Assessing the agreement of biomarker data in the presence of left-censoring

BMC Nephrology

Table 5 Simulation results based on 1000 data sets with sample size of 25 -- Per cent censoring (25%, 25%)

Per cent censoring	True ρ	True ρ _c	Method	Mean ${\hat{ρ}}_{c}$	Relative bias (%)	Empirical SD	Mean SE	The percentage of 95% confidence intervals that include true value of CCC
(25%, 25%)	0.25	0.238	1. Delete the pair	0.1300	−45.38	0.2287	0.2002	85.7
			2. Replace by LOD	0.2159	−9.29	0.2176	0.1563	84.1
			3. Replace by 0.5 × LOD	0.1821	−23.49	0.2280	0.1550	78.5
			4. Replace by c × LOD	0.1897	−20.29	0.2215	0.1552	78.4
			5. ML	0.2225	−6.51	0.1905	0.1783	93.1
	0.50	0.476	1. Delete the pair	0.2862	−39.87	0.2088	0.1853	83.4
			2. Replace by LOD	0.3963	−16.74	0.2030	0.1356	83.1
			3. Replace by 0.5 × LOD	0.3538	−25.67	0.2277	0.1372	76.3
			4. Replace by c × LOD	0.3642	−23.49	0.2105	0.1372	78.7
			5. ML	0.4496	−5.55	0.1650	0.1526	93.3
	0.75	0.714	1. Delete the pair	0.4850	−32.07	0.1951	0.1489	77.3
			2. Replace by LOD	0.6031	−15.53	0.2122	0.0960	83.5
			3. Replace by 0.5 × LOD	0.5467	−23.43	0.2545	0.0984	77.0
			4. Replace by c × LOD	0.5436	−23.87	0.2700	0.0991	77.6
			5. ML	0.6897	−3.40	0.1136	0.1027	92.1

Abbreviations: LLD Lower Limit of Detection, ML Maximum Likelihood, C = Random number from uniform distribution (0, 1), CI confidence interval, Relative bias = $\frac{(Mean {\hat{ρ}}_{c} - True ρ_{c})}{True ρ_{c}} \times 100 %$ , CCC⁵= $ρ_{c} = \frac{2 COV (X, Y)}{VAR (X) + VAR (Y) + {(E (X) - E (Y))}^{2}}$ .

ISSN: 1471-2369