Parameter estimation of Poisson generalized linear mixed models based on three different statistical principles : a simulation study

Generalized linear mixed models are flexible tools for modeling non-normal data and are useful for accommodating overdispersion in Poisson regression models with random effects. Their main difficulty resides in the parameter estimation because there is no analytic solution for the maximization of the marginal likelihood. Many methods have been proposed for this purpose and many of them are implemented in software packages. The purpose of this study is to compare the performance of three different statistical principles - marginal likelihood, extended likelihood, Bayesian analysis-via simulation studies. Real data on contact wrestling are used for illustration.

Equação de regressão linear múltipla para estimativa do erro experimental

Este trabalho teve por objetivo estimar equações de regressão linear múltipla tendo, como variáveis explicativas, as demais características avaliadas em experimento de milho e, como variáveis principais, a diferença mínima significativa em percentagem da média (DMS%) e quadrado médio do erro (QMe), para peso de grãos. Com 610 experimentos conduzidos na Rede de Ensaios Nacionais de Competição de Cultivares de Milho, realizados entre 1986 e 1996 (522 experimentos) e em 1997 (88 experimentos), estimaram-se duas equações de regressão, com os 522 experimentos, validando estas pela análise de regressão simples entre os valores reais e os estimados pelas equações, com os 88 restantes, observando que, para a DMS% a equação não estimava o mesmo valor que a fórmula original e, para o QMe, a equação poderia ser utilizada na estimação. Com o teste de Lilliefors, verificou-se que os valores do QMe aderiam à distribuição normal padrão e foi construída uma tabela de classificação dos valores do QMe, baseada nos valores observados na análise da variância dos experimentos e nos estimados pela equação de regressão.

Response surface models to predict broiler performance and applications for economic analysis

A study was carried out to elaborate response surface models using broiler performance data recovered from literature in order to predict performance and elaborate economic analyses. Nineteen studies published between 1995 and 2005 were retrieved using the systematic literature review method. Weight gain and feed conversion data were collected from eight studies that fulfilled the pre-established inclusion criteria, and a response surface model was adjusted using crude protein, environmental temperature, and age as independent variables. The models produced for weight gain (r² = 0.93) and feed conversion (r² = 0.85) were accurate, precise, and not biased. Protein levels, environmental temperature and age showed linear and quadratic effects on weight gain and feed conversion. There was no interaction between protein level and environmental temperature. Age and crude protein showed interaction for weight gain and feed conversion, whereas interaction between age and temperature was detected only for weight gain. It was possible to perform economic analyses to determine maximum profit as a function of the variables that were included in the model. It was concluded that the response surface models are effective to predict the performance of broiler chickens and allow the elaboration of economic analyses to optimize profit.

Models for the analysis of growth curves for rearing tinamous (Rhynchotus rufescens) in captivity

Growth curves models provide a visual assessment of growth as a function of time, and prediction body weight at a specific age. This study aimed at estimating tinamous growth curve using different models, and at verifying their goodness of fit. A total number 11,639 weight records from 411 birds, being 6,671 from females and 3,095 from males, was analyzed. The highest estimates of a parameter were obtained using Brody (BD), von Bertalanffy (VB), Gompertz (GP,) and Logistic function (LG). Adult females were 5.7% heavier than males. The highest estimates of b parameter were obtained in the LG, GP, BID, and VB models. The estimated k parameter values in decreasing order were obtained in LG, GP, VB, and BID models. The correlation between the parameters a and k showed heavier birds are less precocious than the lighter. The estimates of intercept, linear regression coefficient, quadratic regression coefficient, and differences between quadratic coefficient of functions and estimated ties of quadratic-quadratic-quadratic segmented polynomials (QQQSP) were: 31.1732 +/- 2.41339; 3.07898 +/- 0.13287; 0.02689 +/- 0.00152; -0.05566 +/- 0.00193; 0.02349 +/- 0.00107, and 57 and 145 days, respectively. The estimated predicted mean error values (PME) of VB, GP, BID, LG, and QQQSP models were, respectively, 0.8353; 0.01715; -0.6939; -2.2453; and -0.7544%. The coefficient of determination (RI) and least square error values (MS) showed similar results. In conclusion, the VB and the QQQSP models adequately described tinamous growth. The best model to describe tinamous growth was the Gompertz model, because it presented the highest R-2 values, easiness of convergence, lower PME, and the easiness of parameter biological interpretation.

Analysis of bone microarchitecture related to anthropometry in climateric women

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

Assessing relationships between genetic evaluations using robust regression with an application to holsteins in Uruguay

Globalization of dairy cattle breeding has created a need for international sire proofs. Some early methods for converting proofs from one population to another are based on simple linear regression. An alternative robust regression method based on the t-distribution is presented, and maximum likelihood and Bayesian techniques for analysis are described, including the situation in which some proofs are missing. Procedures were used to investigate the relationship between Holstein sire proofs obtained by two Uruguayan genetic evaluation programs. The results suggest that conversion equations developed from data including only sires having proofs in both populations can lead to distorted results, relative to estimates obtained using techniques for incomplete data. There was evidence of non-normality of regression residuals, which constitutes an additional source of bias. A robust estimator may not solve all problems, but can provide simple conversion equations that are less sensitive to outlying proofs and to departures from assumptions.

Comparison of random regression models to estimate genetic parameters for milk production in Guzerat (Bos indicus) cows

Random regression models have been widely used to estimate genetic parameters that influence milk production in Bos taurus breeds, and more recently in B. indicus breeds. With the aim of finding appropriate random regression model to analyze milk yield, different parametric functions were compared, applied to 20,524 test-day milk yield records of 2816 first-lactation Guzerat (B. indicus) cows in Brazilian herds. The records were analyzed by random regression models whose random effects were additive genetic, permanent environmental and residual, and whose fixed effects were contemporary group, the covariable cow age at calving (linear and quadratic effects), and the herd lactation curve. The additive genetic and permanent environmental effects were modeled by the Wilmink function, a modified Wilmink function (with the second term divided by 100), a function that combined third-order Legendre polynomials with the last term of the Wilmink function, and the Ali and Schaeffer function. The residual variances were modeled by means of 1, 4, 6, or 10 heterogeneous classes, with the exception of the last term of the Wilmink function, for which there were 1, from 0.20 to 0.33. Genetic correlations between adjacent records were high values (0.83-0.99), but they declined when the interval between the test-day records increased, and were negative between the first and last records. The model employing the Ali and Schaeffer function with six residual variance classes was the most suitable for fitting the data. © FUNPEC-RP.

Linear and undulating periodized strength plus aerobic training promote similar benefits and lead to improvement of insulin resistance on obese adolescents

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

Analysis of metabolic pools in broilers chicks

This paper shows the possibility of obtaining new parameters for the mathematical modelling of data on stable isotopes in biological systems and its application in obtaining data on metabolic pools of blood plasma, blood serum, liver and muscle of broilers. This theory states that the modelling of turnover used for studies of isotopic incorporation when the metabolism has a single metabolic pool is feasible by the technique of setting an exponential. However, when the metabolism has more than one metabolic pool, it is necessary to apply the linearization technique, linear regression adjustment and evaluation of the assumptions of regression to obtain the kinetic parameters such as half-life (T1/2) and isotope exchange rate (k). The application of this technique on carbon-13 data from 100 one-day-old chicks, with the change of diet composed of grains of the photosynthetic cycle of plants from C4 to C3, in broilers has enabled the discovery that the liver, blood plasma and blood serum have a single metabolic pool; however, the pectoral muscle has two metabolic pools. For the liver, blood plasma and blood serum, the half-life values were found by the exponential fit being T1/2 = 1.4 days with the rate of exchange of k = 0.502, T1/2 = 2.4 days with k = 0.293 and T1/2 = 2.0 days with k = 0.348, respectively. For the pectoral muscle, after linearization, the half-life values were found for T1/2(1) = 1.7 and T1/2(2) = 3 days, with exchange rates of k1 = 0.405 and k2 = 0.235, representing approximately 66 and 34 %, respectively.

Previsão de demanda de veículos automotores através do modelo de regressão linear múltipla

This study aimed to model a equation for the demand of automobiles and light commercial vehicles, based on the data from February 2007 to July 2014, through a multiple regression analysis. The literature review consists of an information collection of the history of automotive industry, and it has contributed to the understanding of the current crisis that affects this market, which consequence was a large reduction in sales. The model developed was evaluated by a residual analysis and also was used an adhesion test - F test - with a significance level of 5%. In addition, a coefficient of determination (R2) of 0.8159 was determined, indicating that 81.59% of the demand for automobiles and light commercial vehicles can be explained by the regression variables: interest rate, unemployment rate, broad consumer price index (CPI), gross domestic product (GDP) and tax on industrialized products (IPI). Finally, other ten samples, from August 2014 to May 2015, were tested in the model in order to validate its forecasting quality. Finally, a Monte Carlo Simulation was run in order to obtain a distribution of probabilities of future demands. It was observed that the actual demand in the period after the sample was in the range that was most likely to occur, and that the GDP and the CPI are the variable that have the greatest influence on the developed model

Previsão de demanda de veículos automotores através do modelo de regressão linear múltipla

This study aimed to model a equation for the demand of automobiles and light commercial vehicles, based on the data from February 2007 to July 2014, through a multiple regression analysis. The literature review consists of an information collection of the history of automotive industry, and it has contributed to the understanding of the current crisis that affects this market, which consequence was a large reduction in sales. The model developed was evaluated by a residual analysis and also was used an adhesion test - F test - with a significance level of 5%. In addition, a coefficient of determination (R2) of 0.8159 was determined, indicating that 81.59% of the demand for automobiles and light commercial vehicles can be explained by the regression variables: interest rate, unemployment rate, broad consumer price index (CPI), gross domestic product (GDP) and tax on industrialized products (IPI). Finally, other ten samples, from August 2014 to May 2015, were tested in the model in order to validate its forecasting quality. Finally, a Monte Carlo Simulation was run in order to obtain a distribution of probabilities of future demands. It was observed that the actual demand in the period after the sample was in the range that was most likely to occur, and that the GDP and the CPI are the variable that have the greatest influence on the developed model

Bartlett corrections in Birnbaum-Saunders nonlinear regression models

Lemonte and Cordeiro [Birnbaum-Saunders nonlinear regression models, Comput. Stat. Data Anal. 53 (2009), pp. 4441-4452] introduced a class of Birnbaum-Saunders (BS) nonlinear regression models potentially useful in lifetime data analysis. We give a general matrix Bartlett correction formula to improve the likelihood ratio (LR) tests in these models. The formula is simple enough to be used analytically to obtain several closed-form expressions in special cases. Our results generalize those in Lemonte et al. [Improved likelihood inference in Birnbaum-Saunders regressions, Comput. Stat. DataAnal. 54 (2010), pp. 1307-1316], which hold only for the BS linear regression models. We consider Monte Carlo simulations to show that the corrected tests work better than the usual LR tests.

Response plateau models fitting via isotonic regression

Within the nutritional context, the supplementation of microminerals in bird food is often made in quantities exceeding those required in the attempt to ensure the proper performance of the animals. The experiments of type dosage x response are very common in the determination of levels of nutrients in optimal food balance and include the use of regression models to achieve this objective. Nevertheless, the regression analysis routine, generally, uses a priori information about a possible relationship between the response variable. The isotonic regression is a method of estimation by least squares that generates estimates which preserves data ordering. In the theory of isotonic regression this information is essential and it is expected to increase fitting efficiency. The objective of this work was to use an isotonic regression methodology, as an alternative way of analyzing data of Zn deposition in tibia of male birds of Hubbard lineage. We considered the models of plateau response of polynomial quadratic and linear exponential forms. In addition to these models, we also proposed the fitting of a logarithmic model to the data and the efficiency of the methodology was evaluated by Monte Carlo simulations, considering different scenarios for the parametric values. The isotonization of the data yielded an improvement in all the fitting quality parameters evaluated. Among the models used, the logarithmic presented estimates of the parameters more consistent with the values reported in literature.

Influência da idade no comportamento da frequência cardíaca na transição repouso-exercício: uma análise por deltas e regressão linear

INTRODUÇÃO: As modificações da frequência cardíaca (FC) durante a transição repouso-exercício podem ser caracterizadas por meio da aplicação de cálculos matemáticos simples, como: deltas 0-10 e 0-30s para inferir sobre o sistema nervoso parassimpático, e delta e regressão linear aplicados no intervalo 60-240s para inferir sobre o sistema nervoso simpático. Assim, o objetivo deste estudo foi testar a hipótese de que indivíduos jovens e de meia-idade apresentam diferentes respostas da FC em exercício de intensidade moderada e intensa, com diferentes cálculos matemáticos. MÉTODOS: Homens aparentemente saudáveis, sendo sete de meia-idade e 10 jovens, foram submetidos a testes de carga constante de intensidade moderada e intensa. Foram calculados os deltas da FC nos períodos de 0-10s, 0-30s e 60-240s e a regressão linear simples no período de 60 a 240s. Os parâmetros obtidos na análise de regressão linear simples foram: intercepto e inclinação angular. Utilizou-se o teste Shapiro-Wilk para verificar a distribuição dos dados e o teste t não pareado para comparação entre os grupos. O nível de significância estatística considerado foi 5%. RESULTADOS: O valor do intercepto e do delta 0-10s foi menor no grupo meia-idade nas duas cargas e a inclinação do ângular foi menor no grupo meia-idade no exercício moderado. CONCLUSÃO: Os indivíduos jovens apresentam retirada vagal de maior magnitude no estágio inicial da resposta da FC durante exercício dinâmico em carga constante nas intensidades analisadas e maior velocidade de ajuste da resposta simpática em exercícios moderados.