Exploring nest destruction and bird mortality in mown Mediterranean dry grasslands: an increasing threat to grassland bird conservation

In recent years, haying has extended to Iberian Mediterranean dry grasslands potentially impacting on grassland bird ecology. We evaluated the impact of haying on a grassland bird community of South Portugal. Our main goals were: (1) to investigate the exposure of different species to haying, (2) to investigate potential removal of nests and dead birds from hayed fields by haying machinery using the ratio (REC) between the expected number of records and the number of records collected and (3) to link clutch destruction and bird mortality with haying management practices. Hayed fields were surveyed for signs of breeding and birds censused prior to mowing. Linear models were computed, linking the REC with haying machinery and sward properties. GLMs and model averaging were used to obtain models linking clutch destruction, bird mortality and haying management variables. Only 4 % of records evidenced successful nesting attempts (N = 177). REC evaluation suggested high nest or dead bird removal by the machinery, particularly in fields with lower vegetation biomass prior to cutting. Sickle bar mowers and one-rotor rotary rakes returned higher REC but lower probability of found nests removed from the original nesting sites comparatively to discs mowers and wheel rakes. Higher probabilities of mortality events were found in fields mown earlier (but not in all years). On the other hand, lower mortality was found in fields raked with two-rotor rotary rakes. Delayed haying, silage production in temporary crops and the use haying machinery enabling simultaneously mowing and gathering hay in lines are discussed as management alternatives.

Between and within-year effects of haying on grassland bird

In recent years, haying has extended to Iberian Mediterranean dry grasslands potentially threatening grassland birds. We evaluate the between and within-year effects of haying on grassland birds in Alentejo region, Portugal. Our main goals were: (1) to investigate variations on bird abundance and species richness in the fields hayed, with respect to past haying events occurred in a field and its surroundings and (2) to investigate the shifts in bird abundance, species richness and spatial dynamics resulting from haying a field and its surrounding area in a given year. We conducted grassland bird censuses during the breeding season through point counts from 2012 to 2015. The relationship between bird abundance/richness and past haying events was investigated using Generalized Linear Models whereas within-year effects of haying were analysed using Generalized Additive Models. Bird abundance in a field was positively related with the surface hayed in the vicinity of that field in the previous year. However, contrasting yearly effects were found for non passerines. Also, some species prefer fields with less haying events or surface hayed, whereas others occur mostly in fields frequently managed for haying. Haying a field leads, in the short term, to its abandonment by birds, and thus to a decrease in bird abundance and, for some species, to spatial concentration in surrounding fields offering suitable habitat. We conclude that within-year effects of haying have higher impact on grassland birds than between-year effects. Maintaining haying at low levels by rotating haying yearly through the different fields in each farm and using partial haying may be an adequate way to ensure an effective management of grassland bird populations.

Modelação do cancro da mama na região do Alentejo

Estudos epidemiológicos são estudos estatísticos onde se procura relacionar ocorrências de eventos de saúde com uma ou várias causas específicas. A importância que os modelos epidemiológicos assumem hoje no estudo de doenças de foro oncológico, em particular no estabelecimento das suas etiologias, é incontornável. Segundo Ogden, J. (1999) o cancro é "um crescimento incontrolável de células anormais que produzem tumores chamados neoplasias". Estes tumores podem ter origem benigna (não se espalham pelo corpo) ou maligna (apresentam metastização de outros órgãos). Sendo uma doença actual, com uma elevada taxa de incidência em Portugal quando comparada com outras doenças (Instituto Nacional de Estatística- INE, 2009), aumentando esta taxa com a idade tal como refere Marques, L. (2003), podendo ocorrer o diagnóstico desta doença em qualquer idade. De acordo com INE (2000) pode dizer-se que o cancro está entre as três principais causas de morte em Portugal, registando-se um aumento progressivo do seu peso proporcional, sendo o cancro da mama o tipo de cancro mais comum entre as mulheres e uma das doenças com maior impacto na nossa sociedade. O objectivo principal deste trabalho é a estimação e modelação do risco de contrair uma doença de natureza não contagiosa e rara (neste caso, cancro da mama), usando dados da região do Alentejo. Pretende-se fazer um apanhado das metodologias mais empregues nesta área e aplicá-las na prática, com ênfase nos estudos caso-controlo e nos modelos lineares generalizados (GLM) - mais concretamente regressão logística. Os estudos caso-controlo são usados para identificar os factores que podem contribuir para uma condição médica, comparando indivíduos que têm essa condição (casos) com pacientes que não têm a condição, mas que de resto são semelhantes (controlos). Neste trabalho utilizou-se essa metodologia para estudar a associação entre o viver em ambiente rural/urbano e o cancro da mama. Tendo em conta que o objectivo principal deste estudo se prende com o estudo da relação entre variáveis, mais propriamente, análise de influência que uma ou mais variáveis (explicativas) têm sobre uma variável de interesse (resposta), para esse efeito são estudados os modelos lineares generalizados - GLM - unificados na mesma moldura teórica pela primeira vez por Nelder & Wedderburn (1972) - e, posteriormente aplicados ao conjunto de dados sobre cancro da mama na Região do Alentejo. O presente trabalho pretende assim, ser um contributo na identificação de factores de risco do cancro da mama na região do Alentejo. ABSTRACT: Epidemiological studies are statistical studies where attempts to relate occurrences of health events with one or more specific causes. The importance of epidemiological models that are far in the study of diseases of cancer forum, particularly in establishing their etiology, is inescapable. According to Ogden, J. (1999) cancer is "an incontrollable growth of abnormal cells that produce tumors called cancer". These tumors may be benign (not spread throughout the body) or malignant (show metastasis to other organs). Being a current illness with a high incidence rate in Portugal compared with the same respect to other diseases (National Statistics 1nstitute -1NE, 2009) having an increasing rate with age as mentioned Marques, L. (2003), and can possibly be diagnosed at any age. According to 1NE (2000) the cancer is among the top three causes of death in Portugal and there is a progressive increase of its proportional weight. Breast cancer is the most common form of cancer among women and the diseases with major impact in our society. The main objective of this work is to model and estimate the risk of contracting a non-contagious and rare disease (in this case, breast cancer), using data from the Alentejo region. It is intended to summarize some of the methodologies employed in this area and apply them in practice, with emphasis on case-control studies and generalized linear models (GLM) - more specifically the logistic regression. The case-control studies are used to identify factors that may contribute to a medical condition, comparing individuals who have this condition (cases) with patients who have not the condition but that are otherwise similar (controls). ln this work we used this methodology to study the association between living in a rural/urban and breast cancer. Given that the main objective of this study rather relates to the study of the relationship between variables to analyze the influence that one or more variables (explanatory) have on a variable (response), for this purpose we study the generalized linear models - GLM - first unified in the same theoretical framework by Nelder and Wedderburn (1972) and subsequently applied to the data set on breast cancer in the Alentejo region. This work intends to be a contribution in identifying risk factors for breast cancer in the Alentejo region.

Different strategies to estimate genetic parameters for the rank of Santa Ines sheep in agricultural-shows.

2016

Robust linear mixed models with skew-normal independent distributions from a Bayesian perspective

Linear mixed models were developed to handle clustered data and have been a topic of increasing interest in statistics for the past 50 years. Generally. the normality (or symmetry) of the random effects is a common assumption in linear mixed models but it may, sometimes, be unrealistic, obscuring important features of among-subjects variation. In this article, we utilize skew-normal/independent distributions as a tool for robust modeling of linear mixed models under a Bayesian paradigm. The skew-normal/independent distributions is an attractive class of asymmetric heavy-tailed distributions that includes the skew-normal distribution, skew-t, skew-slash and the skew-contaminated normal distributions as special cases, providing an appealing robust alternative to the routine use of symmetric distributions in this type of models. The methods developed are illustrated using a real data set from Framingham cholesterol study. (C) 2009 Elsevier B.V. All rights reserved.

Leverage analysis for linear mixed models

We consider a generalized leverage matrix useful for the identification of influential units and observations in linear mixed models and show how a decomposition of this matrix may be employed to identify high leverage points for both the marginal fitted values and the random effect component of the conditional fitted values. We illustrate the different uses of the two components of the decomposition with a simulated example as well as with a real data set.

Likelihood ratio tests for variance components in linear mixed models

Although the asymptotic distributions of the likelihood ratio for testing hypotheses of null variance components in linear mixed models derived by Stram and Lee [1994. Variance components testing in longitudinal mixed effects model. Biometrics 50, 1171-1177] are valid, their proof is based on the work of Self and Liang [1987. Asymptotic properties of maximum likelihood estimators and likelihood tests under nonstandard conditions. J. Amer. Statist. Assoc. 82, 605-610] which requires identically distributed random variables, an assumption not always valid in longitudinal data problems. We use the less restrictive results of Vu and Zhou [1997. Generalization of likelihood ratio tests under nonstandard conditions. Ann. Statist. 25, 897-916] to prove that the proposed mixture of chi-squared distributions is the actual asymptotic distribution of such likelihood ratios used as test statistics for null variance components in models with one or two random effects. We also consider a limited simulation study to evaluate the appropriateness of the asymptotic distribution of such likelihood ratios in moderately sized samples. (C) 2008 Elsevier B.V. All rights reserved.

Local Influence Analysis for Skew-Normal Linear Mixed Models

In this article, we consider local influence analysis for the skew-normal linear mixed model (SN-LMM). As the observed data log-likelihood associated with the SN-LMM is intractable, Cook`s well-known approach cannot be applied to obtain measures of local influence. Instead, we develop local influence measures following the approach of Zhu and Lee (2001). This approach is based on the use of an EM-type algorithm and is measurement invariant under reparametrizations. Four specific perturbation schemes are discussed. Results obtained for a simulated data set and a real data set are reported, illustrating the usefulness of the proposed methodology.

Feasible estimation of generalized linear mixed models (GLMM) with weak dependency between groups

This paper presents a two-step pseudo likelihood estimation technique for generalized linear mixed models with the random effects being correlated between groups. The core idea is to deal with the intractable integrals in the likelihood function by multivariate Taylor's approximation. The accuracy of the estimation technique is assessed in a Monte-Carlo study. An application of it with a binary response variable is presented using a real data set on credit defaults from two Swedish banks. Thanks to the use of two-step estimation technique, the proposed algorithm outperforms conventional pseudo likelihood algorithms in terms of computational time.

Likelihood prediction for generalized linear mixed models under covariate uncertainty

This paper presents the techniques of likelihood prediction for the generalized linear mixed models. Methods of likelihood prediction is explained through a series of examples; from a classical one to more complicated ones. The examples show, in simple cases, that the likelihood prediction (LP) coincides with already known best frequentist practice such as the best linear unbiased predictor. The paper outlines a way to deal with the covariate uncertainty while producing predictive inference. Using a Poisson error-in-variable generalized linear model, it has been shown that in complicated cases LP produces better results than already know methods.

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.

Generalized linear mixed models for the genetic evaluation of binary reproductive traits: a simulation study

The objective of this study was to evaluate the use of probit and logit link functions for the genetic evaluation of early pregnancy using simulated data. The following simulation/analysis structures were constructed: logit/logit, logit/probit, probit/logit, and probit/probit. The percentages of precocious females were 5, 10, 15, 20, 25 and 30% and were adjusted based on a change in the mean of the latent variable. The parametric heritability (h²) was 0.40. Simulation and genetic evaluation were implemented in the R software. Heritability estimates (ĥ²) were compared with h² using the mean squared error. Pearson correlations between predicted and true breeding values and the percentage of coincidence between true and predicted ranking, considering the 10% of bulls with the highest breeding values (TOP10) were calculated. The mean ĥ² values were under- and overestimated for all percentages of precocious females when logit/probit and probit/logit models used. In addition, the mean squared errors of these models were high when compared with those obtained with the probit/probit and logit/logit models. Considering ĥ², probit/probit and logit/logit were also superior to logit/probit and probit/logit, providing values close to the parametric heritability. Logit/probit and probit/logit presented low Pearson correlations, whereas the correlations obtained with probit/probit and logit/logit ranged from moderate to high. With respect to the TOP10 bulls, logit/probit and probit/logit presented much lower percentages than probit/probit and logit/logit. The genetic parameter estimates and predictions of breeding values of the animals obtained with the logit/logit and probit/probit models were similar. In contrast, the results obtained with probit/logit and logit/probit were not satisfactory. There is need to compare the estimation and prediction ability of logit and probit link functions.

On the Behaviour of Marginal and Conditional Akaike Information Criteria in Linear Mixed Models

In linear mixed models, model selection frequently includes the selection of random effects. Two versions of the Akaike information criterion (AIC) have been used, based either on the marginal or on the conditional distribution. We show that the marginal AIC is no longer an asymptotically unbiased estimator of the Akaike information, and in fact favours smaller models without random effects. For the conditional AIC, we show that ignoring estimation uncertainty in the random effects covariance matrix, as is common practice, induces a bias that leads to the selection of any random effect not predicted to be exactly zero. We derive an analytic representation of a corrected version of the conditional AIC, which avoids the high computational cost and imprecision of available numerical approximations. An implementation in an R package is provided. All theoretical results are illustrated in simulation studies, and their impact in practice is investigated in an analysis of childhood malnutrition in Zambia.

Algebraic structure for interaction on mixed models

Binary operations on commutative Jordan algebras, CJA, can be used to study interactions between sets of factors belonging to a pair of models in which one nests the other. It should be noted that from two CJA we can, through these binary operations, build CJA. So when we nest the treatments from one model in each treatment of another model, we can study the interactions between sets of factors of the first and the second models.