Skip to main content

Table 5 Mean prediction bias, root mean squared error (RMSE) in estimating diameter inside bark using different models. Statistics were obtained by using leave-one-out cross validation method e.g. bias and RMSE for dataset I were obtained by applying the models fitted using datasets II and III

From: Estimating upper stem diameters and volume of Douglas-fir and Western hemlock trees in the Pacific northwest

Model Dataset Douglas-fir Western hemlock
Bias (cm) RMSE (cm) Bias (cm) RMSE (cm)
M1 I 0.85 2.67 −1.07 4.02
II −0.34 1.30   
III −1.10 3.84 1.83 3.64
M2 I 0.61 2.46 −1.06 3.32
II −0.36 1.28   
III −0.17 3.54 1.35 4.25
M3 I − 0.59 2.69 −0.94 3.34
II −0.62 1.30   
III −0.55 4.05 1.38 4.25
M4 I 0.35 2.21 −1.09 3.44
II −0.28 1.04   
III −0.35 3.35 1.49 4.27
M5 I −0.09 3.04 −0.37 3.83
II −0.16 1.26   
III −1.76 4.70 1.16 3.61