Measuring the health of the Indian elderly: evidence from National Sample Survey data

Chen, Bradley; Mahal, Ajay

doi:10.1186/1478-7954-8-30

Population Health Metrics

Table 6 Test for differential response by sector

From: Measuring the health of the Indian elderly: evidence from National Sample Survey data

	Less than primary education				Primary education completed
	North	East	South	West	North	East	South	West
Males
Log likelihood: rural	-2459.77	-1874.81	-947.86	-598.91	-391.29	-471.61	-387.01	-125.49
Log likelihood: urban	-561.68	-377.78	-394.38	-228.74	-762.63	-600.70	-661.10	-586.81
Log likelihood sum (unrestricted model, L ^U)	-3021.45	-2252.59	-1342.24	-827.65	-1153.92	-1072.30	-1048.11	-712.29
Log likelihood restricted model (L ^R)	-3025.87	-2256.75	-1347.63	-833.03	-1155.66	-1081.02	-1050.42	-716.86
X ² -first stage test statistic: -2*( L ^R-L ^U)	8.83	8.32	10.78	10.74	3.49	17.43	4.63	9.14
Sample size	4069	2713	1888	1168	1544	1306	1443	918
P- value (8 degrees of freedom) ¹	0.36	0.40	0.21	0.22	0.90	0.03	0.80	0.33
Log likelihood partially-restricted model (L ^Rα)	n.a.	n.a.	n.a.	n.a.	n.a.	-1072.72	n.a.	n.a.
X ²-test statistic for cut-point shift: -2*( L ^Rα-L ^U)	n.a.	n.a.	n.a.	n.a.	n.a.	0.84	n.a.	n.a.
P- value (2 degrees of freedom) ²	n.a.	n.a.	n.a.	n.a.	n.a.	0.659	n.a.	n.a.
X ²-test statistic for g (.) function: -2*( L ^R-L ^Rα)	n.a.	n.a.	n.a.	n.a.	n.a.	16.59	n.a.	n.a.
P- value (6 degrees of freedom) ³	n.a.	n.a.	n.a.	n.a.	n.a.	0.011	n.a.	n.a.
Females
Log likelihood: rural	-2810.45	-2102.21	-1320.54	-801.73	-79.89	-56.35	-169.58	-18.70
Log likelihood: urban	-1183.61	-801.69	-876.94	-551.19	-307.07	-291.29	-329.00	-330.72
Log likelihood sum (unrestricted model, L ^U)	-3994.06	-2903.90	-2197.49	-1352.93	-386.96	-347.64	-498.58	-349.42
Log likelihood restricted model (L ^R)	-3998.27	-2911.38	-2210.64	-1360.39	-391.51	-365.76	-503.08	-354.41
X ² -first stage test statistic: -2*( L ^R-L ^U)	8.42	14.97	26.32	14.93	9.09	36.24	9.00	9.98
Sample size	5522	3553	3091	2009	546	445	767	477
P- value (8 degrees of freedom) ¹	0.39	0.06	9.27 × 10-04	0.06	0.33	1.59 × 10-05	0.34	0.27
Log likelihood partially-restricted model (L ^Rα)	n.a.	n.a.	-2205.52	n.a.	n.a.	-355.21	n.a.	n.a.
X ²-test statistic for cut-point shift: -2*( L ^Rα-L ^U)	n.a.	n.a.	16.08	n.a.	n.a.	15.14	n.a.	n.a.
P- value (2 degrees of freedom) ²	n.a.	n.a.	0.0003	n.a.	n.a.	0.0005	n.a.	n.a.
X ²-test statistic for g (.) function: -2*( L ^R-L ^Rα)	n.a.	n.a.	10.24	n.a.	n.a.	21.10	n.a.	n.a.
P- value (6 degrees of freedom) ³	n.a.	n.a.	0.115	n.a.	n.a.	0.002	n.a.	n.a.

¹6 parameters for H^o (α) and 3 cut-points (τ) were estimated the unrestricted model for two subgroups (9 × 2 = 18); 6 parameters for H^o (α), 1 parameters for membership (θ) and 3 cut-points (τ) were estimated for the restricted model. The degree of freedom is equal to the difference in the number of estimated parameters between these two models (18-10 = 8).
² 16 parameters, including 6 parameters for H^o (α) for the two subgroups (6 × 2 = 12), 1 parameters for membership (θ) and 3 cut-points (τ) were estimated for the partially-restricted model. The degree of freedom is equal to the difference of number of estimated parameters between unrestricted and partially-restricted models (18-16 = 2).
³ The degree of freedom is equal to the difference of number of estimated parameters between partially-restricted models and restricted models (16-10 = 6).

Back to article page

ISSN: 1478-7954

Contact us

General enquiries: journalsubmissions@springernature.com