Incremental Sampling Methodology: Applications for Background Screening Assessments.

Area of Science:

• Environmental Science
• Statistical Modeling
• Geospatial Analysis

Background:

• Background screening assessments are crucial for environmental site evaluations.
• Incremental sampling methods (ISMs) are increasingly used, presenting unique data analysis challenges.
• Evaluating statistical methods for ISM data is essential for accurate environmental decision-making.

Purpose of the Study:

• To evaluate the performance of statistical analysis methods for background screening using data from incremental sampling methods (ISMs).
• To compare hypothesis testing and upper tolerance limit (UTL) screening methods under various site and background conditions.
• To provide recommendations on appropriate statistical approaches for ISM-generated datasets.

Main Methods:

• Numerical simulation study to assess statistical method performance.
• Implementation of hypothesis tests (two-sample t-tests) and UTL screening methods.
• Adherence to U.S. Environmental Protection Agency (USEPA) guidance for error rate specification.

Main Results:

• Two-sample t-tests demonstrate robust performance, meeting standard criteria even with smaller sample sizes.
• Performance of t-tests is influenced by unequal population variances and small mean differences.
• UTL methods show conceptual limitations for single-decision unit ISM datasets and insufficient statistical power.

Conclusions:

• Hypothesis testing, specifically two-sample t-tests, is a reliable method for background screening with ISMs.
• UTL screening methods are generally unsuitable for ISM data due to inherent limitations and low power.
• The findings support the use of hypothesis testing for environmental background assessments using ISM data.