Standard Guide for Developing Appropriate Statistical Approaches for Groundwater Detection Monitoring Programs

SIGNIFICANCE AND USE
The principal use of this guide is in groundwater detection monitoring of hazardous and municipal solid waste disposal facilities. There is considerable variability in the way in which existing Guide USEPA regulation and guidance are interpreted and practiced. Often, much of current practice leads to statistical decision rules that lead to excessive false positive or false negative rates, or both. The significance of this proposed guide is that it jointly minimizes false positive and false negative rates at nominal levels without sacrificing one error for another (while maintaining acceptable statistical power to detect actual impacts to groundwater quality (4)).
Using this guide, an owner/operator or regulatory agency should be able to develop a statistical detection monitoring program that will not falsely detect contamination when it is absent and will not fail to detect contamination when it is present.
SCOPE
1.1 This guide covers the context of groundwater monitoring at waste disposal facilities. Regulations have required statistical methods as the basis for investigating potential environmental impact due to waste disposal facility operation. Owner/operators must perform a statistical analysis on a quarterly or semiannual basis. A statistical test is performed on each of many constituents (for example, 10 to 50 or more) for each of many wells (5 to 100 or more). The result is potentially hundreds, and in some cases, a thousand or more statistical comparisons performed on each monitoring event. Even if the false positive rate for a single test is small (for example, 1 %), the possibility of failing at least one test on any monitoring event is virtually guaranteed. This assumes you have done the correct statistic in the first place.
1.2 This guide is intended to assist regulators and industry in developing statistically powerful groundwater monitoring programs for waste disposal facilities. The purpose of this guide is to detect a potential groundwater impact from the facility at the earliest possible time while simultaneously minimizing the probability of falsely concluding that the facility has impacted groundwater when it has not.
1.3 When applied inappropriately, existing regulation and guidance on statistical approaches to groundwater monitoring often suffer from a lack of statistical clarity and often implement methods that will either fail to detect contamination when it is present (a false negative result) or conclude that the facility has impacted groundwater when it has not (a false positive). Historical approaches to this problem have often sacrificed one type of error to maintain control over the other. For example, some regulatory approaches err on the side of conservatism, keeping false negative rates near zero while false positive rates approach 100 %.
1.4 The purpose of this guide is to illustrate a statistical groundwater monitoring strategy that minimizes both false negative and false positive rates without sacrificing one for the other.
1.5 This guide is applicable to statistical aspects of groundwater detection monitoring for hazardous and municipal solid waste disposal facilities.
1.6 It is of critical importance to realize that on the basis of a statistical analysis alone, it can never be concluded that a waste disposal facility has impacted groundwater. A statistically significant exceedance over background levels indicates that the new measurement in a particular monitoring well for a particular constituent is inconsistent with chance expectations based on the available sample of background measurements.
1.7 Similarly, statistical methods can never overcome limitations of a groundwater monitoring network that might arise due to poor site characterization, well installation and location, sampling, or analysis.
1.8 It is noted that when justified, intra-well comparisons are generally preferable to their inter-well counterparts because they completely...

General Information

Status
Historical
Publication Date
31-Dec-2004
Current Stage
Ref Project

Relations

Buy Standard

Guide
ASTM D6312-98(2005) - Standard Guide for Developing Appropriate Statistical Approaches for Groundwater Detection Monitoring Programs
English language
14 pages
sale 15% off
Preview
sale 15% off
Preview

Standards Content (Sample)


NOTICE: This standard has either been superseded and replaced by a new version or withdrawn.
Contact ASTM International (www.astm.org) for the latest information
Designation: D6312 − 98(Reapproved 2005)
Standard Guide for
Developing Appropriate Statistical Approaches for
Groundwater Detection Monitoring Programs
This standard is issued under the fixed designation D6312; the number immediately following the designation indicates the year of
original adoption or, in the case of revision, the year of last revision.Anumber in parentheses indicates the year of last reapproval.A
superscript epsilon (´) indicates an editorial change since the last revision or reapproval.
1. Scope 1.4 The purpose of this guide is to illustrate a statistical
groundwater monitoring strategy that minimizes both false
1.1 This guide covers the context of groundwater monitor-
negative and false positive rates without sacrificing one for the
ing at waste disposal facilities. Regulations have required
other.
statistical methods as the basis for investigating potential
1.5 This guide is applicable to statistical aspects of ground-
environmental impact due to waste disposal facility operation.
water detection monitoring for hazardous and municipal solid
Owner/operators must perform a statistical analysis on a
waste disposal facilities.
quarterlyorsemiannual basis.Astatistical test is performedon
each of many constituents (for example, 10 to 50 or more) for
1.6 It is of critical importance to realize that on the basis of
eachofmanywells(5to100ormore).Theresultispotentially
a statistical analysis alone, it can never be concluded that a
hundreds, and in some cases, a thousand or more statistical
waste disposal facility has impacted groundwater. A statisti-
comparisons performed on each monitoring event. Even if the cally significant exceedance over background levels indicates
false positive rate for a single test is small (for example, 1%), that the new measurement in a particular monitoring well for a
the possibility of failing at least one test on any monitoring particular constituent is inconsistent with chance expectations
event is virtually guaranteed. This assumes you have done the based on the available sample of background measurements.
correct statistic in the first place.
1.7 Similarly, statistical methods can never overcome limi-
tations of a groundwater monitoring network that might arise
1.2 This guide is intended to assist regulators and industry
duetopoorsitecharacterization,wellinstallationandlocation,
in developing statistically powerful groundwater monitoring
sampling, or analysis.
programs for waste disposal facilities. The purpose of this
guide is to detect a potential groundwater impact from the
1.8 It is noted that when justified, intra-well comparisons
facility at the earliest possible time while simultaneously
aregenerallypreferabletotheirinter-wellcounterpartsbecause
minimizing the probability of falsely concluding that the
they completely eliminate the spatial component of variability.
facility has impacted groundwater when it has not.
Due to the absence of spatial variability, the uncertainty in
measured concentrations is decreased, making intra-well com-
1.3 When applied inappropriately, existing regulation and
parisonsmoresensitivetorealreleases(thatis,falsenegatives)
guidance on statistical approaches to groundwater monitoring
and false positive results due to spatial variability are com-
often suffer from a lack of statistical clarity and often imple-
pletely eliminated.
mentmethodsthatwilleitherfailtodetectcontaminationwhen
1.9 Finally, it should be noted that the statistical methods
itispresent(afalsenegativeresult)orconcludethatthefacility
described here are not the only valid methods for analysis of
has impacted groundwater when it has not (a false positive).
groundwatermonitoringdata.Theyare,however,currentlythe
Historicalapproachestothisproblemhaveoftensacrificedone
most useful from the perspective of balancing site-wide false
type of error to maintain control over the other. For example,
positive and false negative rates at nominal levels. A more
some regulatory approaches err on the side of conservatism,
complete review of this topic and the associated literature is
keepingfalsenegativeratesnearzerowhilefalsepositiverates
presented by Gibbons (1).
approach 100%.
1.10 The values stated in both inch-pound and SI units are
toberegardedasthestandard.Thevaluesgiveninparentheses
are for information only.
ThisguideisunderthejurisdictionofASTMCommitteeD18onSoilandRock
and is the direct responsibility of Subcommittee D18.21 on Groundwater and
Vadose Zone Investigations.
Current edition approved Jan. 1, 2005. Published February 2005. Originally
approved in 1998. Last previous edition approved in 1998 as D6312–98. DOI: The boldface numbers given in parentheses refer to a list of references at the
10.1520/D6312-98R05. end of the text.
Copyright © ASTM International, 100 Barr Harbor Drive, PO Box C700, West Conshohocken, PA 19428-2959. United States
D6312 − 98 (2005)
1.11 This standard does not purport to address all of the 2.2.2 falsepositiverate,n—indetectionmonitoring,therate
safety concerns, if any, associated with its use. It is the at which the statistical procedure indicates possible contami-
responsibility of the user of this standard to establish appro- nation when none is present.
priate safety and health practices and determine the applica-
2.2.3 nonparametric, adj—a term referring to a statistical
bility of regulatory limitations prior to use.
technique in which the distribution of the constituent in the
1.12 This guide offers an organized collection of informa-
population is unknown and is not restricted to be of a specified
tion or a series of options and does not recommend a specific
form.
course of action. This document cannot replace education or
2.2.4 nonparametric prediction limit, n—the largest (or
experienceandshouldbeusedinconjunctionwithprofessional
second largest) of n background samples.The confidence level
judgment.Notallaspectsofthisguidemaybeapplicableinall
associatedwiththenonparametricpredictionlimitisafunction
circumstances. This ASTM standard is not intended to repre-
of n and k .
sent or replace the standard of care by which the adequacy of
a given professional service must be judged, nor should this
2.2.5 parametric, adj—a term referring to a statistical tech-
documentbeappliedwithoutconsiderationofaproject’smany nique in which the distribution of the constituent in the
unique aspects. The word “Standard” in the title of this
population is assumed to be known.
document means only that the document has been approved
2.2.6 verification resample, n—in the event of an initial
through the ASTM consensus process.
statistical exceedance, one (or more) new independent sample
is collected and analyzed for that well and constituent which
2. Terminology
exceeded the original limit.
2.1 Definitions:
2.3 Symbols:
2.1.1 assessment monitoring program, n—groundwater
2.3.1 α—the false positive rate for an individual compari-
monitoring that is intended to determine the nature and extent
son (that is, one well and constituent).
of a potential site impact following a verified statistically
2.3.2 α*—thesite-widefalsepositiveratecoveringallwells
significant exceedance of the detection monitoring program.
and constituents.
2.1.2 combined Shewhart (CUSUM) control chart, n—a
2.3.3 k—the number of future comparisons for a single
statisticalmethodforintra-wellcomparisonsthatissensitiveto
monitoring event (for example, the number of downgradient
both immediate and gradual releases.
monitoring wells multiplied by the number of constituents to
be monitored) for which statistics are to be computed.
2.1.3 detection limit (DL), n—the true concentration at
which there is a specified level of confidence (for example,
2.3.4 n—the number of background measurements.
99% confidence) that the analyte is present in the sample (2).
2.3.5 σ —the true population variance of a constituent.
2.1.4 detection monitoring program, n—groundwater moni-
2.3.6 s—the sample-based standard deviation of a constitu-
toring that is intended to detect a potential impact from a
ent computed from n background measurements.
facility by testing for statistically significant changes in geo-
2.3.7 s —the sample-based variance of a constituent com-
chemistry in a downgradient monitoring well relative to
puted from n background measurements.
background levels.
2.1.5 intra-well comparisons, n—a comparison of one or 2.3.8 µ—the true population mean of a constituent.
more new monitoring measurements to statistics computed
2.3.9 x¯—thesample-basedmeanoraverageconcentrationof
fromasampleofhistoricalmeasurementsfromthatsamewell.
a constituent computed from n background measurements.
2.1.6 inter-well comparisons, n—a comparison of a new
3. Summary of Guide
monitoring measurement to statistics computed from a sample
of background measurements (for example, upgradient versus
3.1 This guide is summarized in Fig. 1, which provides a
downgradient comparisons).
flowchart illustrating the steps in developing a statistical
monitoring plan. The monitoring plan is based either on
2.1.7 prediction interval or limit, n—astatisticalestimateof
background versus monitoring well comparisons (for example,
the minimum or maximum concentration, or both, that will
upgradient versus downgradient comparisons or intra-well
containthenextseriesofkmeasurementswithaspecifiedlevel
comparisons, or a combination of both). Fig. 1 illustrates the
of confidence (for example, 99% confidence) based on a
various decision points at which the general comparative
sample of n background measurements.
strategy is selected (that is, upgradient background versus
2.1.8 quantification limit (QL), n—the concentration at
intra-well background) and how the statistical methods are to
which quantitative determinations of an analyte’s concentra-
beselectedbasedonsite-specificconsiderations.Thestatistical
tion in the sample can be reliably made during routine
methods include parametric and nonparametric prediction
laboratory operating conditions (3).
limitsforbackgroundversusmonitoringwellcomparisonsand
2.2 Definitions of Terms Specific to This Standard:
combined Shewhart-CUSUM control charts for intra-well
2.2.1 false negative rate, n—in detection monitoring, the comparisons. Note that the background database is intended to
rateatwhichthestatisticalproceduredoesnotindicatepossible expand as new data become available during the course of
contamination when contamination is present. monitoring.
D6312 − 98 (2005)
FIG. 1 Development of a Statistical Detection Monitoring Plan
D6312 − 98 (2005)
FIG. 1 (continued)
D6312 − 98 (2005)
FIG. 1 (continued)
D6312 − 98 (2005)
FIG. 1 (continued)
D6312 − 98 (2005)
FIG. 1 (continued)
D6312 − 98 (2005)
4. Significance and Use 5.1.1.11 If less than 13 samples are available, more back-
ground data must be collected to use the nonparametric
4.1 The principal use of this guide is in groundwater
prediction limit.
detection monitoring of hazardous and municipal solid waste
5.1.1.12 AnalternativewouldbetouseaPoissonprediction
disposal facilities. There is considerable variability in the way
limit that can be computed from four or more background
in which existing Guide USEPA regulation and guidance are
measurements regardless of the detection frequency and can
interpretedandpracticed.Often,muchofcurrentpracticeleads
adjust for multiple wells and constituents.
to statistical decision rules that lead to excessive false positive
5.1.1.13 If downgradient wells fail, determine cause.
or false negative rates, or both. The significance of this
5.1.1.14 Ifthedowngradientwellsfailbecauseofnaturalor
proposed guide is that it jointly minimizes false positive and
off-site causes, select constituents for intra-well comparisons
false negative rates at nominal levels without sacrificing one
(9).
error for another (while maintaining acceptable statistical
5.1.1.15 If site impacts are found, a site plan for assessment
power to detect actual impacts to groundwater quality (4)).
monitoring may be necessary (10).
4.2 Using this guide, an owner/operator or regulatory
5.1.2 Intra-well Comparisons:
agency should be able to develop a statistical detection
5.1.2.1 For those facilities that either have no definable
monitoring program that will not falsely detect contamination
hydraulic gradient, have no existing contamination, have too
whenitisabsentandwillnotfailtodetectcontaminationwhen
few background wells to meaningfully characterize spatial
it is present.
variability (for example, a site with one upgradient well or a
facility in which upgradient water quality is either inaccessible
5. Procedure
or not representative of downgradient water quality), compute
NOTE 1—In the following, an overview of the general procedure is
intra-well comparisons using combined Shewhart-CUSUM
described with specific technical details described in Section 6.
control charts (9).
5.1 Detection Monitoring:
5.1.2.2 For those wells and constituents that fail upgradient
5.1.1 Upgradient Versus Downgradient Comparisons:
versus downgradient comparisons, compute combined
5.1.1.1 Detection frequency ≥50%.
Shewhart-CUSUM control charts. If no volatile organic com-
5.1.1.2 If the constituent is normally distributed, compute a
pounds (VOCs) or hazardous metals are detected and no trend
normal prediction limit (5) selecting the false positive rate
is detected in other indicator constituents, use intra-well
based on number of wells, constituents, and verification
comparisons for detection monitoring of those wells and
resamples (6)adjustingestimatesofsamplemeanandvariance
constituents.
for nondetects.
5.1.2.3 If data are all non-detects after 13 quarterly sam-
5.1.1.3 If the constituent is lognormally distributed, com-
pling events, use the QL as the nonparametric prediction limit
pute a lognormal prediction limit (7).
(8). Thirteen samples provide a 99% confidence nonparamet-
5.1.1.4 If the constituent is neither normally nor lognor-
ric prediction limit with one resample (1). Note that 99%
mallydistributed,computeanonparametricpredictionlimit (7)
confidence is equivalent to a 1% false positive rate, and
unless background is insufficient to achieve a 5% site-wide
pertains to a single comparison (that is, well and constituent)
false positive rate. In this case, use a normal distribution until
and not the site-wide error rate (that is, all wells and constitu-
sufficient background data are available (7).
ents) that is set to 5%.
5.1.1.5 Ifthebackgroun
...

Questions, Comments and Discussion

Ask us and Technical Secretary will try to provide an answer. You can facilitate discussion about the standard in here.