This paper investigates the occurrence of severe oral mucositis and associated factors in blood solid cancer pediatric patients subjected to treatment, using a survival analysis. A longitudinal, descriptive, observational inductive study 142 aged from 0 19 years was conducted 2013 2017. Data were collected form record sociodemographic characteristics health-related aspects modified Oral Assessment Guide (OAG). Survival analysis performed Kaplan-Meier method Cox semiparametric model. The...

Beta regression models are useful for modeling data that assume values in the standard unit interval (0, 1), such as rates and proportions. These models, however, cannot be used when contain observations equal zero or one (the limits of interval). Ospina Ferrari (2012 OspinaR.FerrariS. L. P. (2012) A general class zero-or-one inflated beta Computational Statistics Data Analysis 56:1609–1623.[Crossref], [Web Science ®] , [Google Scholar]) developed regressions to handle situations which...

The present paper proposes a control chart for monitoring quality characteristics that take values in the (0,1] or [0,1) interval, such as rates proportions can contain zero one with positive probability. proposed has limits defined from inflated unit gamma distribution. An extensive Monte Carlos simulation study was carried out to evaluate performance of charts terms run length. We performed comparison between and beta chart, considering two approaches. considered individuals first approach...

AbstractThe class of inflated beta regression models generalizes that regressions [S.L.P. Ferrari and F. Cribari-Neto, Beta for modelling rates proportions, J. Appl. Stat. 31 (2004), pp. 799–815] by incorporating a discrete component allows practitioners to model data on proportions with observations equal an interval limit. For instance, one can responses assume values in (0, 1]. The likelihood ratio test tends be quite oversized (liberal, anticonservative) estimated small number...

This paper provides a general framework for controlling quality characteristics related to control variables and limited the intervals (0, 1], [0, 1), or 1]. The proposed chart is based on inflated beta regression model considering reparametrization of distribution indexed by response mean, which useful modeling fractions proportions. contribution twofold. First, we extend allowing structure precision parameter. We also present closed-form expressions score vector Fisher's information...

The inflated beta regression model aims to enable the modeling of responses in intervals (0, 1], [0, 1), or 1]. In this model, hypothesis testing is often performed based on likelihood ratio statistic. critical values are obtained from asymptotic approximations, which may lead distortions size small samples. sense, article proposes bootstrap Bartlett correction statistic model. proposed adjustment only requires a simple Monte Carlo simulation. Through extensive simulations finite sample...

In this paper we model the administrative efficiencies of Brazilian municipalities grouped by regions.We use inflated beta regression model, since efficiency indices take values in interval (0,1].Fully efficient units have unit scores.Except for North Brazil, urban counties tend to be more than non-urban ones.In Northeast and Southeast regions, that receive royalties excess 10% their total revenue less they would otherwise.The same holds Northeast, Midwest regions part intermunicipal...

The beta prime regression model proposed by Bourguignon, Santos-Neto, and de Castro is an alternative to the generalized linear models useful positive asymmetric data. In this paper, we propose two general misspecification tests based on RESET test for with varying precision. first test, add testing variable in mean submodel, whereas second focuses adding variables all submodels. We conduct extensive Monte Carlo simulation study evaluate performance of finite sample size terms their sizes...

We consider testing inference in inflated beta regressions subject to model misspecification. In particular, quasi-z tests based on sandwich covariance matrix estimators are described and their finite sample behavior is investigated via Monte Carlo simulations. The numerical evidence shows that can be considerably more accurate than made through the usual z tests, especially when there Interval estimation also considered. present an empirical application uses real (not simulated) data.