Data Subset

All (n = 242)

Random (n = 160/82)

L_{1} ≥ 2–10≤ U_{1} (n = 87)



r
^{2}

1
^{st}

≥
2
^{nd}

≥
3
^{rd}

r
^{2}
(n=87)

Cat. Err
.

Pull & Grab

0.72

80%

94%

99%

0.71

18%

Regression

0.68

17%

70%

95%

0.68

31%

Interpolation

0.64

3%

28%

50%

0.57

22%

Garki

0.58

0%

0%

5%

0.46

25%

PR
_{2}

0.05

0%

0%

0%

0.21

38%

 A summary of the skill of the four candidate standardization algorithms. The columns summarize the proportion of variance explained (r^{2}), for the full data, the rankings of the four algorithms fitted to 100 random subsamples of the testing set (n = 160) and tested on the remainder (n = 82), and the r^{2} and the proportion of categorical errors for the subset of the testing set that was within the standardization range. The table also includes an evaluation of the paired PfPR estimate (PR_{2}).