On the consequences of misspecifing assumptions concerning residuals distribution in a repeated measures and nonlinear mixed modelling context

In this paper we describe the results of a simulation study performed to elucidate the robustness of the Lindstrom and Bates (1990) approximation method under non-normality of the residuals, under different situations. Concerning the fixed effects, the observed coverage probabilities and the true bias and mean square error values, show that some aspects of this inferential approach are not completely reliable. When the true distribution of the residuals is asymmetrical, the true coverage is markedly lower than the nominal one. The best results are obtained for the skew normal distribution, and not for the normal distribution. On the other hand, the results are partially reversed concerning the random effects. Soybean genotypes data are used to illustrate the methods and to motivate the simulation scenarios

Impact of incorrect assumptions on the covariance structure of random effects and/or residuals in nonlinear mixed models for repeated measures data

In this paper we analyse, using Monte Carlo simulation, the possible consequences of incorrect assumptions on the true structure of the random effects covariance matrix and the true correlation pattern of residuals, over the performance of an estimation method for nonlinear mixed models. The procedure under study is the well known linearization method due to Lindstrom and Bates (1990), implemented in the nlme library of S-Plus and R. Its performance is studied in terms of bias, mean square error (MSE), and true coverage of the associated asymptotic confidence intervals. Ignoring other criteria like the convenience of avoiding over parameterised models, it seems worst to erroneously assume some structure than do not assume any structure when this would be adequate.

Predicting the growth response to thinning for Scots pine stands using individual-tree growth models

Summary

Structure and energetics of mixed 4He-3He drops

Using a finite-range density functional, we have investigated the energetics and structural features of mixed helium clusters. The possibility of doping the cluster with a molecule of sulfur hexafluoride is also considered. It is seen that the repulsion introduced by the impurity strongly modifies the properties of the smallest drops. Although only a qualitative comparison is possible, the gross features displayed by our calculations are in agreement with recent experimental findings.

Fill-in seedlings in constituting the stocking of Scots pine stands in northern Finland

Summary

Quantized vortices in mixed 3He-4He drops

Using density functional theory, we investigate the structure of mixed 3HeN3-4HeN4 droplets with an embedded impurity (Xe atom or HCN molecule) which pins a quantized vortex line. We find that the dopant+vortex+4HeN4 complex, which in a previous work [F. Dalfovo et al., Phys. Rev. Lett. 85, 1028 (2000)] was found to be energetically stable below a critical size Ncr, is robust against the addition of 3He. While 3He atoms are distributed along the vortex line and on the surface of the 4He drop, the impurity is mostly coated by 4He atoms. Results for N4 = 500 and a number of 3He atoms ranging from 0 to 100 are presented, and the binding energy of the dopant to the vortex line is determined.

Shell structure in mixed 3He-4He droplets

Due to the immiscibility of 3He into 4He at very low temperatures, mixed helium droplets consist of a core of 4He atoms coated by a 3He layer whose thickness depends on the number of atoms of each isotope. When these numbers are such that the centrifugal kinetic energy of the 3He atoms is small and can be considered as a perturbation to the mean-field energy, a novel shell structure arises, with magic numbers different from these of pure 3He droplets. If the outermost shell is not completely filled, the valence atoms align their spins up to the maximum value allowed by the Pauli principle.

Soil fauna as an indicator of soil quality in forest stands, pasture and secondary forest

The interactions between soil invertebrates and environmental variations are relatively unknown in the assessment of soil quality. The objective of this study was to evaluate soil quality in areas with different soil management systems, based on soil fauna as indicator, in Além Paraíba, Minas Gerais, Brazil. The soil invertebrate community was sampled using pitfall traps, in the dry and rainy seasons, from areas with five vegetation types (acacia, mimosa, eucalyptus, pasture, and secondary forest). The abundance of organisms and the total and average richness, Shannon's diversity index, the Pielou uniformity index, and change index V were determined. The fauna was most abundant in the areas of secondary forest and mimosa plantations in the dry season (111.3 and 31.7 individuals per trap per day, respectively). In the rainy season, the abundance of organisms in the three vegetation types did not differ. The highest values of average and total richness were recorded in the secondary forest in the dry season and in the mimosa stand in the rainy season. Shannon's index ranged from 1.57 in areas with acacia and eucalyptus in the rainy season to 3.19 in the eucalyptus area in the dry season. The uniformity index was highest in forest stands (eucalyptus, acacia and mimosa) in the dry season, but higher in the rainy season in the pasture and secondary forest than in the forest stands. The change index V indicated that the percentage of extremely inhibited groups was lowest in the area with mimosa, both in the dry and rainy season (36 and 23 %, respectively). Of all forest stands, the mimosa area had the most abundant soil fauna.

Comparing Basal Area Diameter Distributions Estimated by Tree Species and for the Entire Stock in a Mixed Stand

Summary