Application of Cox Proportional Hazards Model in Case of Tuberculosis Patients in Selected Addis Ababa Health Centres, Ethiopia

Table 8

Result of test of proportionality assumption containing the variables in Table 7 and their interaction with log time.

(a)  

Analysis of maximum likelihood estimates
Covariates	DF	Parameter estimate	Standard error	Chi-Square	Pr > ChiSq	Hazard ratio
Age	1	0.01919	0.02212	0.7526	0.3857	1.019
TBC	1	0.20274	0.95433	0.0451	0.8318	1.225
HIV	1	1.09680	1.13372	0.9359	0.3333	2.995
AgHIV	1	−0.02914	0.01722	2.8638	0.0906	0.971
Age * log (time)	1	0.00223	0.00561	0.6904	0.6904	1.002
TBC * log (time)	1	−0.19525	0.23829	0.6714	0.4126	0.823
HIV * log (time)	1	0.31882	0.27050	1.3891	0.2385	1.375
agHIV * log (time)	1	−0.0001785	0.0001725	1.0712	0.3007	1.000

(b)  

Linear hypotheses testing results
Label	Wald; Chi-Square	DF	Pr > ChiSq
Test proportionality	2.1579	4	0.7067