SU0003940 SSCRPT - Laserfiche WebLink

Home Browse Search

transformed normal distribution. If greater than 15 percent but less than 50 percent of the background data set consist of non-detect values, the mean and standard deviation of the data set are adjusted using the Cohen's Method. The tolerance limit is then calculated using the adjusted values. Nonparametric Tolerance Limit When the background data set contains greater than 50 percent but less than 100.percent nondetect values and/or its distribution is not normal (or transformed normal), Sanitas applies the nonparametric tolerance limit method. However, this method requires a large number of samples to achieve a false positive rate of 1 percent or less, which is required by CCR Title 23, Chapter 15,Article 5 guidelines. Thus, when the alpha level was higher than 1 percent, the concentration limit was not established and footnoted as to why. Nonstatistical Approach When the background data set contains 100 percent nondetect values, Sanitas applies the nonstatistical approach. This approach takes into consideration that if historically a constituent has not been detected, any detection of that constituent would be considered an exceedence. Thus, in these situations (100 percent nondetected values), the tolerance limit is set at "detect", meaning that if a value is detected above its method detection limit, this value is an exceedence of the concentration limit. Intrawell Rank Sum When Intrawell Tolerance Limit analysis is unable to normalize the data and thus a nonparametric analysis is performed, the false positive rate becomes greater than five percent. When this happens a Intrawell Rank Sum analysis is performed. This is a nonparametric procedure where the sums of ranked data sets are compared. Subsequent sample data are compared with sampling data from the initial monitoring period of the same well. It is assumed that during the initial monitoring period the well has shown no evidence of contamination nor an increasing trend. This test procedure is used to evaluate whether the historical (background data) and the compliance data have the same median constituent concentration. TREND ANALYSIS Sen's Slope measures the change in constituent concentrations per unit time. Sen's method is not greatly affected by outliers, and the slope can be computed when data are missing. Sen's estimator is closely related to the Mann-Kendall test, which is a nonparametric rank correlation test for trend. The test uses only the relative magnitudes of the data rather than their actual values; therefore,missing values are allowed, and constituents that are reported as less than the detection limit can be used by assigning them values equal to half the detection limit. Sen's Slope and the Mann-Kendall tests are described in "Statistical Methods for Environmental Pollution Monitoring," Richard O. Gilbert, Van Nostrand Reinhold,New York, 1987. Mann-Kendall test is recommended in"An Evaluation of Trend