Predicting crown width and length using nonlinear mixed-effects models: a test of competition measures using Chinese fir (Cunninghamia lanceolata (Lamb.) Hook.)

Table 9 The lack-of-fit statistics of the crown length mixed-effects model using different variance functions

Model	Variance function	AIC	BIC	− 2LL (df)	L.Ratio	p value
(15)	None	4869	4912	4853.39 (8)
(15.1)	ConstPower	4817	4870	4796.61 (10)	56.78^c	< 0.0001
(15.2)	Power	4817	4865	4799.06 (9)	54.33^c	< 0.0001
(15.3)	Exponent	4798	4846	4780.25 (9)	73.15^c	< 0.0001

AIC, Akaike information criterion; BIC, Bayesian information criterion; − 2LL(df), − 2 log-likelihood (degree of freedom). ^cL.Ratio, the value of likelihood ratio test, which was calculated with respect to model (15)

ISSN: 1297-966X