Table 1 Relative mean squared error (MSE) by method, cutpoint, and compliance distribution (relative to intention to treat (ITT))

From: Dichotomizing partial compliance and increased participant burden in factorial designs: the performance of four noncompliance methods

Cutpoint	Method	Compliance distribution
Cutpoint	Method	Beta (1, 0.1765)	Beta (0.25, 0.05)	Beta (0.5, 0.5)	Uniform
0.9	PP	1.064	0.951	0.991	2.251
	AT	1.148	0.898	1.023	2.365
	IV	2.598	1.508	17.183	173.917
0.85	PP	1.024	0.930	0.863	1.390
	AT	1.081	0.868	0.905	1.504
	IV	2.004	1.434	8.887	44.182
0.8	PP	0.998	0.915	0.760	1.050
	AT	1.025	0.847	0.793	1.160
	IV	1.671	1.366	5.543	18.681
0.75	PP	0.985	0.918	0.690	0.866
	AT	1.001	0.856	0.712	0.981
	IV	1.469	1.313	3.833	9.308
0.7	PP	0.954	0.913	0.658	0.795
	AT	0.959	0.853	0.682	0.912
	IV	1.336	1.274	2.858	5.467
0.65	PP	0.944	0.909	0.637	0.720
	AT	0.944	0.851	0.656	0.835
	IV	1.242	1.245	2.230	3.476
0.6	PP	0.933	0.900	0.616	0.667
	AT	0.927	0.845	0.635	0.779
	IV	1.172	1.218	1.818	2.369
0.55	PP	0.933	0.898	0.607	0.651
	AT	0.927	0.848	0.619	0.745
	IV	1.127	1.190	1.555	1.763
0.5	PP	0.931	0.904	0.592	0.641
	AT	0.924	0.857	0.603	0.720
	IV	1.092	1.171	1.362	1.386

Back to article page

ISSN: 1745-6215

Contact us

Submission enquiries: Access here and click Contact Us
General enquiries: info@biomedcentral.com