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.

Recursive Methods for Construction of Balanced N-ary Block Designs

2000 Mathematics Subject Classification: Primary 05B05; secondary 62K10.

Equitably coloured balanced incomplete block designs

In this thesis we determine necessary and sufficient conditions for the existence of an equitably ℓ-colourable balanced incomplete block design for any positive integer ℓ > 2. In particular, we present a method for constructing non-trivial equitably ℓ-colourable BIBDs and prove that these designs are the only non-trivial equitably ℓ-colourable BIBDs that exist. We also observe that every equitable ℓ-colouring of a BIBD yields both an equalised ℓ-colouring and a proper 2-colouring of the same BIBD. We also discuss generalisations of these concepts including open questions for further research. The main results presented in this thesis also appear in [7].

The extended metamorphosis of a complete bipartite design into a cycle system

A K-t,K-t-design of order n is an edge-disjoint decomposition of K-n into copies of K-t,K-t. When t is odd, an extended metamorphosis of a K-t,K-t-design of order n into a 2t-cycle system of order n is obtained by taking (t - 1)/2 edge-disjoint cycles of length 2t from each K-t,K-t block, and rearranging all the remaining 1-factors in each K-t,K-t block into further 2t-cycles. The 'extended' refers to the fact that as many subgraphs isomorphic to a 2t-cycle as possible are removed from each K-t,K-t block, rather than merely one subgraph. In this paper an extended metamorphosis of a K-t,K-t-design of order congruent to 1 (mod 4t(2)) into a 2t-cycle system of the same order is given for all odd t > 3. A metamorphosis of a 2-fold K-t,K-t-design of any order congruent to 1 (mod 4t(2)) into a 2t-cycle system of the same order is also given, for all odd t > 3. (The case t = 3 appeared in Ars Combin. 64 (2002) 65-80.) When t is even, the graph K-t,K-t is easily seen to contain t/2 edge-disjoint cycles of length 2t, and so the metamorphosis in that case is straightforward. (C) 2004 Elsevier B.V. All rights reserved.

Large supersaturated designs

A supersaturated design (SSD) is an experimental plan, useful for evaluating the main effects of m factors with n experimental units when m > n - 1, each factor has two levels and when the first-order effects of only a few factors are expected to have dominant effects on the response. Use of these plans can be extremely cost-effective when it is necessary to screen hundreds or thousands of factors with a limited amount of resources. In this article we describe how to use cyclic balanced incomplete block designs and regular graph designs to construct E (s(2)) optimal and near optimal SSDs when m is a multiple of n - 1. We also provide a table that can be used to construct these designs for screening thousands of factors. We also explain how to obtain SSDs when m is not a multiple of n - 1. Using the table and the approaches given in this paper, SSDs can be developed for designs with up to 24 runs and up to 12,190 factors.

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.

Variance-balanced designs under interference for dependent observations

It is shown that variance-balanced designs can be obtained from Type I orthogonal arrays for many general models with two kinds of treatment effects, including ones for interference, with general dependence structures. These designs can be used to obtain optimal and efficient designs. Some examples and design comparisons are given. (C) 2002 Elsevier B.V. All rights reserved.

An fMRI study indicating increased cortical recruitment during a cognitive interference task in Huntington's disease patients

We used an event related fMRI design to study the BOLD response in Huntington’s disease (HD) patients during performance of a Simon interference task. We hypothesised that HD patients will demonstrate significantly slower RTs than controls, and that there will be significant differences in the pattern of brain activation between groups. Seventeen HD patients and 15 age and sex matched controls were scanned using 3T GE scanner (FOV = 24 cm2; TE = 40 ms; TR = 3 s; FA = 60°; slice thickness = 6 mm; in-plane resolution = 1.88x1.88 mm2). The task involved two activation conditions, namely congruent (for example, left pointing arrow appearing on the left side of the screen) and incongruent (for example, left pointing arrow appearing on the right side of the screen), and a baseline condition. Each stimulus was presented for 2500 ms followed by a blank screen for 500 ms. Subjects were instructed to press a button using the same hand as indicated by the direction of the arrow head and were given 3000 ms to respond. Data analysis was performed using SPM2 with a random effects analysis model. For each subject parameter estimates for combined task conditions (congruent and incongruent combined) were calculated. Comparisons such as these, based on block designs, have superior statistical power for detecting subtle changes in the BOLD response anywhere in the brain. The activations reported are significant at PFDR_corr

Planeamento de Experiências: Modelos e desafios dos Planos em Blocos Incompletos

O principal objetivo de um Planeamento de Experiências reside essencialmente na procura de relações entre variáveis e na comparação de níveis de fatores, recorrendo ao tratamento estatístico dos dados recolhidos. A utilização de blocos no Planeamento de Experiências é fundamental, pois permite reduzir ou eliminar a variabilidade introduzida por fatores que podem influenciar a experiência mas que não interessam e/ou não foram explicitamente incluídos durante o planeamento. Neste trabalho apresentamos os resultados do estudo e investigação dos Planos em Blocos Incompletos Equilibrados (BIBD), Planos em Blocos Incompletos Equilibrados com repetição de blocos (BIBDR) e Planos em Blocos Incompletos com blocos de diferentes dimensões (VBBD). Exploramos algumas propriedades e métodos de construção destes planos e ilustramos, sempre que possível, com exemplos. Tendo como base o planeamento em blocos, apresentamos uma aplicação dos BIBDR na área da Educação com o objetivo de comparar cinco domínios do pensamento algébrico de uma amostra de alunos do 1º ano do ensino superior em Cabo Verde. Para a análise dos dados da amostra foi utilizado o software R, versão 2.12.1. Pudemos constatar que existem diferenças significativas entre alguns dos domínios do pensamento algébrico, nomeadamente entre os domínios da Generalização da Aritmética e Tecnicismo Algébrico com os restantes domínios. Recomendamos a escolha de uma amostra mais representativa constituída por alunos de todas as instituições superiores de Cabo Verde.

Planeamento de experiências : modelos e desafios dos planos em blocos incompletos

The main purpose of an Experimental Design resides mainly in the search for relationships between variables and in comparing levels of factors, using statistical treatment of collected data. The use of blocks in Experimental Design is essential because it allows reducing or eliminating the variability introduced by factors that can influence the experience but are not of main interest and/or were not explicitly included during experiments. In this work we present the results of the study and research of Balanced Incomplete Block Designs (BIBD), Balanced Incomplete Block Designs with repeated blocks (BIBDR) and the Incomplete Blocks Designs with blocks with different dimensions (VBBD). We explore some properties and construction methods of such designs and illustrate, when possible, with examples. Based on Block Designs, we present an application of BIBDR in Education, with the aim of comparing five domains of algebraic thinking in a sample of 1st year students of higher education in Cape Verde. For the analysis of sample data, the software R was used, version 2.12.1. We observed that significant differences exist between some of the domains of algebraic thinking, especially among the domains of Generalization of Arithmetic and Algebraic Technicality with the remaining areas. For a more representative sample, we recommend a bigger sample consisting of students from all higher institutions of Cape Verde.

Planeamento de experiências : modelos e desafios dos planos em blocos incompletos

The main purpose of an Experimental Design resides mainly in the search for relationships between variables and in comparing levels of factors, using statistical treatment of collected data. The use of blocks in Experimental Design is essential because it allows reducing or eliminating the variability introduced by factors that can influence the experience but are not of main interest and/or were not explicitly included during experiments. In this work we present the results of the study and research of Balanced Incomplete Block Designs (BIBD), Balanced Incomplete Block Designs with repeated blocks (BIBDR) and the Incomplete Blocks Designs with blocks with different dimensions (VBBD). We explore some properties and construction methods of such designs and illustrate, when possible, with examples. Based on Block Designs, we present an application of BIBDR in Education, with the aim of comparing five domains of algebraic thinking in a sample of 1st year students of higher education in Cape Verde. For the analysis of sample data, the software R was used, version 2.12.1. We observed that significant differences exist between some of the domains of algebraic thinking, especially among the domains of Generalization of Arithmetic and Algebraic Technicality with the remaining areas. For a more representative sample, we recommend a bigger sample consisting of students from all higher institutions of Cape Verde.

Planeamento de experiências : modelos e desafios dos planos em blocos incompletos.

O principal objetivo de um Planeamento de Experiências reside essencialmente na procura de relações entre variáveis e na comparação de níveis de fatores, recorrendo ao tratamento estatístico dos dados recolhidos. A utilização de blocos no Planeamento de Experiências é fundamental, pois permite reduzir ou eliminar a variabilidade introduzida por fatores que podem influenciar a experiência mas que não interessam e/ou não foram explicitamente incluídos durante o planeamento. Neste trabalho apresentamos os resultados do estudo e investigação dos Planos em Blocos Incompletos Equilibrados (BIBD), Planos em Blocos Incompletos Equilibrados com repetição de blocos (BIBDR) e Planos em Blocos Incompletos com blocos de diferentes dimensões (VBBD). Exploramos algumas propriedades e métodos de construção destes planos e ilustramos, sempre que possível, com exemplos. Tendo como base o planeamento em blocos, apresentamos uma aplicação dos BIBDR na área da Educação com o objetivo de comparar cinco domínios do pensamento algébrico de uma amostra de alunos do 1º ano do ensino superior em Cabo Verde. Para a análise dos dados da amostra foi utilizado o software R, versão 2.12.1. Pudemos constatar que existem diferenças significativas entre alguns dos domínios do pensamento algébrico, nomeadamente entre os domínios da Generalização da Aritmética e Tecnicismo Algébrico com os restantes domínios. Recomendamos a escolha de uma amostra mais representativa constituída por alunos de todas as instituições superiores de Cabo Verde

Multivariate analyses of genotype x environment interaction of popcorn

The objectives of this work were to evaluate the genotype x environment (GxE) interaction for popcorn and to compare two multivariate analyses methods. Nine popcorn cultivars were sown on four dates one month apart during each of the agricultural years 1998/1999 and 1999/2000. The experiments were carried out using randomized block designs, with four replicates. The cv. Zélia contributed the least to the GxE interaction. The cv. Viçosa performed similarly to cv. Rosa-claro. Optimization of GxE was obtained for cv. CMS 42 for a favorable mega-environment, and for cv. CMS 43 for an unfavorable environment. Multivariate analysis supported the results from the method of Eberhart & Russell. The graphic analysis of the Additive Main effects and Multiplicative Interaction (AMMI) model was simple, allowing conclusions to be made about stability, genotypic performance, genetic divergence between cultivars, and the environments that optimize cultivar performance. The graphic analysis of the Genotype main effects and Genotype x Environment interaction (GGE) method added to AMMI information on environmental stratification, defining mega-environments and the cultivars that optimized performance in those mega-environments. Both methods are adequate to explain the genotype x environment interactions.

Ideal culture conditions for Dicyma pulvinata conidia mass production

The objective of this work was to set up ideal conditions for conidia mass production of Dicyma pulvinata. Four isolates were compared in terms of their growth and conidia production on various substrates (grains of parboiled rice, common rice, maize and wheat, besides chipped maize and rice husk), temperatures (19, 22, 25, 28 and 31ºC), growth containers (aluminum trays, polypropylene bags and Erlenmeyers) and light regimes (continuous darkness, 6 and 12 hours of light/darkness, and continuous light). Temperature effects on conidia germination capacity were also evaluated. The experiments were done in randomized complete block designs, in factorial arrangements (isolates x treatments - substrates, containers, temperatures and light regimes), with four replicates. In general, parboiled rice and polypropylene bags provided the best development of the fungus. Complete darkness and 6 hours of light increased mycelial growth, whereas continuous light favored sporulation. All tested temperatures favored the cultures of the fungus, except 31ºC. Temperatures between 19 and 25ºC ensure spore germination of more than 76%.

Experimental alternatives for evaluation of progenies and clones in eucalyptus breeding programs

The feasibility of using augmented block designs and spatial analysis methods for early stage selection in eucalyptus breeding programs was tested. A total of 113 half-sib progenies of Eucalyptus urophylla and eight clones were evaluated in an 11 x 11 triple lattice experiment at two locations: Posto da Mata (Bahia, Brazil) and São Mateus (Minas Gerais, Brazil). Four checks were randomly allocated within each block. Plots consisted of 15 m long rows containing 6 plants spaced 3 m apart. The girth at breast height (cm/plant) was evaluated at 19 and 26 months of age. Variance analyses were performed according to the following methods: lattice design, randomized complete block design, augmented block design, Papadakis method, moving means method, and check plots. Comparisons among different methods were based on the magnitude of experimental errors and precision of the estimates of genetic and phenotypic parameters. General results indicated that augmented block design is useful to evaluate progenies and clones in early selection in eucalyptus breeding programs using moderate and low selection intensities. However, this design is not suitable for estimating genetic and phenotypic parameters due to its low precision. Check plots, nearest neighbour, Papadakis (1937), and moving means methods were efficient in removing the heterogeneity within blocks. These efficiencies were compared to that in lattice analysis for estimation of genetic and phenotypic parameters.