D.13 PAM

Approximate Cost: Free (freeware)

Version: 0.62 Beta

Source: www.henlopen.net/pam/index.htm

Operating System Needs: Windows (Macintosh OS X and Linux versions are available by request).

Usage Restrictions: PAM is freeware and can be downloaded and used free of cost. However, PAM is not open-source and cannot be distributed or resold or included in any other package. Full license details are provided with the downloadable installation program.

Input Structure: Data are provided to PAM in text files.

Overview

PAM is designed to support CERCLAComprehensive Environmental Response, Compensation, and Liability Act (Superfund) analyses for the USEPA Region 5 GEOS Program and focuses on intrawellComparison of measurements over time at one monitoring well (Unified Guidance). tests. The program can analyze multiple monitoring locations, contaminants, and events for a broad view of the changing groundwater conditions and contaminant concentrations. PAM creates outputs in standardized formats, including PDF documents, HTML pages, and PNG images. The program also evaluates trends, comparisons to standards, and comparison of recent data to baseline

Statistical Functions

Statistical Method	Capability As Is	Capability with Scripts/Add-Ins
Handling of NDs
Simple Substitution	●	N/A
Kaplan-Meier		N/A
ROS		N/A
Cohen/MLE	●	N/A
Exploratory/Diagnostic Tools
Summary Statistics		N/A
Distributional tests	●	N/A
Outlier tests		N/A
Data transformations		N/A
Statistical Design
Statistical Power		N/A
SWFPR		N/A
Contaminant ranking		N/A
Monitoring network optimization		N/A
Statistical Limits
Confidence Limits	●	N/A
Tolerance Limits	●	N/A
Prediction Limits	●	N/A
Testing Compliance Limits	●	N/A
Graphics
Plots/Charts	●	N/A
Batch plots	●	N/A
Tweaking of graphics	●	N/A
Statistical Comparisons
t-tests	●	N/A
ANOVA	◒	N/A
Spatial Analysis
Geostatistics/Mapping		N/A
Kriging/Interpolation		N/A
Spatial smoothing		N/A
Regression/Time Series
Trend Tests	●	N/A
Mann-Kendall	●	N/A
Linear regression		N/A
Nonlinear regression		N/A
Theil-Sen line	●	N/A
Time Series analysis		N/A
Multivariate Analysis
Multiple regression		N/A
Factor/Discriminant analysis		N/A
Bootstrapping

Capability Ratings:

N/A = Not applicable or not available

● = Full capability

◒ = Some capability

(blank cell) = No capability

Add-Ins Available

According to the PAM website, the software can be customized to incorporate additional input data formats, new statistical tests, and revised summary report tables. Authorized customization is performed by Subterranean Research, Inc.

Ease of Use and Data Import

PAM is easy to run because it is designed to support CERCLAComprehensive Environmental Response, Compensation, and Liability Act analyses, rather than a general purpose statistical package. Data input to PAM is provided in text files that can be easily generated from spreadsheets or databases.

Types of Distribution

PAM supports some basic distributional tests, but is not geared toward a comprehensive parametricA statistical test that depends upon or assumes observations from a particular probability distribution or distributions (Unified Guidance)., distributional analysis of data.

Visualization

The program displays results using charts and color-coded data tables. Charts show the original data, subsets of data used for each statistical test, and various confidence, prediction, and regulatory limits in a concise format.

Primary Uses for Groundwater Data Analysis

For each specified contaminant at a monitoring well, three types of tests can be performed:

Comparison to Standard Test: The data are compared to a standard, such as a maximum contaminant level (MCL) or alternate compliance limit (ACL), to determine whether the data are in compliance with the standard.
Comparison to Baseline Test: The most recent data value is compared to the prediction interval of the population.
Trend Hypothesis Test and Estimate: The Mann-Kendall and Theil-Sen trend line test are used to determine whether a statistical trend is present in the time-series data set.

Benefits

User-friendly environment for exploring data trends and analyzing whether the time series data are in compliance.
Runs in batch mode to process large data sets
Built atop MATLAB Component Runtime for fast computation
Free

Limitations

PAM is not a general-purpose statistical software and can only be used to perform trend and compliance-type tests.

Publication Date: December 2013

Permission is granted to refer to or quote from this publication with the customary acknowledgment of the source (see suggested citation and disclaimer).