Sec. 26.13.05.06-3. Statistical Methods for Evaluating Ground Water Monitoring Data

A. General.

(1) The owner or operator shall specify, subject to §B of this regulation, a statistical method to be used in evaluating ground water monitoring data for each hazardous constituent identified in accordance with Regulation .06-1B of this chapter.

(2) Once a choice of statistical method is approved by the Secretary, the owner or operator shall use the statistical method as a condition of the owner's or operator's CHS facility permit.

(3) The owner or operator shall conduct the chosen statistical test separately for each hazardous constituent identified in accordance with Regulation .06-1B of this chapter in each well.

(4) If a practical quantification limit (pql) is to be used in a statistical method specified under this section to comply with the performance standards of §C(9) of this regulation, the owner or operator shall propose the pql to the Secretary for approval.

(5) The owner or operator shall ensure that a statistical method specified under this section:

(a) Is protective of human health and the environment; and

(b) Complies with the performance standards outlined in §C of this regulation.

B. Statistical Methods. In satisfying the requirement of §A(1) of this regulation, the owner or operator shall specify one of the following statistical methods:

(1) A parametric analysis of variance (ANOVA) followed by multiple comparisons procedures to identify statistically significant evidence of contamination, if the method includes estimation and testing of the contrasts between each compliance well's mean and the background mean levels for each constituent;

(2) An analysis of variance (ANOVA) based on ranks followed by multiple comparisons procedures to identify statistically significant evidence of contamination, if the method includes estimation and testing of the contrasts between each compliance well's median and the background median levels for each constituent;

(3) A tolerance or prediction interval procedure in which an interval for each constituent is established from the distribution of the background data, and the level of each constituent in each compliance well is compared to the upper tolerance or prediction limit;

(4) A control chart approach that gives control limits for each constituent; or

(5) Another statistical test method submitted by the owner or operator and approved by the Secretary.

C. Performance Standards.

(1) The owner or operator shall comply with the following requirements for any statistical method chosen under §§A and B of this regulation for specification in the facility permit.

(2) The owner or operator shall ensure that the statistical method used to evaluate ground water monitoring data is appropriate for the distribution of the chemical parameters or hazardous constituents.

(3) If the distribution of a chemical parameter or hazardous constituent for which data are collected under the ground water monitoring program is inappropriate for a normal theory test, then the owner or operator shall transform the data into an appropriate form or use a distribution-free theory test.

(4) If the statistical distributions for the constituents for which data are collected differ, the owner or operator may use more than one statistical method.

(5) In tests other than those using tolerance intervals, prediction intervals, or control charts, in comparing an individual compliance well constituent concentration with background constituent concentrations or a ground water protection standard, the owner or operator shall ensure that:

(a) If an individual well comparison is used, the Type I error level is not less than 0.01 for each testing period; and

(b) If a multiple comparisons procedure is used, the Type I overall experimental error rate for each testing period is not less than 0.05, and the Type I error of not less than 0.01 for individual well comparisons is maintained.

(6) If a control chart approach is used to evaluate ground water monitoring data, the owner or operator shall propose the specific type of control chart and its associated parameter values for approval by the Secretary, contingent upon the approach being protective of human health and the environment.

(7) Tolerance Intervals.

(a) If a tolerance interval or a prediction interval is used by the owner or operator to evaluate ground water monitoring data, the owner or operator shall propose the following for approval by the Secretary, contingent on values for these parameters being protective of human health and the environment:

(i) Levels of confidence; and

(ii) For tolerance intervals, the percentage of the population that the interval is to contain.

(b) The Secretary shall consider the following in reviewing the parameters proposed under §C(7)(a) of this regulation:

(i) The number of samples in the background data base;

(ii) The data distribution for each constituent of concern; and

(iii) The range of the concentration values for each constituent of concern.

(8) The owner or operator shall ensure that the statistical method accounts for data below the limit of detection with one or more statistical procedures.

(9) In proposing a practical quantification limit (pql) for use in a statistical procedure to account for data below the limit of detection, the owner or operator shall select the lowest concentration level that can be reliably achieved within specified limits of precision and accuracy during routine laboratory operating conditions that are available to the facility.

(10) The owner or operator shall ensure that the statistical method includes procedures to control or correct for seasonal and spatial variability as well as temporal correlation in the data, as required.