Abstract

Abstract
We consider two sampling plans by variables to inspect batches of products from an industrial process under a context of unknown distribution underlying the measurements of the quality characteristic under study. Through the use of the bootstrap methodology and Monte Carlo simulations we evaluate and compare the performance of those sampling plans in terms of probability of acceptance of lots and average outgoing quality level.

Abstract
In real situations the evaluation of the global quality of either a product or a service depends on more than one quality characteristic. In order to monitor the variability of multivariate processes and identify the variables responsible for changes in the process, we will use the STATIS (Structuration des Tableaux A Trois Indices de la Statistique) methodology, a three-way data analysis method. For this purpose we consider a control chart based on a similarity measure between two positive semi-definite matrices, the RV coefficient, and we evaluate the performance of this control chart for monitoring multivariate normal data.

Abstract
A control chart based on the quantile function to monitor the shape parameter of a Weibull distribution is proposed and its performance is analyzed by Monte Carlo simulation. The importance of monitoring the shape parameter even when the other parameters of the Weibull distribution are assumed known is further enhanced, together with motivating examples. © 2014 Proceedings of COMPSTAT 2014 - 21st International Conference on Computational Statistics. All rights reserved.

Abstract

Abstract
Background: Handgrip strength (HGS) is a useful indicator of nutrition status in adults, but evidence is lacking in pediatric patients. The aim of this study was to describe the association between undernutrition and HGS in pediatric patients at hospital admission, quantifying the modifying effect of disease severity, anthropometrics, and other patient characteristics on HGS. Materials and Methods: Eighty-nine inpatients aged >= 6 years consecutively admitted were recruited in a longitudinal study. Nutrition status was evaluated using body mass index (BMI) z scores, and HGS was evaluated at admission and discharge. Results: In the total sample, 30.3% of patients were undernourished at admission, and 64% lost HGS during the hospital stay. This study showed that HGS at admission was independently associated with undernutrition defined by BMI z scores (beta = 0.256, P = .037). In this multivariate analysis, sex, age, height, and BMI z scores explained 67.1% of HGS at hospital admission. Conclusion: Lower HGS may be a potential marker of undernutrition in hospitalized pediatric patients, although HGS data should be interpreted according to sex, age, and height of the patient.