Point estimates and confidence regions for sequential trials involving selection

A number of authors have proposed clinical trial designs involving the comparison of several experimental treatments with a control treatment in two or more stages. At the end of the first stage, the most promising experimental treatment is selected, and all other experimental treatments are dropped from the trial. Provided it is good enough, the selected experimental treatment is then compared with the control treatment in one or more subsequent stages. The analysis of data from such a trial is problematic because of the treatment selection and the possibility of stopping at interim analyses. These aspects lead to bias in the maximum-likelihood estimate of the advantage of the selected experimental treatment over the control and to inaccurate coverage for the associated confidence interval. In this paper, we evaluate the bias of the maximum-likelihood estimate and propose a bias-adjusted estimate. We also propose an approach to the construction of a confidence region for the vector of advantages of the experimental treatments over the control based on an ordering of the sample space. These regions are shown to have accurate coverage, although they are also shown to be necessarily unbounded. Confidence intervals for the advantage of the selected treatment are obtained from the confidence regions and are shown to have more accurate coverage than the standard confidence interval based upon the maximum-likelihood estimate and its asymptotic standard error.

Estimation following selection of the largest of two normal means

This paper considers the problem of estimation when one of a number of populations, assumed normal with known common variance, is selected on the basis of it having the largest observed mean. Conditional on selection of the population, the observed mean is a biased estimate of the true mean. This problem arises in the analysis of clinical trials in which selection is made between a number of experimental treatments that are compared with each other either with or without an additional control treatment. Attempts to obtain approximately unbiased estimates in this setting have been proposed by Shen [2001. An improved method of evaluating drug effect in a multiple dose clinical trial. Statist. Medicine 20, 1913–1929] and Stallard and Todd [2005. Point estimates and confidence regions for sequential trials involving selection. J. Statist. Plann. Inference 135, 402–419]. This paper explores the problem in the simple setting in which two experimental treatments are compared in a single analysis. It is shown that in this case the estimate of Stallard and Todd is the maximum-likelihood estimate (m.l.e.), and this is compared with the estimate proposed by Shen. In particular, it is shown that the m.l.e. has infinite expectation whatever the true value of the mean being estimated. We show that there is no conditionally unbiased estimator, and propose a new family of approximately conditionally unbiased estimators, comparing these with the estimators suggested by Shen.

Effects of fungicide dose and mixtures on selection for triazole resistance in Mycosphaerella graminicola under field conditions

The effects of varying doses of fungicides, alone or in mixtures, on selection for triazole resistance were examined under field conditions. Two experiments were conducted using the triazole fungicide fluquinconazole with the strobilurin fungicide azoxystrobin as a mixture partner. Inoculated wheat plots with a known ratio of more sensitive to less sensitive isolates of the leaf blotch fungus Mycosphaerella graminicola were sprayed with fungicide and sampled once symptoms had appeared. Selection for fluquinconazole resistance increased in proportion to the dose, up to one-half of the full dose (the maximum tested) in both experiments. At the higher doses of fluquinconazole, the addition of azoxystrobin was associated with a decrease in selection (nonsignificant in the first experiment) for triazole resistance. Control by low doses of fluquinconazole was increased by mixture with azoxystrobin, but at higher doses mixture with azoxystrobin sometimes decreased control, so that reduced selection was obtained at the cost of some reduction in control. The effects on resistance are not necessarily general consequences of mixing fungicides, and suggest that the properties of any specific mixture may need to be demonstrated experimentally. Selection was inversely related to control in the unmixed treatments in both experiments, but the relationship was weaker in the mixtures with azoxystrobin.

Orthogonal forward selection for constructing the radial basis function network with tunable nodes

An orthogonal forward selection (OFS) algorithm based on the leave-one-out (LOO) criterion is proposed for the construction of radial basis function (RBF) networks with tunable nodes. This OFS-LOO algorithm is computationally efficient and is capable of identifying parsimonious RBF networks that generalise well. Moreover, the proposed algorithm is fully automatic and the user does not need to specify a termination criterion for the construction process.

Construction of tunable radial basis function networks using orthogonal forward selection

An orthogonal forward selection (OFS) algorithm based on leave-one-out (LOO) criteria is proposed for the construction of radial basis function (RBF) networks with tunable nodes. Each stage of the construction process determines an RBF node, namely, its center vector and diagonal covariance matrix, by minimizing the LOO statistics. For regression application, the LOO criterion is chosen to be the LOO mean-square error, while the LOO misclassification rate is adopted in two-class classification application. This OFS-LOO algorithm is computationally efficient, and it is capable of constructing parsimonious RBF networks that generalize well. Moreover, the proposed algorithm is fully automatic, and the user does not need to specify a termination criterion for the construction process. The effectiveness of the proposed RBF network construction procedure is demonstrated using examples taken from both regression and classification applications.

Genotypic variation in photosynthetic and leaf traits in cocoa

The photosynthetic characteristics of eight contrasting cocoa genotypes were studied with the aim of examining genotypic variation in maximum (light-saturated) photosynthetic rates, light-response curve parameters and water use efficiency. Photosynthetic traits were derived from single leaf gas exchange measurements using a portable infra-red gas analyser. All measurements were conducted in a common greenhouse environment. Significant variation was observed in light-saturated photosynthesis ranging from 3.4 to 5.7 µmol CO2 m-2 s-1 for the clones IMC 47 and SCA 6, respectively. Furthermore, analyses of photosynthetic light response curves indicated genotypic differences in light saturation point and quantum efficiency (i.e. the efficiency of light use). Stomatal conductance was a significant factor underlying genotypic differences in assimilation. Genotypic variation was also observed in a number of leaf traits, including specific leaf area (the ratio of leaf area to leaf weight), chlorophyll concentration and nitrogen content. There was a positive correlation between leaf nitrogen per unit area and light-saturated photosynthesis. Water use efficiency, defined as the ratio of photosynthetic rate to transpiration rate, also varied significantly between clones (ranging from 3.1 mmol mol-1 H2O for the clone IMC 47 to 4.2 mmol mol-1 H2O for the clone ICS 1). Water use efficiency was a negative function of specific leaf area, suggesting that low specific leaf area might be a useful criterion for selection for increased water use efficiency. It is concluded that both variation in water use efficiency and the photosynthetic response to light have the potential to be exploited in breeding programmes.

Mitochondrial sequence data and Dipsacales phylogeny: Mixed models, partitioned Bayesian analyses, and model selection

Phylogenetic analyses of chloroplast DNA sequences, morphology, and combined data have provided consistent support for many of the major branches within the angiosperm, clade Dipsacales. Here we use sequences from three mitochondrial loci to test the existing broad scale phylogeny and in an attempt to resolve several relationships that have remained uncertain. Parsimony, maximum likelihood, and Bayesian analyses of a combined mitochondrial data set recover trees broadly consistent with previous studies, although resolution and support are lower than in the largest chloroplast analyses. Combining chloroplast and mitochondrial data results in a generally well-resolved and very strongly supported topology but the previously recognized problem areas remain. To investigate why these relationships have been difficult to resolve we conducted a series of experiments using different data partitions and heterogeneous substitution models. Usually more complex modeling schemes are favored regardless of the partitions recognized but model choice had little effect on topology or support values. In contrast there are consistent but weakly supported differences in the topologies recovered from coding and non-coding matrices. These conflicts directly correspond to relationships that were poorly resolved in analyses of the full combined chloroplast-mitochondrial data set. We suggest incongruent signal has contributed to our inability to confidently resolve these problem areas. (c) 2007 Elsevier Inc. All rights reserved.

Generating segmented meshes from textured color images

This paper presents a new framework for generating triangular meshes from textured color images. The proposed framework combines a texture classification technique, called W-operator, with Imesh, a method originally conceived to generate simplicial meshes from gray scale images. An extension of W-operators to handle textured color images is proposed, which employs a combination of RGB and HSV channels and Sequential Floating Forward Search guided by mean conditional entropy criterion to extract features from the training data. The W-operator is built into the local error estimation used by Imesh to choose the mesh vertices. Furthermore, the W-operator also enables to assign a label to the triangles during the mesh construction, thus allowing to obtain a segmented mesh at the end of the process. The presented results show that the combination of W-operators with Imesh gives rise to a texture classification-based triangle mesh generation framework that outperforms pixel based methods. Crown Copyright (C) 2009 Published by Elsevier Inc. All rights reserved.

Model selection, estimation and forecasting in VAR models with short-run and long-run restrictions

We study the joint determination of the lag length, the dimension of the cointegrating space and the rank of the matrix of short-run parameters of a vector autoregressive (VAR) model using model selection criteria. We consider model selection criteria which have data-dependent penalties for a lack of parsimony, as well as the traditional ones. We suggest a new procedure which is a hybrid of traditional criteria and criteria with data-dependant penalties. In order to compute the fit of each model, we propose an iterative procedure to compute the maximum likelihood estimates of parameters of a VAR model with short-run and long-run restrictions. Our Monte Carlo simulations measure the improvements in forecasting accuracy that can arise from the joint determination of lag-length and rank, relative to the commonly used procedure of selecting the lag-length only and then testing for cointegration.

Comparison of selection criteria for pre-weaning growth traits of Nelore cattle

Genetic parameters were estimated for pre-weaning average daily gain (ADG) and number of days to gain 160 kg from birth to weaning (D 160) of Nelore cattle. Ranks of animals were compared for these traits. Heritability estimates were 0.17 and 0.10 for ADG (direct and maternal), and 0.14 and 0.09, for D 160 (direct and maternal). Rank correlations between expected breeding values (EBV) were 0.97 and 0.95, for direct and maternal effects, respectively. Despite similar heritability estimates and high rank correlations, results showed that changes in rank could happen when choosing the best animals according to EBV for D 160 or ADG. There were evidences that sires selected using D 160 would produce progeny that achieve a specified market weight at an earlier age and would be more uniform, since this criterion is calculated as a harmonic mean function. (C) 2003 Elsevier B.V. All rights reserved.

Selection for higher body weight in Nelore cattle is effective in achieving an increase of longissimus muscle area without reducing subcutaneous fat thickness

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

Estimativa de parâmetros genéticos, fenotípicos e ambientes para as produções de leite no dia do controle e em 305 dias de lactação de vacas da raça Gir

Dados de 32.779 controles mensais, de 3.605 lactações em 305 dias (PL305), de 2.082 vacas Gir, filhas de 281 touros, com partos ocorridos de 1987 a 1999, em 11 rebanhos, foram usados com o objetivo de verificar a viabilidade de utilização da produção de leite no dia do controle (PLDC1 a PLDC10) em avaliações genéticas da raça Gir. Foram realizadas análises bivariadas entre as PLDC1 a PLDC10 e PL305, usando para estimar os componentes de (co)variâncias o método de máxima verossimilhança restrita, sob modelo animal, incluindo as três primeiras lactações como medidas repetidas de uma mesma vaca, diferenciadas conforme o grupo contemporâneo de rebanho-ano-estação, de acordo com a idade da vaca ao parto e o intervalo parto-primeiro controle na PLDC1. As médias observadas e os respectivos desvios-padrão (kg) para PLDC1 a PLDC10 e PL305 foram: 11,97±4,64; 11,93±4,68; 10,98±4,40; 10,18±4,12; 9,66±3,88; 9,20±3,69; 8,63±3,51; 8,08±3,33; 7,59±3,27; 7,22±3,15 e 2.746,17±1.299,90. A duração de lactação foi de 273,72±48,95 dias. As estimativas de herdabilidade variaram nas PLDC de 0,24 a 0,14, sendo maior no primeiro controle e decrescendo até o décimo. A herdabilidade da PL305 foi de 0,19. As estimativas de correlações genéticas entre as PLDC e PL305 variaram de 0,85 a 1,00. As correlações genéticas entre PLDC1 a PLDC9 com PLDC6 a PLDC10 foram acima de 0,80, à exceção entre PLDC9 com PLDC1 e PLDC10 com PLDC1, PLDC2, PLDC3 e PLDC6, que foram inferiores. As correlações fenotípicas tiveram valores intermediários entre as correlações genéticas e as residuais (menores). Considerando a eficiência relativa de seleção, esta mostrou que se baseada nas PLDC2 a PLDC4 ocorrerá a mesma ou melhor resposta que se praticada na PL305.

Genetic and environmental heterogeneity of residual variance of weight traits in Nellore beef cattle

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

Breed and selection line differences in the temperament of beef cattle

O temperamento de quatro raças bovinas foi avaliado utilizando-se o teste de velocidade de fuga (FT) e o escore de comportamento (BST). FT foi definida como o tempo necessário para animais percorrerem uma distância de 2 m após a pesagem. BST foi baseada no comportamento dos animais na balança, amostrando-se quatro categorias de comportamento: movimentos, intensidade de respiração, vocalizações e coices. Os coeficientes de herdabilidade de FT e BST foram estimados com uso de um modelo de máxima verossimilhança restrita, considerando meio irmãos paternos. Caracu apresentou menores médias para BST do que as demais raças. Nelore apresentou resultados intermediários, seguida por Guzerat e Gyr com médias mais elevadas (p < 0,05). Resultados similares foram observados para FT, mas as médias de Caracu e Nelore não diferiram entre si. Observou-se baixa associação entre FT e BST (r p= -0,36; p < 0,01). A correlação entre rank de touros ordenados pelos seus valores preditos (p) para FT e BST foi moderada e negativa (r s = -0,63; p < 0,001). A herdabilidade de FT e BST foi de 0,35 e 0,34, respectivamente. A comparação de rebanhos Nelore com diferentes critérios de seleção para peso corporal mostrou que linhas de seleção podem modular positivamente o temperamento de Bos indicus.

Dois critérios de seleção na pré- desmama em bovinos da raça Gir. 2. Efeito na classificação dos animais

A utilização de dois critérios de seleção na pré-desmama, ganho médio diário do nascimento à desmama (GMD) e dias para ganhar 160 kg do nascimento à desmama (D160), foi estudada, analisando-se informações de 16.592 animais, provenientes do controle de desenvolvimento ponderal da Associação Brasileira dos Criadores de Zebu, nascidos no período de 1978 a 1994. Foram incluídos no modelo o efeito fixo de grupo de contemporâneos e os efeitos aleatórios genético aditivo de animal e materno, de ambiente permanente materno e o erro. A covariância entre os efeitos direto e materno foi considerada igual a zero. As estimativas dos componentes de variância e herdabilidade foram obtidas pelo método da máxima verossimilhança restrita e os valores genéticos preditos (VGs), por modelos animais uni-característica. As estimativas de herdabilidade foram: 0,12; 0,05; 0,10 e 0,05 para GMD (efeito direto), GMD (efeito materno), D160 (efeito direto) e D160 (efeito materno), respectivamente. Foram estimadas a correlação genética entre GMD e D160 (efeito direto e materno) e a correlação de classificação (Spearman) entre os valores genéticos para as categorias de touros, vacas e bezerros. As estimativas de correlação genética entre GMD e D160 foram 0,86 e 0,88, para o efeito direto e materno, respectivamente. As estimativas de correlação de ;rank;, também foram altas, entretanto, nenhuma foi igual a um, resultando em alterações na classificação dos animais. A relação entre as médias aritmética (A) e harmônica (H) e o desvio-padrão (S) do GMD ajustado para efeitos ambientais e maternos (GMDc) foi verificada utilizando-se um modelo restrito, sem intercepto, mediante as regressões linear e quadrática do S do GMDc sobre a diferença entre a média aritmética e média harmônica (A-H). Os resultados evidenciaram que, semelhantemente a H, o critério D160 apresentou a propriedade de discriminar touros com progênie mais uniforme.