Type-I censored data monitoring using different conditional statistics

Monitoring censored data is a challenging task and for this purpose, many control charts have been proposed in the literature using different methodologies. In particular, conditional expected value (CEV) and conditional median (CM) are commonly used to replace the censored observations for efficient monitoring. These central tendency measures do not take into account the variation of the data. Thus, the main aim of the article is to propose control charts for type-I censored data monitoring using conditional standard deviation (CSD) and compare it with the existing censored data charts. To this end, exponentially weighted moving average (EWMA) and double EWMA (DEWMA) charts are proposed and studied assuming CSD, CEV, and CM statistics for Weibull data. Different size of shifts as well as smoothing parameters are considered to evaluate the effectiveness of the CSD based charts compared to the existing charts. The performance of the charts is assessed using average run length and standard deviation of run length. Based on simulations as well as two real data examples, the results indicated that the new measure CSD perform better than the CEV and CM statistics.

Automated summary

This article introduces control charts for monitoring censored data using conditional standard deviation (CSD) and compares it with existing censored data charts. The charts are assessed based on average run length and standard deviation of run length, showing that the CSD measure outperforms CEV and CM statistics.