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

A flexible model for survival data with a cure rate: a Bayesian approach

In this paper we deal with a Bayesian analysis for right-censored survival data suitable for populations with a cure rate. We consider a cure rate model based on the negative binomial distribution, encompassing as a special case the promotion time cure model. Bayesian analysis is based on Markov chain Monte Carlo (MCMC) methods. We also present some discussion on model selection and an illustration with a real dataset.

A hands-on approach for fitting long-term survival models under the GAMLSS framework

In many data sets from clinical studies there are patients insusceptible to the occurrence of the event of interest. Survival models which ignore this fact are generally inadequate. The main goal of this paper is to describe an application of the generalized additive models for location, scale, and shape (GAMLSS) framework to the fitting of long-term survival models. in this work the number of competing causes of the event of interest follows the negative binomial distribution. In this way, some well known models found in the literature are characterized as particular cases of our proposal. The model is conveniently parameterized in terms of the cured fraction, which is then linked to covariates. We explore the use of the gamlss package in R as a powerful tool for inference in long-term survival models. The procedure is illustrated with a numerical example. (C) 2009 Elsevier Ireland Ltd. All rights reserved.

A Bayesian Long-term Survival Model Parametrized in the Cured Fraction

The main goal of this paper is to investigate a cure rate model that comprehends some well-known proposals found in the literature. In our work the number of competing causes of the event of interest follows the negative binomial distribution. The model is conveniently reparametrized through the cured fraction, which is then linked to covariates by means of the logistic link. We explore the use of Markov chain Monte Carlo methods to develop a Bayesian analysis in the proposed model. The procedure is illustrated with a numerical example.

Power series generalized nonlinear models

We introduce in this paper a new class of discrete generalized nonlinear models to extend the binomial, Poisson and negative binomial models to cope with count data. This class of models includes some important models such as log-nonlinear models, logit, probit and negative binomial nonlinear models, generalized Poisson and generalized negative binomial regression models, among other models, which enables the fitting of a wide range of models to count data. We derive an iterative process for fitting these models by maximum likelihood and discuss inference on the parameters. The usefulness of the new class of models is illustrated with an application to a real data set. (C) 2008 Elsevier B.V. All rights reserved.

Comparasion of two minimally invasive methods on the longevity of glass ionomer cement restorations: short-term results of a pilot study

The purpose of this study was to evaluate the clinical performance of glass ionomer cement (GIC) restorations comparing two minimally invasive methods in permanent teeth after 12 months. Fifty pregnant women (second trimester of pregnancy), mean age 22 ± 5.30 years, were treated by two previously trained operators. The treatment approaches tested were: chemomechanical method (CarisolvTM; MediTeam) and atraumatic restorative treatment (ART). A split-mouth study design was used in which the two treatments were randomly placed in 50 matched pairs of permanent teeth. The chemomechanical method (CM) was the test group and the ART was the control group. The treatments were performed in Public Health Centers. The tested restorative material was a high-strength GIC (Ketac Molar; 3M/ESPE). The restorations were placed according to the ART guidelines. Two calibrated independent examiners evaluated the restorations in accordance with ART criteria. The inter-examiner kappa was 0.97. Data were analyzed using 95% confidence interval on the binomial distribution and Fisher's exact test at 5% significance level. In a 12-month follow-up, 86% of the restorations were evaluated. In the test group (CM), 100% (CI=93.3-100%) of the restorations were considered successful. In the control group (ART) 97.6% (CI=87.4-99.9%) of the restorations were considered successful and 2.4% unsuccessful (marginal defect >0.5 mm). There was no statistically significant difference between the 12-mounth success rate for both groups (Fisher's exact test: P=0.49) and between the two operators (Fisher's exact test: P=1.00). Both minimally invasive methods, chemomechanical method and ART, showed a similar clinical performance after 12 months of follow up.

Double generalized linear model for tissue culture proportion data: a Bayesian perspective

Joint generalized linear models and double generalized linear models (DGLMs) were designed to model outcomes for which the variability can be explained using factors and/or covariates. When such factors operate, the usual normal regression models, which inherently exhibit constant variance, will under-represent variation in the data and hence may lead to erroneous inferences. For count and proportion data, such noise factors can generate a so-called overdispersion effect, and the use of binomial and Poisson models underestimates the variability and, consequently, incorrectly indicate significant effects. In this manuscript, we propose a DGLM from a Bayesian perspective, focusing on the case of proportion data, where the overdispersion can be modeled using a random effect that depends on some noise factors. The posterior joint density function was sampled using Monte Carlo Markov Chain algorithms, allowing inferences over the model parameters. An application to a data set on apple tissue culture is presented, for which it is shown that the Bayesian approach is quite feasible, even when limited prior information is available, thereby generating valuable insight for the researcher about its experimental results.

Tooth loss in Brazilian middle-aged adults: multilevel effects

Objective. To examine the link between tooth loss and multilevel factors in a national sample of middle-aged adults in Brazil. Material and methods. Analyses were based on the 2003 cross-sectional national epidemiological survey of the oral health of the Brazilian population, which covered 13 431 individuals (age 35-44 years). Multistage cluster sampling was used. The dependent variable was tooth loss and the independent variables were classified according to the individual or contextual level. A multilevel negative binomial regression model was adopted. Results. The average tooth loss was 14 (standard deviation 9.5) teeth. Half of the individuals had lost 12 teeth. The contextual variables showed independent effects on tooth loss. It was found that having 9 years or more of schooling was associated with protection against tooth loss (means ratio range 0.68-0.76). Not having visited the dentist and not having visited in the last >= 3 years accounted for increases of 33.5% and 21.3%, respectively, in the risk of tooth loss (P < 0.05). The increase in tooth extraction ratio showed a strong contextual effect on increased risk of tooth loss, besides changing the effect of protective variables. Conclusions. Tooth loss in middle-aged adults has important associations with social determinants of health. This study points to the importance of the social context as the main cause of oral health injuries suffered by most middle-aged Brazilian adults.

Physical disability, recent illnesses and health self-assessment in a population-based study in Sao Paulo, Brazil

Objectives. To investigate health self-assessment and to estimate the prevalence of chronic diseases and recent illnesses in people with and without physical disabilities (PD) in the state of Sao Paulo, southeastern Brazil. Study design. A Cross-sectional study comprising two population-based health surveys conducted in 2002 and 2003. Methods. A total of 8317 persons (165 with PD) were interviewed in the two studies. Variables concerning to health self-assessment; chronic disease and recent illness were compared in the people with and without PD. Negative binomial regression was used in the analysis. Results. Subjects with PD more often assessed their health as poor/very poor compared to non-disabled ones. They reported more illnesses in the 15 days prior to interview as well as more chronic diseases (skin conditions, anaemia, chronic kidney disease, stroke, depression/anxiety, migraine/headache, pulmonary diseases, hypertension, diabetes, arthritis/arthrosis/rheumatic conditions and heart disease). This higher disease prevalence can be either attributed to disability itself or be associated to gender, age and schooling. Conclusions. Subjects with PD had more recent illnesses and chronic diseases and poorer health self-assessment than non-disabled ones. Age, gender, schooling and disability have individual roles in disease development among disabled people.

Random sums of exchangeable variables and actuarial applications

In this paper we study the accumulated claim in some fixed time period, skipping the classical assumption of mutual independence between the variables involved. Two basic models are considered: Model I assumes that any pair of claims are equally correlated which means that the corresponding square-integrable sequence is exchangeable one. Model 2 states that the correlations between the adjacent claims are the same. Recurrence and explicit expressions for the joint probability generating function are derived and the impact of the dependence parameter (correlation coefficient) in both models is examined. The Markov binomial distribution is obtained as a particular case under assumptions of Model 2. (C) 2007 Elsevier B.V. All rights reserved.

Self-organized distribution of periodicity and chaos in an electrochemical oscillator

We report a detailed numerical investigation of a prototype electrochemical oscillator, in terms of high-resolution phase diagrams for an experimentally relevant section of the control (parameter) space. The prototype model consists of a set of three autonomous ordinary differential equations which captures the general features of electrochemical oscillators characterized by a partially hidden negative differential resistance in an N-shaped current-voltage stationary curve. By computing Lyapunov exponents, we provide a detailed discrimination between chaotic and periodic phases of the electrochemical oscillator. Such phases reveal the existence of an intricate structure of domains of periodicity self-organized into a chaotic background. Shrimp-like periodic regions previously observed in other discrete and continuous systems were also observed here, which corroborate the universal nature of the occurrence of such structures. In addition, we have also found a structured period distribution within the order region. Finally we discuss the possible experimental realization of comparable phase diagrams.

Prevalence and distribution of the GBV-C/HGV among HIV-1-infected patients under anti-retroviral therapy

Infection with GB virus C (GBV-C) or hepatitis G virus (HGV) is highly prevalent among HIV/AIDS patients. GBV-C/HGV viremia has not been associated with liver disease and seems to slow HIV disease progression. To study the GBV-C/HGV genotypes prevalence among HIV/AIDS patients and its association with HIV viral load (VL) and CD4+ lymphocyte counts. From February 2003 to February 2004, we analyzed 210 HIV-1-infected subjects who were on anti-retroviral therapy (ART). For 63 of them a PCR-nested to the non-coding 5` (5`NCR) region of the GBV-C/HGV was done, and for 49 a DNA direct sequencing was done. A phylogenetic analysis was performed by PHYLIP program. 63(30%) of the HIV-1-infected patients were co-infected with GBV-C/HGV. The phylogenetic analysis revealed the following genotypes (and respective relative frequencies): 1(10%), 2a (41%), 2b (43%), and 3 (6%). Co-infected patients presented lower HIV-1 VL and higher T CD4+ lymphocyte cells counts as compared with patients negative for GBV-C/HGV sequences (log = 4.52 vs. 4.71, p = 0.036), and T CD4+ lymphocyte counts (cells/mm(3) = 322.6 vs. 273.5, p = 0.081, respectively). T CD4+ cells counts equal to, or higher than, 200/mm(3) were significantly more common among co-infected patients than among HIV-infected-only patients (p = 0.042). The lowest T CD4+ cells counts were associated with genotype 1 and the highest with genotype 2b (p = 0.05). The GBV-C/HGV infection prevalence was 30% among HIV-1-infected subjects, and was associated with lower VL and higher CD4+ lymphocyte counts. GBV-C/HGV genotype 2b may be associated with better immunological response. Published by Elsevier B.V.

Prevalence and nonrandom distribution of exonic mutations in interferon regulatory factor 6 in 307 families with Van der Woude syndrome and 37 families with popliteal pterygium syndrome

Purpose: Interferon regulatory factor 6 encodes a member of the IRF family of transcription factors. Mutations in interferon regulatory factor 6 cause Van der Woude and popliteal pterygium syndrome, two related orofacial clefting disorders. Here, we compared and contrasted the frequency and distribution of exonic Mutations in interferon regulatory factor 6 between two large geographically distinct collections of families with Van der Woude and between one collection of families with popliteal pterygium syndrome. Methods: We performed direct sequence analysis of interferon regulatory factor 6 exons oil samples from three collections, two with Van der Woude and one with popliteal pterygium syndrome. Results: We identified mutations in interferon regulatory factor 6 exons in 68% of families in both Van der Woude collections and in 97% of families with popliteal pterygium syndrome. In sum, 106 novel disease-causing variants were found. The distribution of mutations in the interferon regulatory factor 6 exons in each collection was not random; exons 3, 4, 7, and 9 accounted for 80%. In the Van der Woude collections, the mutations were evenly divided between protein truncation and missense, whereas most mutations identified in the popliteal pterygium syndrome collection were missense. Further, the missense mutations associated with popliteal pterygium syndrome were localized significantly to exon 4, at residues that are predicted to bind directly to DNA. Conclusion: The nonrandom distribution of mutations in the interferon regulatory factor 6 exons suggests a two-tier approach for efficient mutation screens for interferon regulatory factor 6. The type and distribution of mutations are consistent with the hypothesis that Van der Woude is caused by haploinsufficiency of interferon regulatory factor 6. Oil the other hand, the distribution of popliteal pterygium syndrome-associated mutations suggests a different, though not mutually exclusive, effect oil interferon regulatory factor 6 function. Genet Med 2009:11(4):241-247.

A New Class of Non Negative Distributions Generated by Symmetric Distributions

In this article, we study a new class of non negative distributions generated by the symmetric distributions around zero. For the special case of the distribution generated using the normal distribution, properties like moments generating function, stochastic representation, reliability connections, and inference aspects using methods of moments and maximum likelihood are studied. Moreover, a real data set is analyzed, illustrating the fact that good fits can result.

Beta-binomial/Poisson regression models for repeated bivariate counts

We analyze data obtained from a study designed to evaluate training effects on the performance of certain motor activities of Parkinson`s disease patients. Maximum likelihood methods were used to fit beta-binomial/Poisson regression models tailored to evaluate the effects of training on the numbers of attempted and successful specified manual movements in 1 min periods, controlling for disease stage and use of the preferred hand. We extend models previously considered by other authors in univariate settings to account for the repeated measures nature of the data. The results suggest that the expected number of attempts and successes increase with training, except for patients with advanced stages of the disease using the non-preferred hand. Copyright (c) 2008 John Wiley & Sons, Ltd.