Bayesian longitudinal data analysis with mixed models and thick-tailed distributions using MCMC

Linear mixed effects models are frequently used to analyse longitudinal data, due to their flexibility in modelling the covariance structure between and within observations. Further, it is easy to deal with unbalanced data, either with respect to the number of observations per subject or per time period, and with varying time intervals between observations. In most applications of mixed models to biological sciences, a normal distribution is assumed both for the random effects and for the residuals. This, however, makes inferences vulnerable to the presence of outliers. Here, linear mixed models employing thick-tailed distributions for robust inferences in longitudinal data analysis are described. Specific distributions discussed include the Student-t, the slash and the contaminated normal. A Bayesian framework is adopted, and the Gibbs sampler and the Metropolis-Hastings algorithms are used to carry out the posterior analyses. An example with data on orthodontic distance growth in children is discussed to illustrate the methodology. Analyses based on either the Student-t distribution or on the usual Gaussian assumption are contrasted. The thick-tailed distributions provide an appealing robust alternative to the Gaussian process for modelling distributions of the random effects and of residuals in linear mixed models, and the MCMC implementation allows the computations to be performed in a flexible manner.

Additive genetic relationship of longevity with fertility and production traits in Nellore cattle based on bivariate models

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Modelling of fatigue crack growth following overloads

In variable-amplitude loading there are interaction effects between the loading history and the crack propagation rate. The most important of these effects is the retardation in the crack propagation, which may raise the life of the cracked structureconsiderably. The main objective of this research is to analyse and quantify the retardation of crack propagation in a thin plate of the high-resistance aluminium alloy 2024-T3, comparing the results obtained from the mathematical models proposed to account for the retardation effect. The specimens were tested under high-low loading sequences, for different crack sizes and overload ratios. A simplified model was developed, based on crack closure theory, that could represent the crack behaviour during retardation very well. © 1991.

An improved three-dimensional model for growth of oxide films induced by laser heating

In this paper we consider a three-dimensional heat diffusion model to explain the growth of oxide films which takes place when a laser beam is shined on and heats a metallic layer deposited on a glass substrate in a normal atmospheric environment. In particular, we apply this model to the experimental results obtained for the dependence of the oxide layer thickness on the laser density power for growth of TiO2 films grown on Ti-covered glass slides. We show that there is a very good agreement between the experimental results and the theoretical predictions from our proposed three-dimensional model, improving the results obtained with the one-dimensional heat diffusion model previously reported. Our theoretical results also show the occurrence of surface cooling between consecutive laser pulses, and that the oxide track surface profile closely follows the spatial laser profile indicating that heat diffusive effects can be neglected in the growth of oxide films by laser heating. © 2001 Elsevier Science B.V.

One-dimensional analytical model for oxide thin film growth on Ti metal layers during laser heating in air

This paper presents the theoretical and experimental results for oxide thin film growth on titanium films previously deposited over glass substrate. Ti films of thickness 0.1 μm were heated by Nd:YAG laser pulses in air. The oxide tracks were created by moving the samples with a constant speed of 2 mm/s, under the laser action. The micro-topographic analysis of the tracks was performed by a microprofiler. The results taken along a straight line perpendicular to the track axis revealed a Gaussian profile that closely matches the laser's spatial mode profile, indicating the effectiveness of the surface temperature gradient on the film's growth process. The sample's micro-Raman spectra showed two strong bands at 447 and 612 cm -1 associated with the TiO 2 structure. This is a strong indication that thermo-oxidation reactions took place at the Ti film surface that reached an estimated temperature of 1160 K just due to the action of the first pulse. The results obtained from the numerical integration of the analytical equation which describes the oxidation rate (Wagner equation) are in agreement with the experimental data for film thickness in the high laser intensity region. This shows the partial accuracy of the one-dimensional model adopted for describing the film growth rate. © 2001 Elsevier Science B.V.

Estimates of covariance functions for growth from birth to 630 days of age in Nelore cattle

Weight records of Brazilian Nelore cattle, from birth to 630 d of age, recorded every 3 mo, were analyzed using random regression models. Independent variables were Legendre polynomials of age at recording. The model of analysis included contemporary groups as fixed effects and age of dam as a linear and quadratic covariable. Mean trends were modeled through a cubic regression on orthogonal polynomials of age. Up to four sets of random regression coefficients were fitted for animals' direct and maternal, additive genetic, and permanent environmental effects. Changes in measurement error variances with age were modeled through a variance function. Orders of polyno-mial fit from three to six were considered, resulting in up to 77 parameters to be estimated. Models fitting random regressions modeled the pattern of variances in the data adequately, with estimates similar to those from corresponding univariate analysis. Direct heritability estimates decreased after birth and tended to be lowest at ages at which maternal effect estimates tended to be highest. Maternal heritability estimates increased after birth to a peak around 110 to 120 d of age and decreased thereafter. Additive genetic direct correlation estimates between weights at standard ages (birth, weaning, yearling, and final weight) were moderate to high and maternal genetic and environmental correlations were consistently high. © 2001 American Society of Animal Science. All rights reserved.

Estimates of covariance functions for growth of Nelore cattle applying a parametric correlation structure to model within-animal correlations

A total of 20,065 weights recorded on 3016 Nelore animals were used to estimate covariance functions for growth from birth to 630 days of age, assuming a parametric correlation structure to model within-animal correlations. The model of analysis included fixed effects of contemporary groups and age of dam as quadratic covariable. Mean trends were taken into account by a cubic regression on orthogonal polynomials of animal age. Genetic effects of the animal and its dam and maternal permanent environmental effects were modelled by random regressions on Legendre polynomials of age at recording. Changes in direct permanent environmental effect variances were modelled by a polynomial variance function, together with a parametric correlation function to account for correlations between ages. Stationary and nonstationary models were used to model within-animal correlations between different ages. Residual variances were considered homogeneous or heterogeneous, with changes modelled by a step or polynomial function of age at recording. Based on Bayesian information criterion, a model with a cubic variance function combined with a nonstationary correlation function for permanent environmental effects, with 49 parameters to be estimated, fitted best. Modelling within-animal correlations through a parametric correlation structure can describe the variation pattern adequately. Moreover, the number of parameters to be estimated can be decreased substantially compared to a model fitting random regression on Legendre polynomial of age. © 2004 Elsevier B.V. All rights reserved.

Modeling energy utilization and growth parameter description for broiler chickens

Two experiments were conducted to develop and evaluate a model to estimate ME requirements and determine Gompertz growth parameters for broilers. The first experiment was conducted to determine maintenance energy requirements and the efficiencies of energy utilization for fat and protein deposition. Maintenance ME (ME m) requirements were estimated to be 157.8, 112.1, and 127.2 kcal of ME/kg 0.75 per day for broilers at 13, 23, and 32°C, respectively. Environmental temperature (T) had a quadratic effect on maintenance requirements (ME m = 307.87 - 15.63T + 0.3105T 2; r 2= 0.93). Energy requirements for fat and protein deposition were estimated to be 13.52 and 12.59 kcal of ME/g, respectively. Based on these coefficients, a model was developed to calculate daily ME requirements: ME = BW 0.75 (307.87 - 15.63T + 0.3105 T 2) + 13.52 G f + 12.59 G p. This model considers live BW, the effects of environmental temperature, and fractional fat (G f) and protein (G p) deposition. The second experiment was carried out to estimate the growth parameters of Ross broilers and to collect data to evaluate the ME requirement model proposed. Live BW, empty feather-free carcass, weight of the feathers, and carcass chemical compositions were analyzed until 16 wk of age. Parameters of Gompertz curves for each component were estimated. Males had higher growth potential and higher capacity to deposit nutrients than females, except for fat deposition. Data of BW and body composition collected in this experiment were fitted into the energy model proposed herein and the equations described by Emmans (1989) and Chwalibog (1991). The daily ME requirements estimated by the model determined in this study were closer to the ME intake observed in this trial compared with other models. ©2005 Poultry Science Association, Inc.

Remarks on orthotropic elastic models applied to wood

Wood is generally considered an anisotropic material. In terms of engineering elastic models, wood is usually treated as an orthotropic material. This paper presents an analysis of two principal anisotropic elastic models that are usually applied to wood. The first one, the linear orthotropic model, where the material axes L (Longitudinal), R(radial) and T(tangential) are coincident with the Cartesian axes (x, y, z), is more accepted as wood elastic model. The other one, the cylindrical orthotropic model is more adequate of the growth caracteristics of wood but more mathematically complex to be adopted in practical terms. Specifically due to its importance in wood elastic parameters, this paper deals with the fiber orientation influence in these models through adequate transformation of coordinates. As a final result, some examples of the linear model, which show the variation of elastic moduli, i.e., Young's modulus and shear modulus, with fiber orientation are presented.

Genetic effects on preweaning weight gain of Nelore-Hereford calves according to different models and estimation methods

Additive and nonadditive genetic effects on preweaning weight gain (PWG) of a commercial crossbred population were estimated using different genetic models and estimation methods. The data set consisted of 103,445 records on purebred and crossbred Nelore-Hereford calves raised under pasture conditions on farms located in south, southeast, and middle west Brazilian regions. In addition to breed additive and dominance effects, the models including different epistasis covariables were tested. Models considering joint additive and environment (latitude) by genetic effects interactions were also applied. In a first step, analyses were carried out under animal models. In a second step, preadjusted records were analyzed using ordinary least squares (OLS) and ridge regression (RR). The results reinforced evidence that breed additive and dominance effects are not sufficient to explain the observed variability in preweaning traits of Bos taurus x Bos indicus calves, and that genotype x environment interaction plays an important role in the evaluation of crossbred calves. Data were ill-conditioned to estimate the effects of genotype x environment interactions. Models including these effects presented multicolinearity problems. In this case, RR seemed to be a powerful tool for obtaining more plausible and stable estimates. Estimated prediction error variances and variance inflation factors were drastically reduced, and many effects that were not significant under ordinary least squares became significant under RR. Predictions of PWG based on RR estimates were more acceptable from a biological perspective. In temperate and subtropical regions, calves with intermediate genetic compositions (close to 1/2 Nelore) exhibited greater predicted PWG. In the tropics, predicted PWG increased linearly as genotype got closer to Nelore. ©2006 American Society of Animal Science. All rights reserved.

Structural change and productivity growth, 20 years later: old problems, new opportunities

Includes bibliography

Microstructural effects on fatigue crack growth behavior of a microalloyed steel

Thermal transformations on microalloyed steels can produce multiphase microstructures with different amounts of ferrite, martensite, bainite and retained austenite. These different phases, with distinct morphologies, are determinant of the mechanical behavior of the steel and can, for instance, affect the crack path or promote crack shielding, thus resulting in changes on its propagation rate under cyclic loading. The aim of the present work is to evaluate the effects of microstructure on the tensile strength and fatigue crack growth (FCG) behaviour of a 0.08%C-1,5%Mn (wt. pct.) microalloyed steel, recently developed by a Brazilian steel maker under the designation of RD480. This steel is being considered as a promising alternative to replace low carbon steel in wheel components for the automotive industry. Various microstructural conditions were obtained by means of heat treatments followed by water quench, in which the material samples were kept at the temperatures of 800, 950 and 1200 °C. In order to describe the FCG behavior, two models were tested: the conventional Paris equation and a new exponential equation developed for materials showing non-linear FCG behavior. The results allowed correlating the tensile properties and crack growth resistance to the microstructural features. It is also shown that the Region II FCG curves of the dual and multiphase microstructural conditions present crack growth transitions that are better modeled by dividing them in two parts. The fracture surfaces of the fatigued samples were observed via scanning electron microscopy in order to reveal the fracture mechanisms presented by the various material conditions. © 2010 Published by Elsevier Ltd.

Alternative measures of potential economic growth in Latin America

Includes bibliography

Balance of payments constrained growth within a consistent stock-flow framework: an application to the economies of CARICOM

Includes bibliography

What can we say about trade and growth when trade becomes a complex system?

Includes bibliography