The use of nonparametric contrasts in one-way layouts and random block designs

Nonparametric simple-contrast estimates for one-way layouts based on Hodges-Lehmann estimators for two samples and confidence intervals for all contrasts involving only two treatments are found in the literature.Tests for such contrasts are performed from the distribution of the maximum of the rank sum between two treatments. For random block designs, simple contrast estimates based on Hodges-Lehmann estimators for one sample are presented. However, discussions concerning the significance levels of more complex contrast tests in nonparametric statistics are not well outlined.This work aims at presenting a methodology to obtain p-values for any contrast types based on the construction of the permutations required by each design model using a C-language program for each design type. For small samples, all possible treatment configurations are performed in order to obtain the desired p-value. For large samples, a fixed number of random configurations are used. The program prompts the input of contrast coefficients, but does not assume the existence or orthogonality among them.In orthogonal contrasts, the decomposition of the value of the suitable statistic for each case is performed and it is observed that the same procedure used in the parametric analysis of variance can be applied in the nonparametric case, that is, each of the orthogonal contrasts has a chi(2) distribution with one degree of freedom. Also, the similarities between the p-values obtained for nonparametric contrasts and those obtained through approximations suggested in the literature are discussed.

Variance dispersion graphs for comparing blocked response surface designs

In this paper, we extend the use of the variance dispersion graph (VDG) to experiments in which the response surface (RS) design must be blocked. Through several examples we evaluate the prediction performances of RS designs in non-orthogonal block designs compared with the equivalent unblocked designs and orthogonally blocked designs. These examples illustrate that good prediction performance of designs in small blocks can be expected in practice. Most importantly, we show that the allocation of the treatment set to blocks can seriously affect the prediction properties of designs; thus, much care is needed in performing this allocation.

Custos e rentabilidade da produção de juvenis de tilápia-do-nilo em tanques-rede utilizando-se diferentes densidades de estocagem

Neste trabalho foi realizada a análise econômica da produção de juvenis de tilápia-do-nilo em tanques-rede utilizando-se diferentes densidades de estocagem. O experimento foi desenvolvido em área aquícola, em delineamento de blocos casualizados, com quatro densidades de estocagem (100, 200, 300 e 400 peixes m-3), avaliadas com seis repetições, em dois períodos de criação: de março a abril de 2005 (52 dias - peso inicial de 43,08 ± 2,98 g e peso final de 262,14 ± 47,86 g) e de março a abril de 2006 (58 dias - peso inicial de 43,16 ± 5,34 g e peso final 314,24 ± 73,30 g). Foram avaliadas as seguintes variáveis econômicas: custo da ração mais custo do juvenil dividido pela biomassa, em R$ kg-1; porcentagem do custo da ração por quilo de peixe produzido sobre o preço de venda; porcentagem do custo do juvenil por quilo de peixe produzido sobre o preço de venda e; porcentagem dos custos da ração mais do juvenil por quilo de peixe produzido sobre o preço de venda. da menor densidade de estocagem (100) para a maior (400), ocorreu diminuição no ganho de peso diário e elevação do índice de conversão alimentar aparente, mas essa redução não comprometeu a taxa de sobrevivência. Entretanto, o ganho de biomassa aumentou com o adensamento de peixes. As maiores receitas líquidas foram obtidas nas densidades de estocagem de 100 e 200 peixes m-3. Os preços não remuneraram os custos operacionais (efetivo e total) em maiores densidades (300 e 400 peixes m-3). Os melhores resultados para a produção de juvenis de tilápia-do-nilo foram obtidos com densidades de até 200 peixes m-3.

Substituição do milho e farelo de algodão pelo milheto no concentrado da dieta de novilhos em confinamento

Objetivou-se identificar possíveis efeitos da substituição do milho e do farelo de algodão por milheto na digestibilidade dos nutrientes da dieta e no desempenho de bovinos em confinamento. As dietas, com relação volumoso:concentrado 65:35, foram compostas de silagens de milho e milheto como volumoso (50:50, com base na matéria natural) e cinco níveis de milheto em substituição ao milho e ao farelo de algodão (0; 23; 49; 80 e 96% da matéria natural) no concentrado. O delineamento de blocos ao acaso foi adotado em ambos os experimentos. Utilizaram-se cinco repetições no estudo de desempenho e quatro na avaliação do consumo e da digestibilidade in vivo. O consumo de matéria seca (MS) expresso em porcentagem do peso vivo (PV) e g/kgPV0,75, diminuiu linearmente com a introdução de milheto na dieta, registrando-se 2,91% e 108,5 g e, 2,5% e 92,53 g para dietas exclusivas de milho e milheto, respectivamente. As digestibilidades de MS, proteína bruta e carboidratos totais não foram afetadas, enquanto a digestibilidade do extrato etéreo diminuiu e a de fibra aumentou linearmente sem afetar os teores de nutrientes digestíveis totais. O ganho de peso vivo diário, o consumo de MS e a conversão alimentar também não foram afetados pela adição de milheto, portanto, é possível substituir o milho e o farelo de algodão por milheto em rações para bovinos em confinamento.

Testes multiambientais na seleção de genótipos de arroz utilizando o modelo de regressão nos sítios ou locais

A análise da interação genótipo x ambiente utilizda no melhoramento de plantas tem sofrido mudanças na última década, melhorando a sua eficiência quanto à seleção dos genótipos sob diferentes condições ambientais. O objetivo deste trabalho foi analisar a produtividade e estabilidade de 12 genótipos de arroz em oito ambientes, durante os anos 2005 e 2006, na Colômbia. O delineamento utilizado foi o de blocos ao acaso com quatro repetições. Os parâmetros de estabilidade fenotípica e o agrupamento dos ambientes foram estimados pelo estudo da interação genótipo x ambiente, segundo o método SREG (Regressão nos sítios ou locais) e seu gráfico biplot (GGE). As análises estatísticas indicaram diferenças significativas (com 5% de probabilidade de erro) entre genótipos e entre ambientes e significância (com 5% de probabilidade de erro) da interação genótipo x ambiente, sugerindo uma resposta diferente dos genótipos nos vários ambientes. No método SREG, os dois primeiros componentes principais da interação explicaram 75,29% da interação. Os genótipos 400094, 350361 e a variedade Fedearroz 50 foram considerados os de maior produtividade. Segundo o gráfico biplot GGE, os ambientes La Libertad e Escobal foram os mais favoráveis para o cultivo do arroz.

Interferěncia da comunidade infestante sobre plantas de Eucalyptus grandis de segundo corte

Currently Brazil is one of the leading paper and pulp producers in the world market, where Sao Paulo State boasts the greatest production. Because of the pulp prices falling in the world market and the low costs of a second coppice rotation, two experiments (started May and December, 2000) were conducted to evaluate the effects of weeds and of weed-free periods (0, 3, 6, 9, 12, 15 and 18 months) on the growth of Eucalyptus grandis second coppice plants. The field trials were set up in a randomized block design with four replicates and the experimental plots consisted of three rows of fve plants. The December weed community was composed mainly of Brachiaria decumbens (Surinam grass) and Panicum maximum (Guinea grass) and the May weed community was composed mainly by B. decumbens and Digitaria insularis (Sour-grass). Weeds had a low negative influence on growth, diameter development and macronutrients content of E. grandis second coppice plants. In both experiments, slight reductions in growth were observed only between the fully weeded and weed-free periods, after 18 months.

Variação genética para caracteres anatômicos e retração volumétrica e sua correlação com a densidade básica da madeira em uma população base de Eucalyptus camaldulensis Dehn

Eucalyptus camaldulensis has great importance in Brazil because of their phenotypic plasticity for different environmental conditions, as soils, altitudes and rainfall. This study is an investigation of a base population of E. camaldulensis from Australia through a progeny test implanted in Selvíria, MS. The trial was established in a randomized block design, with 25 families and 60 replications of single tree plots. Genetic parameters for anatomic traits and volume shrinkage were estimated, as well as their correlations with wood basic density. No significant differences among progenies were observed for the traits studied. The additive genetic variation coefficient at individual and among progeny levels ranged from low (0.26%) to high (16.98%). The narrow sense heritability at individual and family means levels also ranged from low (0.01) to high (0.87). This indicates that some traits are under strong genetic control and can be improved by selection. In the present situation, in order to attain the highest genetic gains, the sequential selection among and within progeny would be recommended.

Variação e parâmetros genéticos em teste de progênies de polinização livre de Peltophorum dubium (Sprengel) taubert em Luiz Antonio -SP

Intensive deforestation and forest fragmentation of the Brazilian forest biomes has contributed to increase the number of trees species under the risk of extinction. Peltophorum dubium (Sprengel) Taubert is one of these species. Some of its populations are being conserved ex situ by the Instituto Florestal de São Paulo through provenance and progeny tests. The aim of this study was to investigate the genetic variation and to estimate genetic parameters at age 24 years in a progeny test of P. dubium established in Luiz Antônio, São Paulo State, Brazil. The trial was established in a random block design, with six replications, five plants per plot and 18 open-pollinated progenies. Measured were: diameter at breast height (DBH), height and stem form. The genetic parameters heritability, genetic variation and effective population size were estimated. Significant genetic differences were observed only for DBH. This trait also presented a high coefficient of genetic variation (CV g=4.8%) and heritability, especially among progeny means (h m 2=0.6607). This indicates that DBH is the most indicated trait for selection in the population. The effective population size conserved ex situ in the test was estimated to be 38.9. Concerning genetic conservation, although the effective population size in the test is small, the values of the genetic variation and of the heritability indicate that the ex situ population has sufficient genetic variation and potential to respond to changes promoted by natural and artificial selection.

Testing extractants for Cu, Fe, Mn, and Zn in tropical soils treated with sewage sludge for 13 consecutive years

In this paper, we report on a field experiment being carried out in a Typic Eutrorthox. The experiment was initiated in the 1997-98 agricultural season as a randomized block design with four treatments (0, 5, 10, and 20 t ha -1) of sewage sludge and five replicates. Compound soil samples were obtained from 20 subsamples collected at depths of 0-0.1 and 0.1-0.2 m. Cu, Fe, Mn, and Zn concentrations were extracted with DTPA pH 7.3; 0.1 mol L -1 HCl, Mehlich-I, Mehlich-III, and 0.01 mol L-1 CaCl 2. Metal concentrations were determined via atomic absorption spectrometry. Diagnostic leaves and the whole above-ground portion of plants were collected to determine Cu, Fe, Mn, and Zn concentrations extracted by nitric-perchloric digestion and later determined via atomic absorption spectrometry. Sewage sludge application caused increases in the concentrations of soil Cu, Fe, and Mn in samples taken from the 0-0.1 m depth evaluated by the extractants Mehlich-I, Mehlich-III, 0.01 mol L-1 HCl and DTPA pH 7.3. None of the extractants provided efficient estimates of changes in Mn concentrations. The acid extractants extracted more Cu, Fe, Mn, and Zn than the saline and chelating solutions. The highest concentrations of Cu, Fe, and Zn were obtained with Mehlich-III, while the highest concentrations of Mn were obtained with HCl. We did not observe a correlation between the extractants and the concentrations of elements in the diagnostic leaves nor in the tissues of the whole maize plant (Zea mays L.). © 2013 Springer Science+Business Media Dordrecht.

Variabilidade genética para características agronômicas entre progênies autofecundadas de mamona (Ricinus communis L.) cv. Al Guarany 2002

Pós-graduação em Agronomia (Agricultura) - FCA

Caracterização da cinza de bagaço de cana-de-açúcar e aplicação no solo

Pós-graduação em Agronomia (Ciência do Solo) - FCAV

Ácido fumárico e quelato de cálcio e fósforo na ração de leitões desmamados

Two experiments (E) were carried out with the objective of evaluating the effects of fumaric acid and carbo-amino-fosfo-quelato of calcium diets of weaned pigs on performance (E1) and intestinal morphology (E2). A total of 96 and 32 pigs with initial mean weights of 5,66 kg ± 0,44kg and 5,34 ± 0,45kg , in E1 and in E2, were used respectively. Randomized block designs were used in both experiments, with a 2 X 2 factorial arrangement in E1 and a 2 X 2 X 2 factorial arrangement in E2. No interaction between acidifier, source of calcium and phosphorus were found for the variables studied in the two experiments. No treatment effects were found on daily feed intake in evaluating periods. Feed conversion from 0 to 17 days was better (P<0.05) when inorganic sources of Ca and P were fed; however, no difference was observed in other periods. The averages of villus height (AV), crypt depth (PC), AV: PC relationship and mucous membrane of the duodenum and of the jejunum didn’t differ among treatments. Considering the total nursery period, no benefit was found in using an acidifier, however the carbo-amino-fosfo-quelato of calcium studied may replace the inorganic sources in the diets of piglets, with no damage to performance and to intestinal morphology.

Multistratum response surface designs

Response surface designs are usually described as if the treatments have been completely randomized to the experimental units. However, in practice there is often a structure to the units, implying the need for blocking. If, in addition, some factors are more difficult to vary between units than others, a multistratum structure arises naturally. We present a general strategy for constructing response surface designs in multistratum unit structures. Designs are constructed stratum by stratum, starting in the highest stratum. In each stratum a prespecified treatment set for the factors applied in that stratum is arranged to be nearly orthogonal to the units in the higher strata, allowing-for all the effects that have to be estimated. Three examples are given to show the applicability of the method and are also used to check the relationship of the final design to the choice of treatment set. Finally, some practical considerations in randomization are discussed.

An algorithm for arranging response surface designs in small blocks

We consider the problem of blocking response surface designs when the block sizes are prespecified to control variation efficiently and the treatment set is chosen independently of the block structure. We show how the loss of information due to blocking is related to scores defined by Mead and present an interchange algorithm based on scores to improve a given blocked design. Examples illustrating the performance of the algorithm are given and some comparisons with other designs are made. (C) 2000 Elsevier B.V. B.V. All rights reserved.

Some practical advice on polynomial regression analysis from blocked response surface designs

It is often necessary to run response surface designs in blocks. In this paper the analysis of data from such experiments, using polynomial regression models, is discussed. The definition and estimation of pure error in blocked designs are considered. It is recommended that pure error is estimated by assuming additive block and treatment effects, as this is more consistent with designs without blocking. The recovery of inter-block information using REML analysis is discussed, although it is shown that it has very little impact if thc design is nearly orthogonally blocked. Finally prediction from blocked designs is considered and it is shown that prediction of many quantities of interest is much simpler than prediction of the response itself.