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.

Native tree seedling growth when fertilized with different amounts of dry sewage sludge and mineral fertilizer

The increasing volume of urban sewage nowadays generates considerable amount of sludge to be disposed of. One environmentally adequate destination could be the application of treated and stabilized sludge (biosolids) to forest plantations as fertilizer and soil conditioner. The purpose of this study was to analyze the feasibility of applying sewage sludge, evaluating its effects on native tree seedlings. The species evaluated were aroeira-pimenteira (Schinus terebinthifolia Raddi), cabreuva-vermelha (Myroxy-Ion peruiferum L. f.), pau-de-viola (Cytarexyllum myrianthum Cham), unha-de-vaca (Bauhinia forficata Link), which are usually planted in forest restoration. Seedlings were cultivated in pots, containing a volume of 4 dm(3) of soil, within a greenhouse. The study was developed in the proximity of Campinas, SP, Brazil, and installed in November, 2003. The design was entirely randomized including seven treatments: control; mineral fertilization; and different doses of sewage sludge (biosolids) complemented with potassium, due to the low concentration of this element in the sludge produced by the wastewater treatment plant of Barueri (Metropolitan region of Sao Paulo city). The results showed that the application of different dosages of biosolids promoted different responses in stem height and biomass production. The treatment with 20 g/dm(3) of dry sewage sludge promoted both the highest growth and the highest seedling biomass production, compared to the control treatment. All native tree species treated with the highest dosage of sewage sludge showed a growth similar to that of mineral fertilization. The seedlings of aroeira-pimenteira, pau-de-viola, and unha-de-vaca, all typical species of the initial succession in natural forest ecosystems, grew and produced more biomass than cabreuva-vermelha, a typical species of the final forest succession.

Characterization of tree-rings of Pinus caribaea var. hondurensis Barr. et Golf. trees by X ray densitometry

This work aimed to determining the anatomical structure of wood, through methodology of histology and X-ray densitometry, of resin-tapped and not resin-tapped Pinus caribaea var. hondurensis trees samples, of three diameter classes. Pine trees, in forest plantation established in 1969, in the Ecological Experimental Station of Itirapina, from the Forestry Institute of Sao Paulo State, were measured and stratified into three classes of trunk diameter. The pine trees were resin-tapped since 2004, with the opening of two simultaneous and opposing panels. Sixty samples of pine wood trees were extracted from the tree trunk through a non-destructive method and in the laboratory. Tree rings were determined in the laboratory and wood apparent density by X-ray densitometry. The test results showed that: (i) false tree rings occur in the early wood and late wood of the tree rings due to climate change; (ii) the X-ray densitometry allowed the demarcation of the tree rings limits; (iii) the wood apparent density average was significantly different between the trees in high class diameter and in the medium-low class; (iv) the wood characteristics from the resin-tapped and non resin-tapped faces did not show significant differences.

COMPETITION AMONG EUCALYPTUS TREES DEPENDS ON GENETIC VARIATION AND RESOURCE SUPPLY

Genetic variation and environmental heterogeneity fundamentally shape the interactions between plants of the same species. According to the resource partitioning hypothesis, competition between neighbors intensifies as their similarity increases. Such competition may change in response to increasing supplies of limiting resources. We tested the resource partitioning hypothesis in stands of genetically identical (clone-origin) and genetically diverse (seed-origin) Eucalyptus trees with different water and nutrient supplies, using individual-based tree growth models. We found that genetic variation greatly reduced competitive interactions between neighboring trees, supporting the resource partitioning hypothesis. The importance of genetic variation for Eucalyptus growth patterns depended strongly on local stand structure and focal tree size. This suggests that spatial and temporal variation in the strength of species interactions leads to reversals in the growth rank of seed-origin and clone-origin trees. This study is one of the first to experimentally test the resource partitioning hypothesis for intergenotypic vs. intragenotypic interactions in trees. We provide evidence that variation at the level of genes, and not just species, is functionally important for driving individual and community-level processes in forested ecosystems.

Tree-ring characterization of Araucaria columnaris Hook and its applicability as a lead indicator in environmental monitoring

Tree-rings have frequently been used for dating of trees and to determine annual growth increments and forest dynamics, but little is known in tropical conditions about their utilization for environmental monitoring. This paper presents the results of Araucaria columnaris tree-ring characterization by wood anatomy and X-ray densitometric analysis and the determination of Pb concentration. Core samples from twelve araucaria trees were extracted from two sites exposed to air pollution due to intense traffic of vehicles and industrial activities. The tree-rings distinctly presented radial variation in early-latewood thickness and density, and characteristics of juvenile and mature wood. Anatomical and X-ray densitometric analysis were useful to delimit the tree-ring boundaries and to date the tree-rings, as well as to prove the annual formation. The lead concentration in annual araucaria tree-rings, analyzed with graphite furnace atomic absorption spectrometry, indicated the seasonal presence of the heavy metal in the environment during the 30 years studied, although the Pb did not affect tree growth. (c) 2008 Elsevier GmbH. All rights reserved.

Variation of wood density and relationship with the tree-ring width of mahogany trees, Swietenia macrophylla, from Amazonian tropical forest of Peru

Mahogany trees, Swietenia macrophylla, occur in open rainforest, semi deciduous and deciduous and dense rainforest of Peruvian Amazonian tropical forest. They occur, preferentially, in areas with a defined dry season, with typical phenology and seasonal variation activity, forming distinct tree-rings. The present work had as aim to determine the wood density radial variation of 14 mahogany trees, of two populations of the Peruvian Amazonian tropical forest, through the X-ray densitometry and to evaluate their application as methodology, compared to the classic method of measurement table, for the determination of the treering width. The radial wood apparent density of the trees profiles rendered it possible to delimit the areas of juvenile-adult wood and of the heartwood-sapwood, relative to the anatomical structure and chemical composition differences, due to the extractives and the vessels obstruction by tyloses. The mean, minimum and maximum wood apparent density of the mahogany trees for the Populations A and B were of 0.70; 0.29; 1.01 g.cm(-3) and 0.81; 0.29; 1.19 g.cm(-3), respectively. The analysis of the variance and mean test indicate differences of mean wood density among the mahogany trees of each population, probably due to the age of the trees. There was no correlation between mean wood density of mahogany trees among the two populations, as well as, between the tree-ring width and the respective mean density. The X-ray densitometry technique is an important tool in the evaluation of the radial variation of wood apparent density and the delimitation of tree-ring boundaries, with correlations of 0.94 and 0.93 in relation to measurement table, for each sampled population.

Alternative Analytical Expressions for the General van Genuchten-Mualem and van Genuchten-Burdine Hydraulic Conductivity Models

The van Genuchten expressions for the unsaturated soil hydraulic properties, first published in 1980, are used frequently in various vadose zone flow and transport applications assuming a specific relationship between the m and n soil hydraulic parameters. By comparison, probably because of the complexity of the hydraulic conductivity equations, the more general solutions with independent m and n values are rarely used. We expressed the general van Genuchten-Mualem and van Genuchten-Burdine hydraulic conductivity equations in terms of hypergeometric functions, which can be approximated by infinite series that converge rapidly for relatively large values of the van Genuchten-Mualem parameter n but only very slowly when n is close to one. Alternative equations were derived that provide very close approximations of the analytical results. The newly proposed equations allow the use of independent values of the parameters m and n in the soil water retention model of van Genuchten for subsequent prediction of the van Genuchten-Mualem and van Genuchten-Burdine hydraulic conductivity models, thus providing more flexibility in fitting experimental pressure-head-dependent water content, theta(h), and hydraulic conductivity, K(h), or K(theta) data.

Forecasting fuel ethanol consumption in Brazil by time series models: 2006-2012

This article analysed scenarios for Brazilian consumption of ethanol for the period 2006 to 2012. The results show that if the country`s GDP sustains a 4.6% a year growth, domestic consumption of fuel ethanol could increase to 25.16 billion liters in this period, which is a volume relatively close to the forecasted gasoline consumption of 31 billion liters. At a lower GDP growth of 1.22% a year, gasoline consumption would be reduced and domestic ethanol consumption in Brazil would be no higher than 18.32 billion liters. Contrary to the current situation, forecasts indicated that hydrated ethanol consumption could become much higher than anhydrous consumption in Brazil. The former is being consumed in cars moved exclusively by ethanol and flex-fuel cars, successfully introduced in the country at 2003. Flex cars allow Brazilian consumers to choose between gasoline and hydrated ethanol and immediately switch to whichever fuel presents the most favourable relative price.

Does using stepwise variable selection to build sequential path analysis models make sense?

Causal inference methods - mainly path analysis and structural equation modeling - offer plant physiologists information about cause-and-effect relationships among plant traits. Recently, an unusual approach to causal inference through stepwise variable selection has been proposed and used in various works on plant physiology. The approach should not be considered correct from a biological point of view. Here, it is explained why stepwise variable selection should not be used for causal inference, and shown what strange conclusions can be drawn based upon the former analysis when one aims to interpret cause-and-effect relationships among plant traits.

Tree performance and fruit yield and quality of `Okitsu` Satsuma mandarin grafted on 12 rootstocks

The citriculture in Brazil, as well as in other important regions in the world, is based on very few mandarin cultivars. This fact leads to a short harvest period and higher prices for off-season fruit. The `Okitsu` Satsuma (Citrus unshiu Marc.) is among the earliest ripening mandarin cultivars and it is considered to be tolerant to, citrus canker (Xanthomonas citri subsp. citri Schaad et al.) and to citrus variegated chlorosis (Xylella fastidiosa Wells et al.). Despite having regular fruit quality under hot climate conditions, the early fruit maturation and absence of seeds of `Okitsu` fruits are well suited for the local market in the summer(December through March), when the availability of citrus fruits for fresh consumption is limited. Yet, only a few studies have been conducted in Brazil on rootstocks for `Okitsu`. Consequently, a field trial was carried out in Bebeclouro, Sao Paulo State, to evaluate the horticultural performance of `Okitsu` Satsuma mandarin budded onto 12 rootstocks: the citrandarin `Changsha` mandarin (Citrus reticulata Blanco) x Poncirus trifoliata `English Small`: the hybrid Rangpur lime (Citrus limonia Osbeck) x `Swingle` citrumelo (P. trifoliata (L.) Raf. x Citrus paradisi Macfad.); the trifoliates (P. trifoliata (L) Raf)`Rubidoux`,`FCAV` and `Flying Dragon`(P. trifoliata var. monstrosa); the mandarins `Sun Chu Sha Kat`(C. reticulata Blanco) and `Sunki`(Citrus sunki (Hayata) Hort. ex. Tanaka); the Rangpur limes (C. limonia Osbeck) `Cravo Limeira` and `Cravo FCAV`;`Carrizo` citrange (Citrus sinensis x P. trifoliata), `Swingle` citrumelo (P. trifoliata x C. paradisi), and `Orlando` tangelo (C. paradisi x Citrus tangerina cv. `Dancy`). The experimental grove was planted in 2001, using a 6 m x 3 m spacing, in a randomized block design. No supplementary irrigation was applied. Fruit yield, canopy volume, and fruit quality were assessed for each rootstock. A cluster multivariate analysis identified three different rootstock pairs with similar effects on plant growth, yield and fruit quality of `Okitsu` mandarin. The `Flying Dragon `trifoliate had a unique effect over the `Okitsu` trees performance, inducing lower canopy volume and higher yield efficiency and fruit quality, and might be suitable for high-density plantings. The `Cravo Limeira` and `Cravo FCAV` Rangpur limes induced early-ripening of fruits, with low fruit quality. `Sun Chu Sha Kat` and `Sunki` mandarins and the `Orlando` tangelo conferred lower yield efficiency and less content of soluble solids for the latter rootstock. (C) 2009 Elsevier B.V. All rights reserved.

`Swingle` citrumelo propagation by cuttings for citrus nursery tree production or inarching

`Swingle` citrumelo [Citrus paradisi MacFaden x Poncirus trifoliata (L.) Raf.] has been extensively used as a rootstock in several citrus growing regions of the World, including Southern Brazil where `Rangpur` lime (Citrus limonia Osbeck) is still the predominant variety despite being affected by several important pathogens. in this case, `Swingle` citrumelo is used to produce nursery trees to establish new orchards or to be inarched in adult and healthy groves in order to change the rootstock. We report herein a system to produce trees on `Swingle` citrumelo more rapidly by budding onto non-rooted cuttings, as well as assessing potential to rapidly multiply `Swingle` through rooting of non-budded cuttings. Therefore, two potential products are described: budded trees and rooted rootstock cuttings. `Valencia` sweet orange [Citrus sinensis (L.) Osbeck] was budded at different heights on cuttings derived from eight-month old rootstocks. Grafted and additional non-budded cuttings were then treated with indole-3-butyric acid (500 mg L(-1)) or left untreated before rooting. Three types of cuttings were evaluated: softwood, semi-hardwood and hardwood. The use of nursery trees derived from pre-budded hardwood cuttings of `Swingle` citrumelo is an alternative grafting method on this cultivar. Softwood cuttings with one leaf pair were considered the most adequate material for rapid multiplication of `Swingle` citrumelo by cutting. This could be particularly useful for inarching production or conventional budding after transplant of cutting-derived rootstocks. (C) 2008 Elsevier B.V. All rights reserved.

Nitrogen, phosphorus and potassium dose effect in the graft box of lemon tree (of the family Rutaceae) nutrition and production.

Nitrogen, phosphorus and potassium dose effect in the graft box of lemon tree (of the family Rutaceae) nutrition and production. The aim of the study was to evaluate the graft box of lemon tree (of the family Rutaceae) nutritional state and its components of growth in function of nitrogen, phosphorus and potassium dose by fertilization. The experimental outlining was entirely made casually in factorial scheme 3(3) + 1, being 3 factors (nitrogen, phosphorus and potassium - NPK), 3 doses and in evidence (without fertilization), with 3 repetitions. The experimental milt was constituted by two tubes of 2,8 cm diameter and 12,3 cm high with a graft box (Hipobioto) of lemon tree (of the family Rutaceae) in each tube. The doses used were constituted by doses of N (460; 920 e 18,10 mg dm(-3)), P (50; 100 e 200 mg dm(-3)) and K (395; 790 e 1580 mg dm(-3)). The fertilization with N and K was carried out by fertirrigations and the P added to the substract of Pinus rind and vermiculite before the seeding. when the plants were 133 days after the germination they were subdivided in radicular system and air part for the determinations of the dry matter mass, height, foliar area, stem diameter and contents of nutrients. The N, K and P doses of 920 mg dm(-3), 790 mg dm(-3), 100 mg dm(-3), respectively, were enough for the suitable development of the graft box of lemon tree (of the family Rutaceae) in tubes.

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.