In many fields, there is the need to monitor quality characteristics defined as the ratio of two random variables. The design and implementation of control charts directly monitoring the ratio stability is required for the continuous surveillance of these quality characteristics. In this paper, we propose two one-sided EWMA charts with subgroups having sample size n > 1 to monitor the ratio of two normal random variables. The optimal EWMA smoothing constants, control limits and ARLs have been computed for different values of the in-control ratio and correlation between the variables and are shown in several figures and tables to discuss the statistical performance of the proposed one-sided EWMA charts. Both deterministic and random shift sizes have been considered to test the two one-sided EWMA charts’ sensitivity. The obtained results show that the proposed one-sided EWMA control charts are more sensitive to process shifts than other charts already proposed in the literature. The practical application of the proposed control schemes is illustrated with an illustrative example.

Monitoring the Ratio of two Normal Variables using EWMA Type Control Charts

CELANO, GIOVANNI
2016-01-01

Abstract

In many fields, there is the need to monitor quality characteristics defined as the ratio of two random variables. The design and implementation of control charts directly monitoring the ratio stability is required for the continuous surveillance of these quality characteristics. In this paper, we propose two one-sided EWMA charts with subgroups having sample size n > 1 to monitor the ratio of two normal random variables. The optimal EWMA smoothing constants, control limits and ARLs have been computed for different values of the in-control ratio and correlation between the variables and are shown in several figures and tables to discuss the statistical performance of the proposed one-sided EWMA charts. Both deterministic and random shift sizes have been considered to test the two one-sided EWMA charts’ sensitivity. The obtained results show that the proposed one-sided EWMA control charts are more sensitive to process shifts than other charts already proposed in the literature. The practical application of the proposed control schemes is illustrated with an illustrative example.
Ratio distribution; Markov chain; EWMA
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/17248
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 31
  • ???jsp.display-item.citation.isi??? 30
social impact