Statistical Monitoring of Nominal Logistic Profiles in Phase II

Noorossana, Rassoul; Niaki, Seyed Taghi Akhavan; Izadbakhsh, Hamidreza

doi:10.1080/03610926.2013.788712

Cited by 12 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MEWMA which was proposed by Zou et al [26], is also applicable in monitoring generalized linear profiles. Soleymanian et al [12] and Noorossana et al [15] used this method for monitoring generalized linear profiles. MEWMA statistic for the j th profile is calculated as: (15) In Equation 15, Z j is a q-dimensional vector which equals to:…”

Section: Mewma Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Phase II Monitoring of Generalized Linear Profiles Under Different Types of Changes

Hajifar

Mahlooji

2019

Scientia Iranica

View full text Add to dashboard Cite

Various control charts have been proposed to monitor generalized linear profiles in Phase II. However, robustness of the proposed methods in detecting different types and especially different directions of changes is not well-studied in the literature. In real-world applications different kinds of changes such as drift and multiple change are likely to happen which can be isotonic (increasing) or antitonic (decreasing). This paper studies the robustness of Rao Score Test (RST) method, T 2 , and multivariate exponential weighted moving average (MEWMA) in different types, drift and multiple, and directions of changes. Rao Score Test method also benefits from a change-point detection approach whose performance is studied as well. According to the results, generally RST method shows a better performance in detecting different types of changes. Moreover, the performance of the RST method is robust to direction of the change, while T 2 and MEWMA are not ARL-unbiased and show different performances under isotonic and antitonic changes. Therefore, to address this issue, we proposed a biasreduced estimator to be used in T 2. Our results demonstrate that the proposed control chart outperforms T 2 and is less biased than T 2. Finally, a real-world problem is presented in which aforementioned methods are applied to real data.

show abstract

Section: Mewma Methodsmentioning

confidence: 99%

“…Nevertheless, 2 performs better than other methods when the step change or drift occurs in both regression parameters simultaneously. Noorossana et al [15] evaluated four methods in Phase II monitoring of polytomous profiles. Their results demonstrate that MEWMA method performs better in detecting small size changes.…”

Section: Introductionmentioning

confidence: 99%

Phase II Monitoring of Generalized Linear Profiles Under Different Types of Changes

Hajifar

Mahlooji

2019

Scientia Iranica

View full text Add to dashboard Cite

show abstract

“…It can be statistically checked that " j 0 s; j = lt + 1; :::; T are independent and identically distributed as: (14) where U = lt +1 0 ; lt +2 0 ; :::; ; (15) where vector b is estimated according to Eq. (14).…”

Section: Proposed Estimator Under Step Changementioning

confidence: 99%

“…Saghaei et al [10] proposed two methods including EWMA2 and Hotelling's T 2 control charts for Phase II monitoring of logistic pro les under binary responses. Four methods, namely, Multivariate Exponentially Weighted Moving Average (MEWMA), 2 , Exponentially Weighted Moving Average (EWMA) with R statistic, and a combination of the last two statistics, were proposed by Noorossana et al [11] to monitor OLR pro les in Phase II. Soleymanian et al [12] proposed four control charts including Hotelling's T 2 , MEWMA, LRT, and LRT/EWMA to monitor pro les with binary response variable in Phase II.…”

Section: Introductionmentioning

confidence: 99%

“…They converted the multinomial logistic regression to the Poisson GLM using log link and proposed two methods including MEWMA and LRT statistics to monitor multinomial logistic regression pro les in Phase II. Using three approaches including LRT, MEWMA, and Support Vector Machine (SVM), the Phase II monitoring of logistic regression pro les was studied by Noorossana et al [14]. Shadman et al [15] introduced a uni ed framework based on Rao score test to monitor GLM pro les in Phase II.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identifying the time of step change and drift in Phase II monitoring of autocorrelated logistic regression profiles

2017

View full text Add to dashboard Cite

In some pro le monitoring applications, the independency assumption of consecutive binary response values within each pro le is violated. To the best of our knowledge, estimating the time of a change in the parameters of an autocorrelated binary pro le is neglected in the literature. In this paper, two maximum likelihood estimators are proposed to estimate the real time of step changes and drift in Phase II monitoring of binary pro les in the case of within-pro le autocorrelation. Our proposed estimators identify the change point not only in the autocorrelated logistic regression parameters, but also in autocorrelation coe cient. The performance of the proposed estimators to identify the time of change points either in regression parameters or autocorrelation coe cient is evaluated through simulation studies. The results, in terms of the accuracy and precision criteria, show the satisfactory performance of the proposed estimators under both step changes and drift. Moreover, a numerical example is given to illustrate the application of the proposed estimators.

show abstract

GLM profile monitoring using robust estimators

Moheghi

Noorossana

Ahmadi

2020

Quality & Reliability Eng

View full text Add to dashboard Cite

It is well known that performance of control scheme in phase II of statistical process control depends on the estimators utilized in phase I. Sometimes, outliers may be present in the data, which could seriously impact the performance of the estimators. In some practical situations, generalized linear models (GLMs) are used to model a wide class of response variables. This study deals with the robust estimation and monitoring of parameters in GLM profiles in the presence of outliers. In this study, robust estimators are used to estimate the parameters of logistic and Poisson profiles. The results are compared with the maximum likelihood estimators (MLEs). In a numerical example, the profile parameters are estimated by the MLE and robust estimators and the resulting test statistics are monitored by a control scheme. The phase II control charts are determined based on these two types of estimators and compared for different out‐of‐control conditions. The simulation results confirm that robust estimators in most cases lead to better estimates in comparison with the MLE estimator in terms of average run length criterion.

show abstract

Statistical Monitoring of Nominal Logistic Profiles in Phase II

Cited by 12 publications

References 31 publications

Phase II Monitoring of Generalized Linear Profiles Under Different Types of Changes

Phase II Monitoring of Generalized Linear Profiles Under Different Types of Changes

Identifying the time of step change and drift in Phase II monitoring of autocorrelated logistic regression profiles

GLM profile monitoring using robust estimators

Contact Info

Product

Resources

About