Estimation and diagnostics for heteroscedastic nonlinear regression models based on scale mixtures of skew-normal distributions

An extension of some standard likelihood based procedures to heteroscedastic nonlinear regression models under scale mixtures of skew-normal (SMSN) distributions is developed. This novel class of models provides a useful generalization of the heteroscedastic symmetrical nonlinear regression models (Cysneiros et al., 2010), since the random term distributions cover both symmetric as well as asymmetric and heavy-tailed distributions such as skew-t, skew-slash, skew-contaminated normal, among others. A simple EM-type algorithm for iteratively computing maximum likelihood estimates of the parameters is presented and the observed information matrix is derived analytically. In order to examine the performance of the proposed methods, some simulation studies are presented to show the robust aspect of this flexible class against outlying and influential observations and that the maximum likelihood estimates based on the EM-type algorithm do provide good asymptotic properties. Furthermore, local influence measures and the one-step approximations of the estimates in the case-deletion model are obtained. Finally, an illustration of the methodology is given considering a data set previously analyzed under the homoscedastic skew-t nonlinear regression model. (C) 2012 Elsevier B.V. All rights reserved.

Error Autocorrelation and Linear Regression for Temperature-Based Evapotranspiration Estimates Improvement

Estimates of evapotranspiration on a local scale is important information for agricultural and hydrological practices. However, equations to estimate potential evapotranspiration based only on temperature data, which are simple to use, are usually less trustworthy than the Food and Agriculture Organization (FAO)Penman-Monteith standard method. The present work describes two correction procedures for potential evapotranspiration estimates by temperature, making the results more reliable. Initially, the standard FAO-Penman-Monteith method was evaluated with a complete climatologic data set for the period between 2002 and 2006. Then temperature-based estimates by Camargo and Jensen-Haise methods have been adjusted by error autocorrelation evaluated in biweekly and monthly periods. In a second adjustment, simple linear regression was applied. The adjusted equations have been validated with climatic data available for the Year 2001. Both proposed methodologies showed good agreement with the standard method indicating that the methodology can be used for local potential evapotranspiration estimates.

A novel method for power quality multiple disturbance decomposition based on Independent Component Analysis

In this paper, a novel method for power quality signal decomposition is proposed based on Independent Component Analysis (ICA). This method aims to decompose the power system signal (voltage or current) into components that can provide more specific information about the different disturbances which are occurring simultaneously during a multiple disturbance situation. The ICA is originally a multichannel technique. However, the method proposes its use to blindly separate out disturbances existing in a single measured signal (single channel). Therefore, a preprocessing step for the ICA is proposed using a filter bank. The proposed method was applied to synthetic data, simulated data, as well as actual power system signals, showing a very good performance. A comparison with the decomposition provided by the Discrete Wavelet Transform shows that the proposed method presented better decoupling for the analyzed data. (C) 2012 Elsevier Ltd. All rights reserved.

Prevalence of asthma and risk factors associated: population based study in Sao Paulo, Southeastern Brazil, 2008-2009

OBJECTIVE: To assess the prevalence of asthma and risk factors associated in children and adolescents. METHODS: Population-based cross-sectional study with 1,185 female and male children and adolescents carried out in the city of Sao Paulo, Southeastern Brazil, from 2008 to 2009. Data were collected through home interviews. Respondents were selected from two-stage (census tract, household) cluster random sampling stratified by gender and age. Multiple Poisson regression was used in the adjusted analysis between the outcome and socioeconomic, demographic, lifestyle and health condition variables. RESULTS: Of all respondents, 9.1% (95%CI 7.0; 11.7) reported asthma. After adjustment, the following variables were found independently associated with asthma: age (0 to 4 years vs. 15 to 19) (PR 3.18, 95%CI 1.20;8.42); age (5 to 9 years vs. 15 to 19) (PR 6.37, 95%CI 2.64;15.39); age (10 to 14 years vs. 15 to 19) (PR 4.51,95%CI 1.95;10.40); allergy (yes vs. no) (PR 2.22, 95%CI 1.24;4.00); rhinitis (yes vs. no) (PR 2.13, 95%CI 1.22;3.73); health conditions in the 15 days preceding the interview (yes vs. no) (PR 1.96, 95%CI 1.23;3.11); number of rooms in the household (1 to 3 vs. 4 and more) (PR 1.67, 95%CI 1.05;2.66); and skin color (black and mixed vs. white) (PR 2.00, 95%CI 1.14;3.49). CONCLUSIONS: This study showed the importance of factors associated with asthma including rhinitis and allergy; age between 5 to 9 years old; black and mixed skin color; and household with few rooms. Frequent health problems are seen as a common consequence of asthma.

The role of clouds in improving the regression model for hourly values of diffuse solar radiation

The study introduces a new regression model developed to estimate the hourly values of diffuse solar radiation at the surface. The model is based on the clearness index and diffuse fraction relationship, and includes the effects of cloud (cloudiness and cloud type), traditional meteorological variables (air temperature, relative humidity and atmospheric pressure observed at the surface) and air pollution (concentration of particulate matter observed at the surface). The new model is capable of predicting hourly values of diffuse solar radiation better than the previously developed ones (R-2 = 0.93 and RMSE = 0.085). A simple version with a large applicability is proposed that takes into consideration cloud effects only (cloudiness and cloud height) and shows a R-2 = 0.92. (C) 2011 Elsevier Ltd. All rights reserved.

Urea-Based Synthesis of Zinc Oxide Nanostructures at Low Temperature

The preparation of nanometer-sized structures of zinc oxide (ZnO) from zinc acetate and urea as raw materials was performed using conventional water bath heating and a microwave hydrothermal (MH) method in an aqueous solution. The oxide formation is controlled by decomposition of the added urea in the sealed autoclave. The influence of urea and the synthesis method on the final product formation are discussed. Broadband photoluminescence (PL) behavior in visible-range spectra was observed with a maximum peak centered in the green region which was attributed to different defects and the structural changes involved with ZnO crystals which were produced during the nucleation process.

THE LOG-BURR XII REGRESSION MODEL FOR GROUPED SURVIVAL DATA

The log-Burr XII regression model for grouped survival data is evaluated in the presence of many ties. The methodology for grouped survival data is based on life tables, where the times are grouped in k intervals, and we fit discrete lifetime regression models to the data. The model parameters are estimated by maximum likelihood and jackknife methods. To detect influential observations in the proposed model, diagnostic measures based on case deletion, so-called 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 these measures, the total local influence and influential estimates are also used. We conduct Monte Carlo simulation studies to assess the finite sample behavior of the maximum likelihood estimators of the proposed model for grouped survival. A real data set is analyzed using a regression model for grouped data.

The Poisson-exponential regression model under different latent activation schemes

In this paper, a new family of survival distributions is presented. It is derived by considering that the latent number of failure causes follows a Poisson distribution and the time for these causes to be activated follows an exponential distribution. Three different activation schemes are also considered. Moreover, we propose the inclusion of covariates in the model formulation in order to study their effect on the expected value of the number of causes and on the failure rate function. Inferential procedure based on the maximum likelihood method is discussed and evaluated via simulation. The developed methodology is illustrated on a real data set on ovarian cancer.

Men's health: a population-based study on social inequalities

This study evaluates social inequalities in health according to level of schooling in the male population. This was a cross-sectional, population-based study with a sample of 449 men ranging from 20 to 59 years of age and living in Campinas, Sao Paulo State, Brazil. The chi-square test was used to verify associations, and a Poisson regression model was used to estimate crude and adjusted prevalence ratios. Men with less schooling showed higher rates of alcohol consumption and dependence, smoking, sedentary lifestyle during leisure time, and less healthy eating habits, in addition to higher prevalence of bad or very bad self-rated health, at least one chronic disease, hypertension, and other health problems. No differences were detected between the two schooling strata in terms of use of health services, except for dental services. The findings point to social inequality in health-related behaviors and in some health status indicators. However, possible equity was observed in the use of nearly all types of health services.

Underlying Factors Associated with Anemia in Amazonian Children: A Population-Based, Cross-Sectional Study

Background: Although iron deficiency is considered to be the main cause of anemia in children worldwide, other contributors to childhood anemia remain little studied in developing countries. We estimated the relative contributions of different factors to anemia in a population-based, cross-sectional survey. Methodology: We obtained venous blood samples from 1111 children aged 6 months to 10 years living in the frontier town of Acrelandia, northwest Brazil, to estimate the prevalence of anemia and iron deficiency by measuring hemoglobin, erythrocyte indices, ferritin, soluble transferrin receptor, and C-reactive protein concentrations. Children were simultaneously screened for vitamin A, vitamin B-12, and folate deficiencies; intestinal parasite infections; glucose-6-phosphate dehydrogenase deficiency; and sickle cell trait carriage. Multiple Poisson regression and adjusted prevalence ratios (aPR) were used to describe associations between anemia and the independent variables. Principal Findings: The prevalence of anemia, iron deficiency, and iron-deficiency anemia were 13.6%, 45.4%, and 10.3%, respectively. Children whose families were in the highest income quartile, compared with the lowest, had a lower risk of anemia (aPR, 0.60; 95% CI, 0.37-0.98). Child age (<24 months, 2.90; 2.01-4.20) and maternal parity (>2 pregnancies, 2.01; 1.40-2.87) were positively associated with anemia. Other associated correlates were iron deficiency (2.1; 1.4-3.0), vitamin B-12 (1.4; 1.0-2.2), and folate (2.0; 1.3-3.1) deficiencies, and C-reactive protein concentrations (>5 mg/L, 1.5; 1.1-2.2). Conclusions: Addressing morbidities and multiple nutritional deficiencies in children and mothers and improving the purchasing power of poorer families are potentially important interventions to reduce the burden of anemia.

Respiratory diseases and associated factors: population-based study in Sao Paulo, Brazil, 2008-2009

OBJECTIVE: To assess the prevalence of acute bronchitis, rhinitis, and sinusitis among children and adolescents and identify associated factors. METHODS: This is a population-based, cross-sectional study. A household survey was conducted with 1,185 children and adolescents from the city of Sao Paulo (Southeastern Brazil), from 2008 to 2009. The participants were selected by means of probability sampling, stratified by sex and age, and by two-stage cluster sampling. For the adjusted analysis, multiple Poisson regression was used. RESULTS: Of the respondents, 7.3% reported acute bronchitis, 22.6% rhinitis and 15.3% sinusitis. After the adjusted analysis, the following characteristics were associated with self;reported acute bronchitis: age 0 to 4 years (PR=17.86; 95%Cl: 3.65;90.91), 5 to 9 years (PR=37.04; 95%CI: 8.13;166.67), 10 to 14 years (PR.=20,83; 95%Cl: 4.93;90.91), allergy (PR=3.12; 95%Cl: 1.70;5.73), black and mixed-ethnicity (black and white) skin color (PR=2.29; 95%Cl: 1.21;4.35), and living in a household with 1 to 3 rooms (PR=1.85; 95%Cl: 1.17;2.94). As to self-reported rhinitis, the following characteristics were associated: age 10 to 14 years (PR=2.77; 95%Cl: 1.60;4.78), 15 to 19 years (P.R=2.58; 95%Cl: 1.52;4.39), allergy (PR=4.32; 95%Cl: 2.79;6.70), asthma (PR=2.30; 95%CI: 1.30;4.10) and living in flats (PR=1.70; 95%Cl: 1.06;2.73). Concerning self-reported sinusitis, the following characteristics were associated: age 5 to 9 years (PR=2.44; 95%Cl: 1.09;5.43), 10 to 14 years (PR=2.99; 95%CI: 1.36;6.58), 15 to 19 years (PR=3.62; 95%Cl: 1.68;7.81), allergy (PR=2.23 (95%CI: 1.41;3.52) and obesity (PR=4.42; 95%Cl: 1.56;12.50). CONCLUSIONS: Respiratory diseases were more prevalent in population groups with defined characteristics, such as age group, self-reported diseases, type of household and obesity.

A log-Birnbaum-Saunders regression model with asymmetric errors

This paper introduces a skewed log-Birnbaum-Saunders regression model based on the skewed sinh-normal distribution proposed by Leiva et al. [A skewed sinh-normal distribution and its properties and application to air pollution, Comm. Statist. Theory Methods 39 (2010), pp. 426-443]. Some influence methods, such as the local influence and generalized leverage, are presented. Additionally, we derived the normal curvatures of local influence under some perturbation schemes. An empirical application to a real data set is presented in order to illustrate the usefulness of the proposed model.

Covariates of high-risk human papillomavirus (HPV) infections are distinct for incident CIN1, CIN2 and CIN3 as disclosed by competing-risks regression models

Background: In addition to the oncogenic human papillomavirus (HPV), several cofactors are needed in cervical carcinogenesis, but whether the HPV covariates associated with incident i) CIN1 are different from those of incident ii) CIN2 and iii) CIN3 needs further assessment. Objectives: To gain further insights into the true biological differences between CIN1, CIN2 and CIN3, we assessed HPV covariates associated with incident CIN1, CIN2, and CIN3. Study Design and Methods: HPV covariates associated with progression to CIN1, CIN2 and CIN3 were analysed in the combined cohort of the NIS (n = 3,187) and LAMS study (n = 12,114), using competing-risks regression models (in panel data) for baseline HR-HPV-positive women (n = 1,105), who represent a sub-cohort of all 1,865 women prospectively followed-up in these two studies. Results: Altogether, 90 (4.8%), 39 (2.1%) and 14 (1.4%) cases progressed to CIN1, CIN2, and CIN3, respectively. Among these baseline HR-HPV-positive women, the risk profiles of incident GIN I, CIN2 and CIN3 were unique in that completely different HPV covariates were associated with progression to CIN1, CIN2 and CIN3, irrespective which categories (non-progression, CIN1, CIN2, CIN3 or all) were used as competing-risks events in univariate and multivariate models. Conclusions: These data confirm our previous analysis based on multinomial regression models implicating that distinct covariates of HR-HPV are associated with progression to CIN1, CIN2 and CIN3. This emphasises true biological differences between the three grades of GIN, which revisits the concept of combining CIN2 with CIN3 or with CIN1 in histological classification or used as a common end-point, e.g., in HPV vaccine trials.

Gender-based violence and socioeconomic inequalities: Does living in more deprived neighbourhoods increase women's risk of intimate partner violence?

This study investigates the influence of neighbourhood socioeconomic conditions on women's likelihood of experiencing intimate partner violence (IPV) in Sao Paulo, Brazil. Data from 940 women who were interviewed as part of the WHO multi-country study on women's health and domestic violence against women, and census data for Sao Paulo City, were analyzed using multilevel regression techniques. A neighbourhood socioeconomic-level scale was created, and proxies for the socioeconomic positions of the couple were included. Other individual level variables included factors related to partner's behaviour and women's experiences and attitudes. Women's risk of IPV did not vary across neighbourhoods in Sao Paulo nor was it influenced by her individual socioeconomic characteristics. However, women in the middle range of the socioeconomic scale were significantly more likely to report having experienced violence by a partner. Partner behaviours such as excessive alcohol use, controlling behaviour and multiple sexual partnerships were important predictors of IPV. A women's likelihood of IPV also increased if either her mother had experienced IPV or if she used alcohol excessively. These findings suggest that although the characteristics of people living in deprived neighbourhoods may influence the probability that a woman will experience IPV, higher-order contextual dynamics do not seem to affect this risk. While poverty reduction will improve the lives of individuals in many ways, strategies to reduce IPV should prioritize shifting norms that reinforce certain negative male behaviours. (C) 2012 Elsevier Ltd. All rights reserved.

Solid electrolytes for electrochromic devices based on reversible metal electrodeposition

Air conditioning and lighting costs can be reduced substantially by changing the optical properties of "intelligent windows." The electrochromic devices studied to date have used copper as an additive. Copper, used here as an electrochromic material, was dissolved in an aqueous animal protein-derived gel electrolyte. This combination constitutes the electrochromic system for reversible electrodeposition. Cyclic voltammetry, chronoamperometric and chromogenic analyses indicated that were obtained good conditions of transparency (initial transmittance of 70%), optical reversibility, small potential window (2.1 V), variation of transmittance in visible light (63.6%) and near infrared (20%) spectral regions. Permanence in the darkened state was achieved by maintaining a lower pulse potential (-0.16 V) than the deposition potential (-1.0 V). Increasing the number of deposition and dissolution cycles favored the transmittance and photoelectrochemical reversibility of the device. The conductivity of the electrolyte (10(-3) S/cm) at several concentrations of CuCl2 was determined by electrochemical impedance spectroscopy. A thermogravimetric analysis confirmed the good thermal stability of the electrolyte, since the mass loss detected up to 100 degrees C corresponded to water evaporation and decomposition of the gel started only at 200 degrees C. Micrographic and small angle X-ray scattering analyses indicated the formation of a persistent deposit of copper particles on the ITO. (C) 2012 Elsevier B.V. All rights reserved.