An application of a pattern-mixture model with multiple imputation for the analysis of longitudinal trials with protocol deviations

Table 4 Monotone data: Parameter estimates from de jure and de facto analyses

	Prednisolone			Time			Prednisolone x Time			ART			Prednisolone x ART			Age
Analysis	Est	s.e.	p-value	Est	s.e.	p-value	Est.	s.e.	p-value	Est.	s.e.	p-value	Est.	s.e.	p-value	Est.	s.e.	p-value
MI	0.56	0.791	0.481	0.39	0.140	0.005	0.13	0.195	0.494	2.76	0.689	<0.0001	-1.12	0.966	0.245	-3.12	1.372	0.023
LMCF	0.46	0.870	0.597	0.34	0.092	<0.0001	-0.05	0.146	0.751	2.81	0.548	<0.0001	-0.75	0.875	0.400	-3.06	1.529	0.046
J2R (P-)	0.42	0.845	0.619	0.53	0.094	<0.0001	0.04	0.161	0.825	2.33	0.556	<0.0001	-0.96	0.842	0.260	-3.00	1.509	0.047
J2R (P+)	0.42	0.849	0.623	0.42	0.103	<0.0001	0.02	0.130	0.879	2.57	0.544	<0.0001	-0.96	0.786	0.275	-3.00	1.518	0.048
CDR (P-)	0.46	0.851	0.586	0.52	0.094	<0.0001	0.05	0.148	0.729	2.33	0.56	<0.0001	-0.96	0.844	0.259	-2.97	1.507	0.049
CDR (P+)	0.46	0.863	0.593	0.41	0.113	0.001	0.027	0.147	0.852	2.59	0.589	<0.0001	-0.88	0.882	0.3230	-2.98	1.52	0.050
CR (P-)	0.43	0.852	0.613	0.53	0.093	<0.0001	0.002	0.144	0.990	2.34	0.554	<0.0001	-0.87	0.815	0.288	-3.00	1.509	0.047
CR (P+)	0.44	0.858	0.608	0.43	0.114	<0.0001	0.006	0.137	0.966	2.55	0.579	<0.0001	-0.839	0.848	0.328	-3.00	1.521	0.049

ISSN: 1471-2288