Missing data mechanisms and their implications on the analysis of categorical data

We review some issues related to the implications of different missing data mechanisms on statistical inference for contingency tables and consider simulation studies to compare the results obtained under such models to those where the units with missing data are disregarded. We confirm that although, in general, analyses under the correct missing at random and missing completely at random models are more efficient even for small sample sizes, there are exceptions where they may not improve the results obtained by ignoring the partially classified data. We show that under the missing not at random (MNAR) model, estimates on the boundary of the parameter space as well as lack of identifiability of the parameters of saturated models may be associated with undesirable asymptotic properties of maximum likelihood estimators and likelihood ratio tests; even in standard cases the bias of the estimators may be low only for very large samples. We also show that the probability of a boundary solution obtained under the correct MNAR model may be large even for large samples and that, consequently, we may not always conclude that a MNAR model is misspecified because the estimate is on the boundary of the parameter space.

Inference for a skew extension of the Grubbs model

In this paper, we discuss inferential aspects for the Grubbs model when the unknown quantity x (latent response) follows a skew-normal distribution, extending early results given in Arellano-Valle et al. (J Multivar Anal 96:265-281, 2005b). Maximum likelihood parameter estimates are computed via the EM-algorithm. Wald and likelihood ratio type statistics are used for hypothesis testing and we explain the apparent failure of the Wald statistics in detecting skewness via the profile likelihood function. The results and methods developed in this paper are illustrated with a numerical example.

Local power of some tests in exponential family nonlinear models

In this paper we obtain asymptotic expansions up to order n(-1/2) for the nonnull distribution functions of the likelihood ratio, Wald, score and gradient test statistics in exponential family nonlinear models (Cordeiro and Paula, 1989), under a sequence of Pitman alternatives. The asymptotic distributions of all four statistics are obtained for testing a subset of regression parameters and for testing the dispersion parameter, thus generalising the results given in Cordeiro et al. (1994) and Ferrari et al. (1997). We also present Monte Carlo simulations in order to compare the finite-sample performance of these tests. (C) 2010 Elsevier B.V. All rights reserved.

EVALUATION OF THE INFLUENCE OF THE PROTEINIC QUALITY OF THE GENETICALLY MODIFIED AND ORGANIC SOY BEANS IN THE GROWTH OF TWO GENERATIONS OF RATS WISTAR

Feijo, T.S., Cardozo, SX, Daleprane, J.B., Sabaa Srur, A.U.O. & Boaventura, G.T. [Evaluation of the influence of the proteinic quality of the genetically modified and organic soy beans in the growth of two generations of rats Wistar.] Avaliacao da influencia da qualidade proteica da soja geneticamente modificada e organica no crescimento de duas geracoes de ratos Wistar. Revista Brasileira de Medicina Veterinaria, 31(3):139-144, 2009. Programa de Pos-Graduacao em Patologia, Hospital Universitario Antonio Pedro. Centro de Ciencias Medicas, Universidade Federal Fluminense. Rua Marques do Parana, 303, Niteroi, RJ 24030-210, Brasil. E-mail: sergian@ufnj.br Sixty four Wistar rats, male of two consecutive generations determined as F(0) and F(1) were used to study the cumulative effect of two variety soy beans, cultivated with organic seasoning and genetically modified, The animals of each generation were divided into three groups of eight rats each fed on diets consisted of organic soy, soy genetically modified and casein respectively. All the animals received water and the diet ad libitum for period of 28 days. Where the diet consumption and the animals weight were evaluated. After statistic analysis of the results no expressive differences were observed on diet consumption, weight variation, protein efficient ratio and food efficiency ratio on same group of animals in the different generations. On the other hand, significant difference was found on final proteinic retention on animal descendants of the same groups; however of different generations. With this, the supplementation of organic soy with L-cistin provided better avail of this protein in relation to the protein of the soy genetically modified. However, this supplementation did not reveal efficiency in keeping the proteinic employment from one generation to another one, since soy varieties presented better performance on F(0) generation when compared with F(1).

ELECTROMYOGRAPHIC AMPLITUDE RATIO OF SERRATUS ANTERIOR AND UPPER TRAPEZIUS MUSCLES DURING MODIFIED PUSH-UPS AND BENCH PRESS EXERCISES

Imbalance and weakness of the serratus anterior and upper trapezius force couple have been described in patients with shoulder dysfunction. There is interest in identifying exercises that selectively activate these muscles and including it in rehabilitation protocols. This study aims to verify the UT/SA electromyographic (EMG) amplitude ratio, performed in different upper limb exercises and on two bases of support. Twelve healthy men were tested (average age = 22.8 +/- 3.1 years), and surface EMG was recorded from the upper trapezius and serratus anterior using single differential surface electrodes. Volunteers performed isometric contractions over a stable base of support and on a Swiss ball during the wall push-up (WP), bench press (BP), and push-up (PU) exercises. All SEMG data are reported as a percentage of root mean square or integral of linear envelope from the maximal value obtained in one of three maximal voluntary contractions for each muscle studied. A linear mixed-effect model was performed to compare UT/SA ratio values. The WP, BP, and PU exercises showed UT/SA ratio mean +/- SD values of 0.69 +/- 0.72, 0.14 +/- 0.12, and 0.39 +/- 0.37 for stable surfaces, respectively, whereas for unstable surfaces, the values were 0.73 +/- 0.67, 0.43 +/- 0.39, and 0.32 +/- 0.30. The results demonstrate that UT/SA ratio was influenced by the exercises and by the upper limb base of support. The practical application is to show that BP on a stable surface is the exercise preferred over WP and PU on either surfaces for serratus anterior muscle training in patients with imbalance between the UT/SA force couple or serratus anterior weakness.

Modeling study of the aspect ratio influence on urban canopy energy fluxes with a modified wall-canyon energy budget scheme

The influence of the aspect ratio (building height/street canyon width) and the mean building height of cities on local energy fluxes and temperatures is studied by means of an Urban Canopy Model (UCM) coupled with a one-dimensional second-order turbulence closure model. The UCM presented is similar to the Town Energy Balance (TEB) model in most of its features but differs in a few important aspects. In particular, the street canyon walls are treated separately which leads to a different budget of radiation within the street canyon walls. The UCM has been calibrated using observations of incoming global and diffuse solar radiation, incoming long-wave radiation and air temperature at a site in So Paulo, Brazil. Sensitivity studies with various aspect ratios have been performed to assess their impact on urban temperatures and energy fluxes at the top of the canopy layer. In these simulations, it is assumed that the anthropogenic heat flux and latent heat fluxes are negligible. Results show that the simulated net radiation and sensible heat fluxes at the top of the canopy decrease and the stored heat increases as the aspect ratio increases. The simulated air temperature follows the behavior of the sensible heat flux. (C) 2010 Elsevier Ltd. All rights reserved.

Modified Steels for Cold-Forming U-Bolts Used In Leaf Springs Systems

In this work, a low alloy steel and a fabrication process were developed to produce U-Bolts for commercial vehicles. Thus, initially five types of no-heat treated steel were developed with different additions of chrome, nickel, and silicon to produce strain hardening effect during cold-forming processing of the U-Bolts, assuring the required mechanical properties. The new materials exhibited a fine perlite and ferrite microstructure due to aluminum and vanadium additions, well known as grain size refiners. The mechanical properties were evaluated in a servo-hydraulic test machine system-MTS 810 according to ASTM A370-03; E739 and E08m-00 standards. The microstructure and fractography analyses of the cold-formed steels were performed by using optical and scanning electronic microscope techniques. To evaluate the performance of the steels and the production process, fatigue tests were carried out under load control (tensile-tensile), R = 0.1 and f = 30 Hz. The Weibull statistic methodology was used for the analysis of the fatigue results. At the end of this work the 0.21% chrome content steel, Alloy 2, presented the best fatigue performance.

The beta modified Weibull distribution

A five-parameter distribution so-called the beta modified Weibull distribution is defined and studied. The new distribution contains, as special submodels, several important distributions discussed in the literature, such as the generalized modified Weibull, beta Weibull, exponentiated Weibull, beta exponential, modified Weibull and Weibull distributions, among others. The new distribution can be used effectively in the analysis of survival data since it accommodates monotone, unimodal and bathtub-shaped hazard functions. We derive the moments and examine the order statistics and their moments. We propose the method of maximum likelihood for estimating the model parameters and obtain the observed information matrix. A real data set is used to illustrate the importance and flexibility of the new distribution.

A generalized modified Weibull distribution for lifetime modeling

A four parameter generalization of the Weibull distribution capable of modeling a bathtub-shaped hazard rate function is defined and studied. The beauty and importance of this distribution lies in its ability to model monotone as well as non-monotone failure rates, which are quite common in lifetime problems and reliability. The new distribution has a number of well-known lifetime special sub-models, such as the Weibull, extreme value, exponentiated Weibull, generalized Rayleigh and modified Weibull distributions, among others. We derive two infinite sum representations for its moments. The density of the order statistics is obtained. The method of maximum likelihood is used for estimating the model parameters. Also, the observed information matrix is obtained. Two applications are presented to illustrate the proposed distribution. (C) 2008 Elsevier B.V. All rights reserved.

Log-modified Weibull regression models with censored data: Sensitivity and residual analysis

This paper proposes a regression model considering the modified Weibull distribution. This distribution can be used to model bathtub-shaped failure rate functions. Assuming censored data, we consider maximum likelihood and Jackknife estimators for the parameters of the model. We derive the appropriate matrices for assessing local influence on the parameter estimates under different perturbation schemes and we also present some ways to perform global influence. Besides, for different parameter settings, sample sizes and censoring percentages, various simulations are performed and the empirical distribution of the modified deviance residual is displayed and compared with the standard normal distribution. These studies suggest that the residual analysis usually performed in normal linear regression models can be straightforwardly extended for a martingale-type residual in log-modified Weibull regression models with censored data. Finally, we analyze a real data set under log-modified Weibull regression models. A diagnostic analysis and a model checking based on the modified deviance residual are performed to select appropriate models. (c) 2008 Elsevier B.V. All rights reserved.

General results for the beta-modified Weibull distribution

We study in detail the so-called beta-modified Weibull distribution, motivated by the wide use of the Weibull distribution in practice, and also for the fact that the generalization provides a continuous crossover towards cases with different shapes. The new distribution is important since it contains as special sub-models some widely-known distributions, such as the generalized modified Weibull, beta Weibull, exponentiated Weibull, beta exponential, modified Weibull and Weibull distributions, among several others. It also provides more flexibility to analyse complex real data. Various mathematical properties of this distribution are derived, including its moments and moment generating function. We examine the asymptotic distributions of the extreme values. Explicit expressions are also derived for the chf, mean deviations, Bonferroni and Lorenz curves, reliability and entropies. The estimation of parameters is approached by two methods: moments and maximum likelihood. We compare by simulation the performances of the estimates from these methods. We obtain the expected information matrix. Two applications are presented to illustrate the proposed distribution.

Genetic potential of a maize population from Southern Brazil for the modified convergent-divergent selection scheme

Maize (Zea mays L.) is a very important cereal to world-wide economy which is also true for Brazil, particularly in the South region. Grain yield and plant height have been chosen as important criteria by breeders and farmers from Santa Catarina State (SC), Brazil. The objective of this work was to estimate genetic-statistic parameters associated with genetic gain for grain yield and plant height, in the first cycle of convergent-divergent half-sib selection in a maize population (MPA1) cultivated by farmers within the municipality of Anchieta (SC). Three experiments were carried out in different small farms at Anchieta using low external agronomic inputs; each experiment represented independent samples of half-sib families, which were evaluated in randomized complete blocks with three replications per location. Significant differences among half-sib families were observed for both variables in all experiments. The expected responses to truncated selection of the 25% better families in each experiment were 5.1, 5.8 and 5.2% for reducing plant height and 3.9, 5.7 and 5.0% for increasing grain yield, respectively. The magnitudes of genetic-statistic parameters estimated evidenced that the composite population MPA1 exhibits enough genetic variability to be used in cyclical process of recurrent selection. There were evidences that the genetic structure of the base population MPA1, as indicated by its genetic variability, may lead to expressive changes in the traits under selection, even under low selection pressure.

Effect of recombinant human bone morphogenetic protein-7 (rhBMP-7) on the viability, proliferation and differentiation of osteoblast-like cells cultured on a chemically modified titanium surface

Aim: The aim of the present study was to assess the influence of the chemical characteristics and roughness of titanium surfaces on the viability, proliferation and differentiation of osteoblast-like cells cultured in a medium supplemented with recombinant human bone morphogenetic protein-7 (rhBMP-7). Material and methods: Osteo-1 cells were grown on titanium disks presenting with the following surfaces: (1) machined, (2) coarse grit-blasted and acid-attacked (SLA) and (3) chemically modified SLA (SLAmod) in the absence or presence of 20 ng/ml rhBMP-7 in culture medium. The viability and number of osteo-1 cells were evaluated after 24 h. Analyses of total protein content (TP) and alkaline phosphatase (AP) activity at 7, 14 and 21 days, collagen content at 7 and 21 days and mineralized matrix formation at 21 days were performed. Results: Cell viability (P=0.5516), cell number (P=0.3485), collagen content (P=0.1165) and mineralized matrix formation (P=0.5319) were not affected by the different surface configurations or by the addition of rhBMP-7 to the medium. Osteo-1 cells cultured on SLA surfaces showed a significant increase in TP at 21 days. The ALPase/TP ratio (P=0.00001) was affected by treatment and time. Conclusion: The results suggest that the addition of rhBMP-7 to the culture medium did not exert any effect on the viability, proliferation or differentiation of osteoblast-like cells grown on the different surfaces tested. All titanium surfaces analyzed allowed the complete expression of the osteoblast phenotype such as matrix mineralization by osteo-1 cells.

Fatigue life and failure modes of crowns systems with a modified framework design

Objectives: To evaluate the effect of framework design on the fatigue life and failure modes of metal ceramic (MC, Ni-Cr alloy core, VMK 95 porcelain veneer), glass-infiltrated alumina (ICA, In-Ceram Alumina/VM7), and veneered yttria-stabilized tetragonal zirconia polycrystals (Y-TZP, IPSe.max ZirCAD/IPS e.max,) crowns. Methods: Sixty composite resin tooth replicas of a prepared maxillary first molar were produced to receive crowns systems of a standard (MCs, ICAs, and Y-TZPs, n = 10 each) or a modified framework design (MCm, ICAm, and Y-TZPm, n = 10 each). Fatigue loading was delivered with a spherical steel indenter (3.18 mm radius) on the center of the occlusal surface using r-ratio fatigue (30-300 N) until completion of 10(6) cycles or failure. Fatigue was interrupted every 125,000 cycles for damage evaluation. Weibull distribution fits and contour plots were used for examining differences between groups. Failure mode was evaluated by light polarized and SEM microscopy. Results: Weibull analysis showed the highest fatigue life for MC crowns regardless of framework design. No significant difference (confidence bound overlaps) was observed between ICA and Y-TZP with or without framework design modification. Y-TZPm crowns presented fatigue life in the range of MC crowns. No porcelain veneer fracture was observed in the MC groups, whereas ICAs presented bulk fracture and ICAm failed mainly through the veneer. Y-TZP crowns failed through chipping within the veneer, without core fractures. Conclusions: Framework design modification did not improve the fatigue life of the crown systems investigated. Y-TZPm crowns showed comparable fatigue life to MC groups. Failure mode varied according to crown system. (C) 2010 Elsevier Ltd. All rights reserved.

Endurance training induces depot-specific changes in IL-10/TNF-alpha ratio in rat adipose tissue

White adipose tissue (WAT) is the source of pro- and anti-inflammatory cytokines and recently, it has been recognized as an important source of interleukin 10 (IL-10). Acute physical exercise is known to induce an anti-inflammatory cytokine profile, however, the effect of chronic physical exercise on the production of IL-10 by WAT has never been examined. We assessed IL-10 and TNF-alpha concentration in WAT of rats engaged in endurance training. Animals were randomly assigned to either a sedentary control group (S, n = 7) or an endurance trained group (T, n = 8). Trained rats ran on a treadmill 5 days/wk for 8 wk (55-65% VO(2max). Detection of IL-10 and TNF-alpha protein and mRNA expression, as well as the gene expression of PPAR-gamma, and immunocytochemistry to detect mononuclear phagocytes were carried out. A reduction in absolute retroperitoneal adipose tissue (RPAT) weight in T (44%; p < 0.01), when compared with S was observed. IL-10 concentration was increased (1.5-fold, p < 0.05), to a higher extent than that of TNF-alpha (66%. p < 0.05) in the mesenteric adipose tissue (MEAT) of the trained group, while no change related to training was observed in RPAT. In MEAT, IL-10/TNF-alpha ratio was increased in T, when compared with S (30%; p < 0.05). PPAR-gamma gene expression was increased in T (1.1-fold; p < 0.01), when compared with S in the same adipose depot. No monocyte infiltration was found. In conclusion, exercise training induced increased IL-10 expression in the mesenteric depot, resulting in a modified IL-10/TNF-alpha ratio. We also conclude that WAT presents a depot-specific response to endurance training regarding the studied aspects. (C) 2008 Elsevier Ltd. All rights reserved.