Kristian Linnet1. 1. Department of Forensic Chemistry, University of Copenhagen, Copenhagen, Denmark. linnet@post7.tele.dk
Abstract
BACKGROUND: The exponentially moving average (EWMA) rule for internal quality control is a well-known type of control rule in industry. Here, the power of the EWMA rule is evaluated to outline the potential of this type of control rule in clinical chemistry. METHODS: Using simulations, the power of the EWMA rule was explicitly compared with that of commonly used rules in clinical chemistry. The type I error levels were standardized to common values to achieve unbiased comparisons. RESULTS: For small to moderately large errors (systematic errors up to 2-3 standard deviations), the EWMA rule outperforms simple rules (N=1) and multi-rules (N=2-6). For example, for a systematic error of 2s, the EWMA rule equivalent to the 1(3s) rule has a power of 0.30, whereas the 1(3s) rule only displays a power of approximately 0.15. For N=4, comparison was carried out with the 1(3s)/2(2s)/R(4s)/4(1s) rule. Here the common type I error level is 0.017. At all error levels, the EWMA rule is superior to the multi-rule. For example, given a 1s systematic error, the EWMA rule has a power (0.4) of twice the value of the multi-rule (0.2). CONCLUSION: The EWMA rule is an efficient control rule with regard to systematic errors that should be considered for general application in the field of clinical chemistry.
BACKGROUND: The exponentially moving average (EWMA) rule for internal quality control is a well-known type of control rule in industry. Here, the power of the EWMA rule is evaluated to outline the potential of this type of control rule in clinical chemistry. METHODS: Using simulations, the power of the EWMA rule was explicitly compared with that of commonly used rules in clinical chemistry. The type I error levels were standardized to common values to achieve unbiased comparisons. RESULTS: For small to moderately large errors (systematic errors up to 2-3 standard deviations), the EWMA rule outperforms simple rules (N=1) and multi-rules (N=2-6). For example, for a systematic error of 2s, the EWMA rule equivalent to the 1(3s) rule has a power of 0.30, whereas the 1(3s) rule only displays a power of approximately 0.15. For N=4, comparison was carried out with the 1(3s)/2(2s)/R(4s)/4(1s) rule. Here the common type I error level is 0.017. At all error levels, the EWMA rule is superior to the multi-rule. For example, given a 1s systematic error, the EWMA rule has a power (0.4) of twice the value of the multi-rule (0.2). CONCLUSION: The EWMA rule is an efficient control rule with regard to systematic errors that should be considered for general application in the field of clinical chemistry.
Authors: Troy E Barger; Lei Zhou; Michael Hale; Michael Moxness; Steven J Swanson; Narendra Chirmule Journal: AAPS J Date: 2009-12-10 Impact factor: 4.009