Quality control charts based on ranked set sampling under various symmetric distributions


Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Fen Edebiyat Fakültesi, İstatistik Bölümü, Türkiye

Tezin Onay Tarihi: 2013

Öğrenci: DİDEM EGEMEN

Danışman: BARIŞ SÜRÜCÜ

Özet:

Quality of a product is a very important property for producers and service providers, and can be maintained by statistical quality control methods. One of these methods is Shewhart control chart, which is the most frequently used in the literature. Construction of accurate control limits is the main issue in this method and it strictly depends on the efficiency of the estimators used to construct control limits. In this thesis, a new sampling method ranked set sampling (RSS), which is more efficient than simple random sampling (SRS), is proposed in the estimation part of Shewhart control charts. With this aim, quality control charts constructed by using SRS and RSS are compared under three different symmetric distributions which are normal, long-tailed symmetric and short-tailed symmetric. The simulation results show that RSS provides more efficient estimators compared to SRS. Moreover, it is demonstrated by simulations that type I errors of the charts obtained by RSS technique are very close to the predefined error level. To give a better illustration of the methods, a real life example is provided at the end of the study.