Bayesian control charts based on predictive distributions

Loading...
Thumbnail Image
Date
2016-01
Authors
Van Zyl, Ruaan
Journal Title
Journal ISSN
Volume Title
Publisher
University of the Free State
Abstract
English: Control charts are statistical process control (SPC) tools that are widely used in the monitoring of processes, specifically taking into account stability and dispersion. Control charts signal when a significant change in the process being studied is observed. This signal can then be investigated to identify issues and to find solutions. It is generally accepted that SPC are implemented in two phases, Phase I and Phase II. In Phase I the primary interest is assessing process stability, often trying to bring the process in control by locating and eliminating any assignable causes, estimating any unknown parameters and setting up the control charts. After that the process move on to Phase II where the control limits obtained in Phase I are used for online process monitoring based on new samples of data. This thesis concentrate mainly on implementing a Bayesian approach to monitoring processes using SPC. This is done by providing an overview of some non-informative priors and then to specifically derive the reference and probability-matching priors for the common coefficient of variation, standardized mean and tolerance limits for a normal population. Using the Bayesian approach described in this thesis SPC is performed, including derivations of control limits in Phase I and monitoring by the use of runlengths and average run-lengths in Phase II for the common coefficient of variation, standardized mean, variance and generalized variance, tolerance limits for normal populations, two-parameter exponential distribution, piecewise exponential model and capability indices. Results obtained using the Bayesian approach are compared to frequentist results.
Afrikaans: Beheer kaarte is statistiese beheer prosesse wat gebruik word om prosesse te monitor, deur veral na stabiliteit en verspreiding te kyk. Beheer kaarte gee ’n waarskuwingsein as daar ’n bedeidende verandering in die proses wat bestudeer word opgemerk word. Hierdie sein kan dan ondersoek word om probleme te identifiseer en op te los. Dit word oor die algemeen aanvaar dat statististiese beheer prosesse in twee fases geimplementeer word. In Fase I word die stabiliteit van die proses geasseseer en die proses word in beheer gebring deur redes vir probleme te identifseer en op te los, onbekende parameters word bepaal en die beheer kaarte word opgestel. In Fase II word die beheer limiete wat in Fase I bereken is gebruik deur ’n voortdurende proses te monitor met nuwe data. Hierdie proefskrif handel grotendeels oor die implementeering van ’n Bayesiaanse metode om statistiese beheer toe te pas. Dit word gedoen deur nie-objektiewe priors te bereken, meer spesifiek die verwysingsprior en die waarskynlikheidsooreenstemmende prior te bereken vir die algemene koeffisient van variasie, die gestandardiseerde gemiddelde en toleransie limiete vir ’n normale populasie. Deur die gebruik van die Bayes metode uiteen gesit in hierdie proefskrif, insluitend die berekeninge van beheer limiete in Fase I en die monitering deur gebruik te maak van proses-lengte en gemidelde proses-lengte in Fase II vir die algemene koeffisient van variasie, gestandardiseerde gemiddelde, variansie en algemene variansie, toleransie limiete vir die normale populasie, twee-parameter eksponensiele verdeling, stuksgewysde eksponensiele model en vermoë indekse. Resultate deur die Bayes proses is dan vergelyk met resultate uit die klassieke statistiek.
Description
Keywords
Statistical process control, Run-length, Control charts, Non-informative priors, Reference priors, Probability-matching priors, Bayes, Bayesian statistical decision theory, Thesis (Ph.D. (Mathematical Statistics and Actuaral Science))--University of the Free State, 2016
Citation