Effect of the number of removed lymph nodes on prostate cancer recurrence and survival: evidence from an observational study

Gigliarano, Chiara; Nonis, Alessandro; Briganti, Alberto; Bonetti, Marco; Serio, Clelia Di

doi:10.1186/s12859-018-2180-8

Table 7 Root Mean Squared Error (MSE) and Bias for the estimation of the marginal survival probability S(1000) for the three groups defined by the number of nodes received

From: Effect of the number of removed lymph nodes on prostate cancer recurrence and survival: evidence from an observational study

Generation		Estimation					Unadjusted		Weighted		Doubly Robust
PM	SM	PM	SM	n	Nodes	S(1000)	\(\sqrt {\text {MSE}}\)	Bias	\(\sqrt {\text {MSE}}\)	Bias	\(\sqrt {\text {MSE}}\)	Bias
1	1	1	1	1000	1-10	0.4808	0.0908	-0.0287	0.0987	-0.0060	0.0845	0.0093
					11-20	0.4808	0.0299	-0.0071	0.0292	-0.0004	0.0262	0.0011
					>20	0.4808	0.1113	0.0728	0.1002	0.0001	0.0935	0.0183
1	1	1	1	5000	1-10	0.4769	0.0459	-0.0259	0.0436	0.0002	0.0373	0.0027
					11-20	0.4769	0.0147	-0.0073	0.0128	-0.0005	0.0113	-0.0001
					>20	0.4769	0.0836	0.0756	0.0463	-0.0001	0.0417	0.0029
1	1	1	1	10000	1-10	0.4775	0.0356	-0.0235	0.0306	0.0005	0.0261	0.0017
					11-20	0.4775	0.0116	-0.0071	0.0093	-0.0002	0.0080	0.0000
					>20	0.4775	0.0786	0.0742	0.0336	-0.0007	0.0298	0.0013
[5pt] 2	2	2	2	1000	1-10	0.4108	0.0948	-0.0329	0.1067	-0.0060	0.0951	0.0102
					11-20	0.4108	0.0293	-0.0070	0.0288	-0.0005	0.0265	0.0005
					>20	0.4108	0.1091	0.0728	0.0968	0.0006	0.0927	0.0160
2	2	2	2	5000	1-10	0.4067	0.0498	-0.0312	0.0463	0.0003	0.0414	0.0031
					11-20	0.4067	0.0141	-0.0068	0.0125	-0.0002	0.0116	-0.0001
					>20	0.4067	0.0778	0.0697	0.0439	-0.0001	0.0410	0.0018
2	2	2	2	10000	1-10	0.4069	0.0391	-0.0289	0.0320	-0.0012	0.0292	0.0002
					11-20	0.4069	0.0111	-0.0064	0.0092	0.0002	0.0084	0.0002
					>20	0.4069	0.0739	0.0695	0.0322	0.0006	0.0300	0.0016
[5pt] 2	3	2	3	1000	1-10	0.4108	0.0948	-0.0329	0.1067	-0.0060	0.0951	0.0102
					11-20	0.2971	0.0283	-0.0044	0.0284	0.0001	0.0269	0.0014
					>20	0.5514	0.1056	0.0727	0.0978	0.0009	0.0895	0.0186
2	3	2	3	5000	1-10	0.4067	0.0498	-0.0312	0.0463	0.0003	0.0414	0.0031
					11-20	0.2941	0.0131	-0.0046	0.0125	-0.0000	0.0120	0.0001
					>20	0.5461	0.0764	0.0687	0.0443	0.0002	0.0390	0.0027
2	3	2	3	10000	1-10	0.4069	0.0391	-0.0289	0.0320	-0.0012	0.0292	0.0002
					11-20	0.2936	0.0099	-0.0045	0.0090	0.0000	0.0086	0.0001
					>20	0.5473	0.0708	0.0666	0.0317	-0.0001	0.0281	0.0015
[5pt] 3	2	3	2	1000	1-10	0.4108	0.1562	-0.1401	0.1061	-0.0082	0.0949	0.0100
					11-20	0.4108	0.0292	0.0011	0.0292	-0.0001	0.0264	0.0009
					>20	0.4108	0.1930	0.1710	0.1110	0.0099	0.0969	0.0241
3	2	3	2	5000	1-10	0.4067	0.1429	-0.1399	0.0455	-0.0023	0.0416	0.0008
					11-20	0.4067	0.0133	0.0010	0.0133	0.0000	0.0122	0.0002
					>20	0.4067	0.1754	0.1711	0.0490	0.0010	0.0414	0.0020
3	2	3	2	10000	1-10	0.4069	0.1362	-0.1345	0.0324	-0.0006	0.0300	0.0007
					11-20	0.4069	0.0095	0.0011	0.0094	0.0000	0.0086	0.0001
					>20	0.4069	0.1721	0.1698	0.0349	0.0002	0.0297	0.0008

Both models for propensity score and survival used in the estimation process here match the corresponding models used for data generation. Results are based on 3000 simulated samples. PM stands for Propensity Score Model, and SM stands for Survival Model. Please refer to the text for the description of the models

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com

BMC Bioinformatics

Contact us