Diagnosis:
Statistics: Coefficient of variation precision
• Precision, otherwise known as the reproducibility of a test, is expressed by using the coefficient of variation (CV).
• Determining the precision is accomplished by repeating the test approximately 20 times using the same sample and determining the range of variation.
• CV (%) = 100 × [standard deviation (SD)/mean]
• The SD is a measure of dispersion from the mean in a Gaussian normal distribution.
• The CV of a test can vary over the assay’s analytical range and therefore should be determined at low, mid, and high range values.
• The “within-run” or “intra-assay” CV is determined by repeating the test using the same sample on 1 day, typically during one run. The “between-run” or “interassay” CV is determined by comparing the results obtained with the same assay on different days using the same sample. Typically, the within-run CV is smaller than the between-run CV.