Current through September 18, 2024
Authority: IC 13-14-8-7; IC 13-15; IC 13-19-3
Affected: IC 13-20; IC 36-9-30
Sec. 6.
(a) The
owner, operator, or permittee shall determine if there is a statistically
significant increase for each constituent analyzed, except for constituents
listed in section 15(b) of this rule (Table 1B). This statistical evaluation is
required each time ground water is collected and analyzed at the monitoring
boundary for all MSWLFs.
(b) To
determine a statistically significant increase compared to the background
ground water quality, each constituent from each ground water monitoring well
sample must be compared to the background ground water quality of that
constituent, according to the statistical procedures and performance standards
specified in this section.
(c) The
owner, operator, or permittee shall submit to the commissioner for approval a
written statistical evaluation plan for each ground water monitoring program
required under this rule. Submittal of the plan must comply with the following:
(1) For all new MSWLFs and lateral expansions
to be permitted under this article, the statistical evaluation plan shall be
developed in accordance with the general description submitted under
329 IAC
10-15-1(a)(12).
(2) For existing MSWLFs, the plan must be
submitted with the next renewal application, at the time of closure, or as
specified by the commissioner, whichever occurs first, unless a statistical
evaluation plan that includes all applicable requirements under this section
has been previously submitted.
(3)
The plan must explain which of the various statistical methods, described in
subsection (f), may be needed to address a continuously expanding ground water
data base. All statistical methods must meet the performance standards outlined
in subsection (g).
(4) The plan
must identify the statistical procedures to be used whenever verification
resampling, as specified under section 8 of this rule, is
implemented.
(5) The plan must
identify any computer data management or statistical evaluation program used by
the owner, operator, or permittee and, upon request by the commissioner,
include appropriate documentation of the computer program.
(d) Changes to the statistical evaluation
plan must not be implemented without approval from the commissioner.
(e) The owner, operator, or permittee shall
submit a statistical evaluation report of the ground water sample analysis to
the commissioner. The report must be submitted within sixty (60) days after
obtaining ground water samples from the ground water monitoring wells, unless a
verification resampling program described under section 8 of this rule, is
implemented. The statistical evaluation report must include the following:
(1) All input data, output data, and
equations used for all calculations and statistical tests utilized.
(2) A detailed discussion of the conclusions
from the statistical evaluation. This discussion must include the
identification of all constituents found to have a statistically significant
increase.
(3) A graphical
representation of the MSWLF's ground water data when requested by the
commissioner. The commissioner shall specify the format of the graphical
representation.
(f) Any
of the following statistical procedures may be chosen for the statistical
evaluation, provided the chosen statistical procedure is capable of meeting the
performance standards in subsection (g):
(1) A
parametric analysis of variance (ANOVA) followed by multiple comparison
procedures to identify a statistically significant increase. The method must
include estimation and testing of the contrasts between each downgradient
ground water monitoring 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. The method must
include estimation and testing of the contrasts between each downgradient
ground water monitoring well's median and the background ground water quality
median levels for each constituent.
(3) A tolerance or prediction interval in
which an interval for each constituent is established from the distribution of
the background ground water quality data, and the level of each constituent in
each downgradient ground water monitoring well for the most recent sampling
event is compared to the upper tolerance limit or upper prediction
limit.
(4) A control chart, which
establishes control limits for each constituent.
(5) A temporal or spatial trend
analysis.
(6) Another valid
statistical test method that meets the performance standards of subsection
(g).
(g) The statistical
procedures and methods used must comply with the following performance
standards:
(1) The statistical procedure used
to evaluate ground water monitoring data must be appropriate for the data
distribution of each constituent. If the data distribution of a constituent is
shown to be inappropriate for a normal theory test, then either the data must
be transformed or a distribution-free statistical test must be used. If data
distributions for the constituents differ, more than one (1) statistical method
may be needed.
(2) If ground water
data from an individual ground water monitoring well is compared either to
background ground water quality, which may include pooled background monitoring
well data from more than one (1) well, or to a ground water protection
standard, then the test must be done at a Type I error level that is no less
than one-hundredth (0.01) for each testing period. If a multiple comparisons
procedure is used, the Type I experiment wise error rate for each testing
period must be no less than five-hundredths (0.05); however, the Type I error
rate of no less than one-hundredth (0.01) for individual monitoring well
comparisons must be maintained. This performance standard does not apply to:
(A) tolerance intervals;
(B) prediction intervals; and
(C) control charts.
(3) The validity of the statistical test
method used must be evaluated prior to applying the method to the ground water
data. This evaluation must address:
(A) the
error potential for false positives and false negatives; and
(B) any other evaluation deemed necessary by
the commissioner to confirm that the test method chosen will sufficiently
detect contamination.
(4) If a control chart is used to evaluate
ground water monitoring data, the specific type of control chart and associated
statistical parameter values must be protective of human health and the
environment. These values must be determined after considering:
(A) the number of background
samples;
(B) the background data
distribution; and
(C) the range of
background concentrations for each constituent analyzed.
(5) If a tolerance interval or a prediction
interval is used to evaluate ground water monitoring data, the levels of
confidence and, for tolerance intervals, the percentage of the population that
the interval must contain, must be protective of human health and the
environment. These statistical parameters must be determined after considering:
(A) the number of background
samples;
(B) the background data
distribution; and
(C) the range of
background concentrations for each constituent analyzed.
(6) The statistical method must account for
data below the limit of detection with one (1) or more statistical procedures.
Any practical quantitation limit that is used in a statistical procedure must:
(A) be the lowest concentration limit that
can be repeatedly and reliably achieved; and
(B) be within specified limits of precision
and accuracy during routine laboratory operating conditions.
(7) If necessary, the statistical
method must include procedures to control or correct for seasonal and spatial
variability.
