Answers are grounded in this paper and cite their sources.
To assess how well a process performs in accordance with standards, process capability indices (PCIs) are widely used. Although higher PCIs suggest a greater level of process quality, this does not necessarily equate to lower rejection rates. Therefore, using a loss-based PCI to gauge process capability is more appropriate. In this context, we consider the PCI [Formula: see text], which is estimated using the maximum likelihood method, a novel capability index based on the symmetric loss function that can be applied to normally distributed processes. This article has three goals: (i) To examine the effectiveness of three parametric bootstrap confidence intervals (BCIs) for [Formula: see text]. (ii) To assess the power of the bootstrap procedures by utilizing the relationship between confidence interval construction and hypothesis testing. (iii) To present receiver operating characteristic (ROC) curves for the three BCIs to evaluate their performance. Through Monte Carlo simulations, the effectiveness of the BCIs is contrasted in terms of average width and coverage probability.
No takes yet. Share an insight, caveat, or question.
Dey et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: