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.

On estimation and influence diagnostics for zero-inflated negative binomial regression models

The zero-inflated negative binomial model is used to account for overdispersion detected in data that are initially analyzed under the zero-Inflated Poisson model A frequentist analysis a jackknife estimator and a non-parametric bootstrap for parameter estimation of zero-inflated negative binomial regression models are considered In addition an EM-type algorithm is developed for performing maximum likelihood estimation Then the appropriate matrices for assessing local influence on the parameter estimates under different perturbation schemes and some ways to perform global influence analysis are derived In order to study departures from the error assumption as well as the presence of outliers residual analysis based on the standardized Pearson residuals is discussed The relevance of the approach is illustrated with a real data set where It is shown that zero-inflated negative binomial regression models seems to fit the data better than the Poisson counterpart (C) 2010 Elsevier B V All rights reserved

Regression models for grouped survival data: Estimation and sensitivity analysis

In this study, regression models are evaluated for grouped survival data when the effect of censoring time is considered in the model and the regression structure is modeled through four link functions. The methodology for grouped survival data is based on life tables, and the times are grouped in k intervals so that ties are eliminated. Thus, the data modeling is performed by considering the discrete models of lifetime regression. The model parameters are estimated by using the maximum likelihood and jackknife methods. To detect influential observations in the proposed models, diagnostic measures based on case deletion, which are denominated global influence, and influence measures based on small perturbations in the data or in the model, referred to as local influence, are used. In addition to those measures, the local influence and the total influential estimate are also employed. Various simulation studies are performed and compared to the performance of the four link functions of the regression models for grouped survival data for different parameter settings, sample sizes and numbers of intervals. Finally, a data set is analyzed by using the proposed regression models. (C) 2010 Elsevier B.V. All rights reserved.

Endophytic Colonization of Potato (Solanum tuberosum L.) by a Novel Competent Bacterial Endophyte, Pseudomonas putida Strain P9, and Its Effect on Associated Bacterial Communities

Pseudomonas putida strain P9 is a novel competent endophyte from potato. P9 causes cultivar-dependent suppression of Phytophthora infestans. Colonization of the rhizoplane and endosphere of potato plants by P9 and its rifampin-resistant derivative P9R was studied. The purposes of this work were to follow the fate of P9 inside growing potato plants and to establish its effect on associated microbial communities. The effects of P9 and P9R inoculation were studied in two separate experiments. The roots of transplants of three different cultivars of potato were dipped in suspensions of P9 or P9R cells, and the plants were planted in soil. The fate of both strains was followed by examining colony growth and by performing PCR-denaturing gradient gel electrophoresis (PCR-DGGE). Colonies of both strains were recovered from rhizoplane and endosphere samples of all three cultivars at two growth stages. A conspicuous band, representing P9 and P9R, was found in all Pseudomonas PCR-DGGE fingerprints for treated plants. The numbers of P9R CFU and the P9R-specific band intensities for the different replicate samples were positively correlated, as determined by linear regression analysis. The effects of plant growth stage, genotype, and the presence of P9R on associated microbial communities were examined by multivariate and unweighted-pair group method with arithmetic mean cluster analyses of PCR-DGGE fingerprints. The presence of strain P9R had an effect on bacterial groups identified as Pseudomonas azotoformans, Pseudomonas veronii, and Pseudomonas syringae. In conclusion, strain P9 is an avid colonizer of potato plants, competing with microbial populations indigenous to the potato phytosphere. Bacterization with a biocontrol agent has an important and previously unexplored effect on plant-associated communities.

Parametric correlation functions to model the structure of permanent environmental (co)variances in milk yield random regression models

The objective of the present study was to estimate milk yield genetic parameters applying random regression models and parametric correlation functions combined with a variance function to model animal permanent environmental effects. A total of 152,145 test-day milk yields from 7,317 first lactations of Holstein cows belonging to herds located in the southeastern region of Brazil were analyzed. Test-day milk yields were divided into 44 weekly classes of days in milk. Contemporary groups were defined by herd-test-day comprising a total of 2,539 classes. The model included direct additive genetic, permanent environmental, and residual random effects. The following fixed effects were considered: contemporary group, age of cow at calving (linear and quadratic regressions), and the population average lactation curve modeled by fourth-order orthogonal Legendre polynomial. Additive genetic effects were modeled by random regression on orthogonal Legendre polynomials of days in milk, whereas permanent environmental effects were estimated using a stationary or nonstationary parametric correlation function combined with a variance function of different orders. The structure of residual variances was modeled using a step function containing 6 variance classes. The genetic parameter estimates obtained with the model using a stationary correlation function associated with a variance function to model permanent environmental effects were similar to those obtained with models employing orthogonal Legendre polynomials for the same effect. A model using a sixth-order polynomial for additive effects and a stationary parametric correlation function associated with a seventh-order variance function to model permanent environmental effects would be sufficient for data fitting.

Random regression models to estimate test-day milk yield genetic parameters Holstein cows in Southeastern Brazil

A total of 152,145 weekly test-day milk yield records from 7317 first lactations of Holstein cows distributed in 93 herds in southeastern Brazil were analyzed. Test-day milk yields were classified into 44 weekly classes of DIM. The contemporary groups were defined as herd-year-week of test-day. The model included direct additive genetic, permanent environmental and residual effects as random and fixed effects of contemporary group and age of cow at calving as covariable, linear and quadratic effects. Mean trends were modeled by a cubic regression on orthogonal polynomials of DIM. Additive genetic and permanent environmental random effects were estimated by random regression on orthogonal Legendre polynomials. Residual variances were modeled using third to seventh-order variance functions or a step function with 1, 6,13,17 and 44 variance classes. Results from Akaike`s and Schwarz`s Bayesian information criterion suggested that a model considering a 7th-order Legendre polynomial for additive effect, a 12th-order polynomial for permanent environment effect and a step function with 6 classes for residual variances, fitted best. However, a parsimonious model, with a 6th-order Legendre polynomial for additive effects and a 7th-order polynomial for permanent environmental effects, yielded very similar genetic parameter estimates. (C) 2008 Elsevier B.V. All rights reserved.

A Log-Linear Regression Model for the Beta-Weibull Distribution

We introduce the log-beta Weibull regression model based on the beta Weibull distribution (Famoye et al., 2005; Lee et al., 2007). We derive expansions for the moment generating function which do not depend on complicated functions. The new regression model represents a parametric family of models that includes as sub-models several widely known regression models that can be applied to censored survival data. We employ a frequentist analysis, a jackknife estimator, and a parametric bootstrap for the parameters of the proposed model. We derive the appropriate matrices for assessing local influences on the parameter estimates under different perturbation schemes and present some ways to assess global influences. Further, for different parameter settings, sample sizes, and censoring percentages, several simulations are performed. In addition, the empirical distribution of some modified residuals are displayed and compared with the standard normal distribution. These studies suggest that the residual analysis usually performed in normal linear regression models can be extended to a modified deviance residual in the proposed regression model applied to censored data. We define martingale and deviance residuals to evaluate the model assumptions. The extended regression model is very useful for the analysis of real data and could give more realistic fits than other special regression models.

Paclitaxel associated with cholesterol-rich nanoemulsions promotes atherosclerosis regression in the rabbit

A cholesterol-rich nanoemulsion (LDE) that resembles LDL binds to the LDL receptors and after injection into the blood stream may concentrate in cells with LDL receptor overexpression, as occurs in neoplasias and other proliferative processes. Thus, LDE can be used as vehicle to target drugs against those cells. The current study was designed to verify in rabbits whether LDE concentrates in the lesioned rabbit artery and whether a paclitaxel derivative, paclitaxel oleate, associated to LDE could reduce the atherosclerotic lesions. Sixteen male New Zealand rabbits were fed a 1% cholesterol diet for 60 days. Starting from day 30 under cholesterol feeding, eight animals were treated with four weekly intravenous injections of LDE-paclitaxel (4 mg/kg) and eight with four weekly intravenous saline solution injections for additional 30 days. On day 60, the animals were sacrificed for analysis. The uptake of LDE labeled with [C-14]-cholesteryl oleate by the aortic arch of cholesterol-fed rabbits was twice as much that observed in animals fed only regular chow. LDE-paclitaxel reduced the lesion areas of cholesterol-fed animals by 60% and intima-media ratio fourfold and inhibited the macrophage migration and the smooth muscle cell proliferation and invasion of the intima. LDE-paclitaxel treatment had no toxicity. In conclusion, LDE-paclitaxel produced pronounced atherosclerosis regression without toxicity and has shown remarkable potential in cardiovascular therapeutics. (c) 2008 Published by Elsevier Ireland Ltd.

Olfactory eavesdropping between two competing stingless bee species

Foragers can improve search efficiency, and ultimately fitness, by using social information: cues and signals produced by other animals that indicate food location or quality. Social information use has been well studied in predator-prey systems, but its functioning within a trophic level remains poorly understood. Eavesdropping, use of signals by unintended recipients, is of particular interest because eavesdroppers may exert selective pressure on signaling systems. We provide the most complete study to date of eavesdropping between two competing social insect species by determining the glandular source and composition of a recruitment pheromone, and by examining reciprocal heterospecific responses to this signal. We tested eavesdropping between Trigona hyalinata and Trigona spinipes, two stingless bee species that compete for floral resources, exhibit a clear dominance hierarchy and recruit nestmates to high-quality food sources via pheromone trails. Gas chromatography-mass spectrometry of T. hyalinata recruitment pheromone revealed six carboxylic esters, the most common of which is octyl octanoate, the major component of T. spinipes recruitment pheromone. We demonstrate heterospecific detection of recruitment pheromones, which can influence heterospecific and conspecific scout orientation. Unexpectedly, the dominant T. hyalinata avoided T. spinipes pheromone in preference tests, while the subordinate T. spinipes showed neither attraction to nor avoidance of T. hyalinata pheromone. We suggest that stingless bees may seek to avoid conflict through their eavesdropping behavior, incorporating expected costs associated with a choice into the decision-making process.

Environmental Exposure to Methylmercury is Associated with a Decrease in Nitric Oxide Production

Some studies have recently suggested that mercury (Hg)-exposed populations face increased risks of cardiovascular diseases, and experimental data indicate that such risks might be due to reductions in nitric oxide bioavailability. However, no previous study has examined whether Hg exposure affects plasma nitrite concentrations in humans as an indication of nitric oxide production. Here, we investigated whether there is an association between circulating nitrite and Hg concentrations in whole blood, plasma and hair from an exposed methylmercury (MeHg) population. Hair and blood samples were collected from 238 persons exposed to MeHg from fish consumption. Hg concentrations in plasma (PHg), whole blood (BHg) and hair Hg (HHg) were determined by inductively coupled plasma-mass spectrometry. Mean BHg content was 49.8 +/- 35.2 mu g/l, mean PHg was 7.8 +/- 6.9 mu g/l and HHg 14.6 +/- 10.6 mu g/g. Mean plasma nitrite concentration was 253.2 +/- 105.5 nM. No association was found between plasma nitrite concentration and BHg or HHg concentrations in a univariate model. However, multiple regression models adjusted for gender, age and fish consumption showed a significant association between plasma nitrite and plasma Hg concentration (beta = -0.1, p < 0.001). Our findings constitute preliminary clinical evidence that exposure to MeHg may cause inhibitory effects on the production of endothelial nitric oxide.

Exploratory Approach to the use of Techniques of Regression Analysis and Pooled Analysis in Studies of Consumer Behavior

This paper is part of a large study to assess the adequacy of the use of multivariate statistical techniques in theses and dissertations of some higher education institutions in the area of marketing with theme of consumer behavior from 1997 to 2006. The regression and conjoint analysis are focused on in this paper, two techniques with great potential of use in marketing studies. The objective of this study was to analyze whether the employement of these techniques suits the needs of the research problem presented in as well as to evaluate the level of success in meeting their premisses. Overall, the results suggest the need for more involvement of researchers in the verification of all the theoretical precepts of application of the techniques classified in the category of investigation of dependence among variables.

Multicollinearity and financial constraint in investment decisions: a Bayesian generalized ridge regression

This paper addresses the investment decisions considering the presence of financial constraints of 373 large Brazilian firms from 1997 to 2004, using panel data. A Bayesian econometric model was used considering ridge regression for multicollinearity problems among the variables in the model. Prior distributions are assumed for the parameters, classifying the model into random or fixed effects. We used a Bayesian approach to estimate the parameters, considering normal and Student t distributions for the error and assumed that the initial values for the lagged dependent variable are not fixed, but generated by a random process. The recursive predictive density criterion was used for model comparisons. Twenty models were tested and the results indicated that multicollinearity does influence the value of the estimated parameters. Controlling for capital intensity, financial constraints are found to be more important for capital-intensive firms, probably due to their lower profitability indexes, higher fixed costs and higher degree of property diversification.

Red Blood Cell Transfusions are Independently Associated with Intra-Hospital Mortality in Very Low Birth Weight Preterm Infants

Objective To test the hypothesis that red blood cell (RBC) transfusions in preterm infants are associated with increased intra-hospital mortality. Study design Variables associated with death were studied with Cox regression analysis in a prospective cohort of preterm infants with birth weight <1500 g in the Brazilian Network on Neonatal Research. Intra-hospital death and death after 28 days of life were analyzed as dependent variables. Independent variables were infant demographic and clinical characteristics and RBC transfusions. Results Of 1077 infants, 574 (53.3%) received at least one RBC transfusion during the hospital stay. The mean number of transfusions per infant was 3.3 +/- 3.4, with 2.1 +/- 2.1 in the first 28 days of life. Intra-hospital death occurred in 299 neonates (27.8%), and 60 infants (5.6%) died after 28 days of life. After adjusting for confounders, the relative risk of death during hospital stay was 1.49 in infants who received at least one RBC transfusion in the first 28 days of life, compared with infants who did not receive a transfusion. The risk of death after 28 days of life was 1.89 times higher in infants who received more than two RBC transfusions during their hospital stay, compared with infants who received one or two transfusions. Conclusion Transfusion was associated with increased death, and transfusion guidelines should consider risks and benefits of transfusion. (J Pediatr 2011; 159: 371-6).

Biomonitoring genotoxic risks under the urban weather conditions and polluted atmosphere in Santo Andre, SP, Brazil, through Trad-MCN bioassay

The present study was made to check if the Trad-MCN bioassay, developed with inflorescences of Tradescantia pallida cv. Purpurea, might discriminate genotoxic risks in areas of the city of Santo Andre (SE Brazil) contaminated by different air pollutants, and periods of the year when risks are higher, and to determine if the variations in the frequency of micronuclei (MCN) can be explained by environmental factors that characterize the stressful situation in each site. Potted plants were exposed in sites highly contaminated by ozone (Capuava and School) and in sites reached by high vehicular emissions (downtown and Celso Daniel Park). Pedroso Park, far from the polluted areas, was taken as reference. From September 2003 to September 2004, 20 young inflorescences were collected twice a week from each place and the frequencies of MCN were estimated. The environmental conditions observed in the polluted sites were stressful enough to promote an increase of MCN, mainly in sites reached by high vehicular emissions. But MCN rates in Capuava and at Celso Daniel Park could not be predicted only by pollutants which characterized the air contamination in these sites. More severe weather conditions, mainly low temperature, relative humidity and rainfall, caused an increase of MCN. Improvement of the biomonitoring system is recommended to minimize this negative influence of weather factors. (C) 2008 Elsevier Inc. All rights reserved.

Regression of glomerular injury by losartan in experimental diabetic nephropathy

Many features of chronic kidney disease may be reversed, but it is unclear whether advanced lesions, such as adhesions of sclerotic glomerular tufts to Bowman`s capsule (synechiae), can resolve during treatment. We previously showed, using a renal ablation model, that the renoprotective effect of the AT-1 receptor blocker, losartan, is dose-dependent. Here we determined if moderate and advanced glomerular lesions, associated with streptozotocin-induced diabetes, regress with conventional or high-dose losartan treatment. Using daily insulin injection for 10 months, we maintained diabetic adult male Munich-Wistar rats in a state of moderate hyperglycemia. Following this period, some rats continued to receive insulin with or without conventional or high-dose losartan for an additional 2 months. Diabetic rats pretreated with insulin for 10 months and age-matched non-diabetic rats served as controls. Mesangial expansion was found in the control diabetic rats and was exacerbated in those rats maintained on only insulin for an additional 2 months. Conventional and high-dose losartan treatments reduced this mesangial expansion and the severity of synechiae lesions below that found prior to treatment; however, the frequency of the latter was unchanged. There was no dose-response effect of losartan. Our results show that regression of mesangial expansion and contraction of sclerotic lesions is feasible in the treatment of diabetes, but complete resolution of advanced glomerulosclerosis may be hard to achieve.