WORK PLANS - Laserfiche WebLink

Home Browse Search

data values. Form 1, Form 2,Form 2 with substantial difference, and two-sided alternative hypotheses approaches(EPA, 2002b) are available in ProUCL 4.0. It is desirable to collect adequate amount of data of good quality from the populations under investigation using appropriate DQOs (EPA, 2006). In case, data sets cannot be collected using DQOs, it is suggested to follow the minimum sample size requirements as described in Chapter 1 of the ProUCL Technical Guide and User Guide. Some single sample and two sample hypotheses testing approaches as available in ProUCL 4.0 are listed as follows. Single Sample Hypotheses Testing Approaches One Sample t-Test: Based upon the sampled site data,this test is used to compare the site mean,p, with some specified cleanup standard, Cs,where the cleanup standard, Cs,represents an average threshold value, say po. The Student's t-test(or a UCL of mean) is often used(assuming normality of site data or when site sample size is large such as larger than 30, 50)to determine the attainment of cleanup levels at a polluted site, perhaps after some remediation activities. This test should be used on data sets without any ND observations. One Sample Sign Test or Wilcoxon Signed Rank(WSR) Test: These two tests are nonparametric tests and can also handle nondetect observations provided all nondetects (e.g., associated detection limits) fall below the specified threshold value, Ca. These tests are used to compare the site location(e.g., median, mean) with some specified cleanup standard, C3,representing the similar location parameter. One Sample Proportion Test or Percentile Test: When a specified cleanup standard,Ao, such as a PRG or a BTV represents an upper threshold value (e.g.,not-to-exceed value, compliance limit) of a contaminant concentration distribution rather than the mean or median concentration value, po, of the contaminant concentration distribution,then a test for a proportion or a percentile (equivalently a UTL 95%-95% or UTL 95%-90%)may be used to compare the site proportion, P, of exceeding (by site observations) the threshold value,Ao with some pre-specified proportion,Po, of exceedances of Ao by site observations. This test is especially useful when the data set consists of many ND observations. However,this test also assumes that all ND observations lie below the Compliance Limit,Ao. Two Sample Hypotheses testing Approaches Typically,two sample hypotheses testing approaches are used for site versus background comparisons, for comparisons of two or more site areas of concern(AOCs), or for comparison of, contaminant concentrations of two or more monitoring wells(MWs),provided enough data are available from each population under evaluation. Two sample hypotheses testing approaches as incorporated in ProUCL 4.0 are listed as follows. 1. Student's Two Sample t-Test to compare means -with equal dispersions - Parametric Test 2. Satterthwaite Two Sample t-Test to compare means -with unequal dispersions - Parametric Test