Process selection is the problem of comparing two processes and selecting the one that has a higher capability value. In this paper, we consider the process selection problem by using the yield index S pk to compare two production processes and select one that has higher production yield. An analytical exact approach is proposed to solve this problem. Testing hypotheses with two phases for comparing two processes are developed. Critical values of the test are obtained to determine the selection decisions. Sample sizes required for designated selection power and confidence level are also investigated. The results provide useful information to practitioners. An application example on comparing two thin-film transistor (TFT) type liquid-crystal display (LCD) production processes is presented to illustrate the practicality of the proposed approach to a real problem in the factory.

Evaluating and selecting suppliers are essential tasks in managing supply chains. Quality is one of the most important factors for supplier selection among various criteria. To compare the quality of k (k ≥ 2) suppliers, this paper proposes a multiple comparisons with the best method based on the yield index, Spk. Other than the existing work that provides a subset containing the best supplier, the proposed method further gives the upper and lower bounds for each difference in Spk from the unknown best supplier at a confidence level of at least 1‐α. The supplier having a zero lower bound is identified as the best supplier with the highest yield, whereas having a positive lower bound is inferior with a lower yield. The power analysis shows that proposed method would be more and more powerful than the existing work when k gets large. The required sample sizes for certain power levels are provided. An application to comparing three suppliers of the IC drivers of the light‐emitting diode module is presented to show the effectiveness of the proposed method to a real‐world problem. Copyright © 2013 John Wiley & Sons, Ltd.

No abstract

No abstract

Early detection of lung cancer has a higher likelihood of curative treatment and thus improves survival rate. Low-dose computed tomography (LDCT) screening has been shown to be effective for high-risk individuals in several clinical trials, but has high false positive rates. To evaluate the risk of stage I lung cancer in the general population not limited to smokers, a retrospective study of 133 subjects was conducted in a medical center in Taiwan. Regularized regression was used to build the risk prediction model by using LDCT and health examinations. The proposed model selected seven variables related to nodule morphology, counts and location, and ten variables related to blood tests and medical history, achieving an area under the curve (AUC) value of 0.93. The higher the age, white blood cell count (WBC), blood urea nitrogen (BUN), diabetes, gout, chronic obstructive pulmonary disease (COPD), other cancers, and the presence of spiculation, ground-glass opacity (GGO), and part solid nodules, the higher the risk of lung cancer. Subjects with calcification, solid nodules, nodules in the middle lobes, more nodules, and diseases related to thyroid, liver, and digestive systems were at a lower risk. The selected variables did not indicate causation.