Сравнение на методи

	Контролна карта по Бейсовски	Байесов контрол на статистически процеси
Област	Планиране на експеримента	Планиране на експеримента
Семейство	Process / pipeline	Process / pipeline
Година на възникване	Formally developed in the 1990s–2000s; roots in Shewhart (1924)	1950s (foundations); formalized 1990s–2000s
Създател	Ulrich Menzefricke and others building on Shewhart (1924) and Bayesian inference (Bayes, 1763)	Various (Girshick & Rubin 1952 early signal detection; Menzefricke 2002 Bayesian control chart framework)
Тип	Statistical process monitoring / quality control	Bayesian process monitoring technique
Основополагащ източник	Menzefricke, U. (2002). On the evaluation of control chart limits based on predictive distributions. Communications in Statistics — Theory and Methods, 31(8), 1423–1440.	Menzefricke, U. (2002). On the evaluation of control chart factors for monitoring the process mean and variance. Journal of Quality Technology, 34(2), 167–178.
Други названия	Bayesian SPC chart, Bayesian monitoring chart, posterior control chart, Bayesian Shewhart chart	Bayesian SPC, Bayesian process monitoring, B-SPC, Bayesian control charting
Свързани	6	5
Резюме	A Bayesian control chart integrates prior knowledge about a process — such as historical mean and variance — with incoming measurement data to produce dynamically updated control limits. Unlike classical Shewhart charts that fix limits from a Phase-I baseline, Bayesian charts update the posterior distribution of process parameters after each sample, yielding limits that adapt to accumulated evidence and are better calibrated under small sample sizes or non-stationary processes.	Bayesian Statistical Process Control (Bayesian SPC) extends classical SPC by replacing fixed, frequentist control limits with a probabilistic framework that incorporates prior knowledge about the process. Rather than waiting for a run of points to exceed a pre-set 3-sigma boundary, Bayesian SPC continuously updates the probability that the process has shifted given the incoming data, enabling earlier and more informed detection of out-of-control states while formally accounting for uncertainty in process parameters.