A practical guide to estimating the light extinction coefficient with nonlinear models—a case study on maize

Table 3 Variability in the estimates of k for different genotypes (i.e., k_j), depending on the statistical technique—point estimates and Bayesian posterior means, and 95% confidence or credible intervals in parenthesis

Genotype	LSE	MLE (normal)	MLE (beta)	LogTLM	Bayesian
DK190	0.50	0.50 (0.46–0.54)	0.46 (0.43–0.49)	0.50 (0.46–0.53)	0.46 (0.43–0.50)
DK2F10	0.52	0.52 (0.48–0.56)	0.48 (0.45–0.52)	0.49 (0.45–0.52)	0.49 (0.46–0.53)
DK72-10	0.44	0.44 (0.41–0.47)	0.42 (0.39–0.44)	0.45 (0.41–0.48)	0.42 (0.39–0.45)
DK752	0.50	0.50 (0.46–0.54)	0.47 (0.44–0.50)	0.44 (0.41–0.47)	0.48 (0.44–0.51)
LP 122–2	0.61	0.62 (0.52–0.71)	0.52 (0.45–0.58)	0.46 (0.40–0.52)	0.55 (0.48–0.62)
P 39 W55	0.71	0.71 (0.61–0.81)	0.59 (0.52–0.65)	0.56 (0.51–0.62)	0.60 (0.54–0.67)
AX 892 MG	0.71	0.71 (0.60–0.82)	0.47 (0.42–0.52)	0.50 (0.46–0.54)	0.54 (0.47–0.60)

LSE least squares estimation, MLE (normal) maximum likelihood estimation assuming a normal distribution of the data, MLE (beta) maximum likelihood estimation assuming a beta distribution of the data, LogTLM log-transformed linear model, and Bayesian techniques

ISSN: 1746-4811