|
On the sensitivity of robust control chartsin monitoring contaminated data |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Kooi Huat Ng 2. Poh Kheng Soon 3. Jeng Young Liew 4. Kok Haur Ng |
| Title | On the sensitivity of robust control chartsin monitoring contaminated data |
| Publisher | Research and Development Office, Prince of Songkla University |
| Publication Year | 2564 |
| Journal Title | Songklanakarin Journal of Science an Technology (SJST) |
| Journal Vol. | 43 |
| Journal No. | 6 |
| Page no. | 1610-1619 |
| Keyword | Shewhart chart, robust, outlier, contamination, standard deviation |
| URL Website | https://rdo.psu.ac.th/sjst/index.php |
| ISSN | 0125-3395 |
| Abstract | Shewhart chart is typically formed under normality assumptions. In reality, much data is contaminated with occasionaloutliers, which may diminish the Shewhart chartโs sensitivity. Hence, robust charts are introduced as outlier-resistant and robustagainst non-normality. This paper intends to study the robust monitoring of contaminated data using (i) median chart based onmedian absolute deviation (MAD), and (ii) trimmed mean chart based on winsorized standard deviation. These charts arecompared with the conventional Shewhart mean( ) Xcharts based on standard deviation and range. In general, through extensivesimulations, the robust charts are quite comparable with theXcharts for normal data of small sample size (n), but for large n,the median chart based on MAD is marginally preferred by all the benchmarks considered. However, when a process iscontaminated, both robust charts outshine theXcharts substantially in a series of investigations. |
