The study of statistical methods for evaluating the comparability of routine chemistry analytes among 3 routine laboratory measurement systems in China

SpringerPlus

Table 3 The robust statistics and robust z-scores^a of glucose test results

Lot	Robust average	Robust s	Range of robust z-scores	The percentage of \|z-score\| ≤2
1	6.009	0.179	−2.397 to 2.268	80 % (16/20)
2	7.117	0.209	−2.354 to 3.124	90 % (18/20)
3	5.126	0.186	−2.102 to 1.957	95 % (19/20)
4	5.746	0.193	−2.881 to 1.731	95 % (19/20)
5	6.683	0.264	−2.379 to 1.390	95 % (19/20)
6	7.630	0.254	−2.795 to 2.008	90 % (18/20)
7	8.795	0.209	−2.895 to 2.656	90 % (18/20)
8	9.949	0.270	−2.793 to 2.133	90 % (18/20)
9	14.434	0.377	−2.517 to 2.125	90 % (18/20)
10	12.026	0.433	−2.023 to 5.356	90 % (18/20)

^aThe z-score in this table have been derived from the data in column “Robust average” and “Robust s”. The formula for the z-score in this table is z = (x − \({\text{x}}^{*}\))/\({\text{s}}^{*}\)