Covariate balance-related propensity score weighting in estimating overall hazard ratio with distributed survival data

Table 6 Comparisons of the proposed method in distributed data and corresponding pooled individual-level data analysis

Distributed Data Analysis
			Setting 1			Setting 2
		Global weight	Local weight	Proposed weight	Global weight	Local weight	Proposed weight
\(K=5\), \({n}_{k}=500\)	Bias	-0.018	-0.014	-0.017	0.045	0.041	0.033
	RMSE	0.116	0.129	0.106	0.129	0.125	0.110
	r-RMSE	1.093	1.215	1.000 (Ref)	1.176	1.140	1.000 (Ref)
\(K=5\), \({n}_{k}=1000\)	Bias	-0.006	-0.008	-0.006	0.039	0.024	0.022
	RMSE	0.089	0.100	0.077	0.096	0.092	0.076
	r-RMSE	1.160	1.303	1.000 (Ref)	1.269	1.216	1.000 (Ref)
\(K=5\), \({n}_{k}=2000\)	Bias	-0.002	-0.003	-0.001	0.031	0.014	0.011
	RMSE	0.066	0.065	0.061	0.093	0.094	0.077
	r-RMSE	1.087	1.071	1.000 (Ref)	1.210	1.223	1.000 (Ref)
Pooled Individual-Level Data Analysis
			Setting 1			Setting 2
		Global weight	Local weight	Proposed weight	Global weight	Local weight	Proposed weight
\(K=5\), \({n}_{k}=500\)	Bias	-0.018	-0.014	-0.017	0.045	0.041	0.033
	RMSE	0.116	0.129	0.106	0.129	0.125	0.110
	r-RMSE	1.093	1.215	1.000 (Ref)	1.176	1.140	1.000 (Ref)
\(K=5\), \({n}_{k}=1000\)	Bias	-0.006	-0.008	-0.006	0.039	0.024	0.022
	RMSE	0.089	0.100	0.077	0.096	0.092	0.076
	r-RMSE	1.160	1.303	1.000 (Ref)	1.269	1.216	1.000 (Ref)
\(K=5\), \({n}_{k}=2000\)	Bias	-0.002	-0.003	-0.001	0.031	0.014	0.011
	RMSE	0.066	0.065	0.061	0.093	0.094	0.077
	r-RMSE	1.087	1.071	1.000 (Ref)	1.210	1.223	1.000 (Ref)

Bias absolute bias, RMSE root mean squared error, r-RMSE ratio of RMSE of global weight or local weight against proposed weight
Setting 1: homogenous design and treatment assignment generated with \({X}_{1}\)~\({X}_{4}\) and \({X}_{1}^{2}\), \({X}_{1}{X}_{4}\); setting 2: heterogeneous design and treatment assignment generated with \({X}_{1}\)~\({X}_{4}\) and \({X}_{1}^{2}\), \({X}_{1}{X}_{4}\)

ISSN: 1471-2288