A method for describing and modelling of within-ring wood density distribution in clones of three coniferous species

Wood density within growth rings was examined and modelled for clones of three coniferous species: Norway spruce, Douglas fir, and maritime pine. Within-ring density measurements obtained by X-ray scanning were represented as a frequency distribution. The distribution was described using both moment-based and non-parametric ( robust) statistics and its sample quantiles were modelled using the generalised lambda distribution. In Norway spruce the frequency distribution of wood density was unimodal and asymmetric (i.e. positively skewed), whereas in Douglas fir and maritime pine, the distribution was bimodal (i.e. mixture of two skewed distributions, corresponding to earlywood and latewood ring zones). In all three species, analyses of covariance revealed that, after adjustment for ring width or mean ring density, there was still significant ( p < 0.01) clone variability in within-ring frequency distribution parameters (i.e. clones with similar growth rate or mean density had different within-ring structure).