postintervention step change (β6)	1.250	[1.078, 1.450]	0.003
Difference in postintervention trends (β7)	1.141	[1.058, 1.229]	0.001

^aThe parameters were obtained for a segmented regression model with the following structure: $Y_t={\beta }_0+{\beta }_1{T}_t+{\beta }_2{X}_t+{\beta }_3{X}_t{T}_t+{\beta }_{4}Z+{\beta }_{5}Z{T}_t+{\beta }_{6}Z{X}_t+{\beta }_{6}Z{X}_t{T}_t+{ϵ}_t$. Here, Y_t is the outcome measure along time t; T_t is the quarterly time counter; X_t indicates pre- and postintervention periods, Z denotes the intervention cohort, and ZT_t, ZX_t, and ZX_tT_t are interaction terms. β₀ to β₃ relate to the control group as follows: β₀, intercept; β₁, pre-intervention trend; β₂, postintervention step change; β₃, postintervention trend. β₄ to β₇ represent differences between the control and intervention districts: β₄, difference in baseline intercepts; β₅, difference in pre-intervention trends; β₆, difference in postintervention step changes; β₇, difference in postintervention trend.

^bIRR based on log-linear GEE Poisson regression with correlation structures determined by the Cumby–Huizinga test and quasi-information criteria.

^cWald test.

^dThe baseline rate denotes case notification rates per quarter.

GEE, generalized estimating equation; IRR, incidence rate ratio; ITS, interrupted time series; TB, tuberculosis.