Products Services Classes Downloads  FAQ  Contact Home






General Questions
Statistical Questions
Support: Sanitas
Support: WQStat Plus

General FAQ

1) Why use a specialized groundwater statistics package?

This question was addressed in 2004 by Dr. Kirk Cameron, author of the USEPA Unified Guidance document. To read that white paper click here.

2) What is Sanitas™?

Sanitas™ is a state-of-the-art groundwater statistical software package that automates EPA-recommended statistical methodologies (and includes all of the statistics offered in the now discontinued WQStat Plus). Its decision support and data pre-screening features contribute to the ease of running large and small tasks, and the program offers considerable flexibility in analysis and output, with out-of-the-box default settings appropriate for most uses. It has evolved over 30 years to satisfy a variety of real-world users, from landfills to coal ash ponds, and it continues to evolve to meet new regulatory and statistical recommendations. Analyses are performed rapidly through the Batch functionality, and optional Summary Tables accompany full-page statistical reports. Sanitas™ is in use by regulators in most US States.

Sanitas™ is licensed by the facility, or analyzed unit. So a user analyzing data at, say, several landfills will purchase a license for each regulated landfill, with the cost based on the tiered discounted pricing structure shown on the Sanitas Pricing page. The software may be installed on multiple machines, and multiple users may simultaneously analyze data.

3) What is the software purchasing and delivery process?

The Sanitas™ package is customized for each user, so we need to collect some information and then email a custom link for downloading the program. We accept credit cards, company purchase orders or mailed checks, or we can invoice your company for the purchase. Please contact us by telephone or e-mail to place your order.

4) What sort of support is offered?

When you purchase a license, you are entitled to one year of unlimited technical support, 90 minutes of statistical software support, and will receive any program updates or new versions of the software that are released within that year. At the end of the year, you may participate in an annual maintenance program which continues to offer these items. As new versions of the software are released, you will automatically receive the updated program. Our tech support is known for fast responses!

Statistical FAQ

1) What are parametric vs. nonparametric limits?

Prior to constructing limits, such as prediction limits, it is necessary to determine whether the background data set follows a normal (or bell-shaped curve) distribution, or whether the distribution is unknown. When the data set follows a normal or transformed-normal distribution, a parametric test may be constructed, where the limit is based on a pre-specified alpha level. The limit can account for the resample plan, and takes into account the background mean and standard deviation, as well as the number of available background samples and the number of future compliance samples that will be compared to the limit. When the distribution of the background data is unknown, a nonparametric limit is recommended which is based on the highest (or sometimes second highest) background value. The alpha level associated with the nonparametric tests is based on the number of background values and can account for the resample plan and number of future compliances values that will be compared to the limit.

2) What does normal or transformed-normal mean when referring to the distribution of the data?

The Shapiro Wilk normality test, for instance, tests the background values of a data set and statistically determines whether the distribution follows a normal (or bell-shaped curve) distribution. If the original data set fails the test, there are a series of transformations known as the Ladder of Powers that may be applied to determine whether any transformation helps fit the data to the bell-shaped curve. The Ladder of Powers was developed by Dennis Helsel and includes the following transformations: x, x1/2, x2, x1/3, x3, natural log, x4, x5, x6. If one of these transformations passes the normality test, all data are transformed prior to the construction of any limits.

Unless “plot transformed values” is selected in the Configure Sanitas options window, Sanitas will back transform the final limit. In either case, it is always advisable to closely examine the statistical limit to confirm that it is appropriate based on the actual data. In certain cases, transforming data can create unusually high limits, which effectively decreases the chance of detecting an impact from the facility.

3) What is “alpha” and how is it related to “confidence” levels?

The alpha level associated with a given test is considered to be the false positive rate (i.e. the odds of declaring an exceedance when there is none). The confidence level then is equal to 1-alpha. Historically, intrawell tests have been performed at a default alpha level of .01 (i.e. 99% confidence) and interwell tests at .05 (i.e. 95% confidence). Because the false positive rate and false negative rate (i.e. the odds of missing a release) are inversely related, these alpha levels were established to balance the two rates. However, the latest guidance from the EPA focuses not so much on the individual false positive rates, but rather on the overall site-wide false positive rate and power associated with the statistical tests to detect a release.

4) How should outliers in background data sets be handled?

Outliers in background may provide limits that are not regulatory conservative. When outlier values are present, they should not automatically be removed, but rather researched to determine whether the value is an error and can either be corrected, or flagged as an outlier and removed prior to construction of statistical limits. Careful consideration should be given when the values cannot be determined to be in error, as these values could represent natural variation. Removing the values could result in limits that will increase exceedances in future compliance points when no contamination is present.

5) What is the difference between interwell and intrawell tests?

Interwell tests are constructed by pooling upgradient well data for the purpose of creating limits for downgradient well comparisons. Intrawell tests, on the other hand, utilize historical data from within a given well for the construction of limits for comparison with more recent data from the same well.

6) How do you decide whether to perform interwell or intrawell tests at a facility?

The hydrogeology should always be considered at a site, and if the underlying aquifer is continuous, it’s possible that interwell tests may be utilized. If the hydrogeology suggests heterogeneity, intrawell tests will most likely be utilized once it is demonstrated that there are no prior releases. In either case, the ANOVA test may be applied to upgradient wells in order to determine “statistically” whether spatial differences exist. In the absence of variation among upgradient wells, interwell limits are preferred. Otherwise, intrawell methods are recommended.

7) What does Site-Wide False Positive Rate (SWFPR) mean?

Based on the total number of statistical tests performed at a facility (i.e. the number of wells x the number of constituents), the SWFPR reflects the percentage of time you can expect at LEAST one false positive per sampling event. The basic equation for estimating the SWFPR (not including resampling) is the following:

SWFPR = 1 – (1-alpha)^n

Where:

alpha = test-wise false positive rate
n = number of wells x number of constituents

The EPA Unified Guidance suggests that the annual SWFPR be no greater than 10% (i.e. 5% per semi-annual event; 2.5% per quarterly event).

It goes without saying that the more statistical tests performed at given alpha level at a facility, the higher the SWFPR.

8) How can you control the Site-Wide False Positive Rate?

The EPA Unified Guidance document addresses this in great detail. In the meantime, there are several ways to reduce the overall site-wide false positive rate, such as reducing the total number of statistical tests performed. Well/constituent pairs with 100% nondetects do not require statistical analysis, therefore, they should not be factored in when calculating the SWFPR. Another way to reduce the total number of tests is to perform statistics on "indicator parameters" (i.e. parameters to monitor at a given that facility – based on leachate data or the composition of the landfill – that would indicate a release). Introducing a resampling plan is also an excellent way to reduce the false positive rate. In the event of a statistically significant finding, one or more resamples is taken for that well/constituent to either verify or refute the initial finding.

9) When proposing to perform intrawell analyses at a facility, what is the best way to determine whether the proposed “background” from within each well has not been impacted?

Prior to performing intrawell analyses, a screening should be conducted at each well for volatile organic compounds (vocs). When vocs are present, an evaluation should be made to determine whether the landfill is the source, or whether something off-site is impacting the monitoring wells. Additionally, all proposed background data from within each well should be carefully screened for outliers, trends, and seasonal effects (i.e. cyclical patterns in data) which, if not addressed, may create limits that are not regulatory conservative.

10) How often should I update background data?

Periodic updating of background data is necessary in order to increase the background sample size, as well as to account for present-day conditions of groundwater due to natural variation. Statistical limits should be reflective of current groundwater quality in the absence of contamination.

EPA Guidance suggests that periodic updating should take place after 4 new sampling events have taken place (i.e. every 2 years for semi-annual sampling; every year for quarterly sampling).

As with the initial screening for proposed background data, the entire data set for each well/constituent should be evaluated for outliers, trends, and seasonal effects. Once those issues are addressed, the Intrawell Mann-Whitney (also known as the Wilcoxon Rank Sum test) may be used to test the current background data set against the group of data you are proposing to add to background. If there are no statistically significant differences between the two populations, the newer data may become part of the existing background data. If statistically significant differences exist, investigation should be done to determine the reason. In some cases, the more historical data may not be reflective of present-day conditions in which case it may be appropriate to propose to use more recent data as background.

SUPPORT FAQ

Sanitas™

1) What's the best way to get my data into Sanitas?

Sanitas provides the easiest import process on the market. If your data are in electronic format, chances are they're already in some kind of "flat file" format. If not it's generally a simple matter to produce a flat file (which is the most common data interchange format). And Sanitas can read ANY* flat file format.

*If the Sanitas Data Translator cannot read your file, or if you are unsure how to handle your data, please send us your file (see our contact page). This offer applies to Demo users as well as licensed users.

2) How do I install a new version in such a way that I can continue to use previous versions of Sanitas for other sites?

Most Sanitas users participate in the maintenance program and renew their Sanitas licenses annually. In doing so, users stay current with the most up-to-date version of the Sanitas software and when a new license is purchased, that facility is easily added to their existing program. If, however, you have not upgraded your software for older licenses, and purchase a more recent version of Sanitas for a new facility, you will need to install the program into a separate directory in order to maintain access to the previous licenses.

3) I'm getting a warning on starting Sanitas: Unable to check for updates.

Sanitas automatically compares itself to the latest version available over the Web. If it is out of date, it will prompt to download the update. If, however, an internet connection is not available, or a firewall prevents access, then this warning will appear. Some of the updates may be quite important, and it is highly recommended that this situation be resolved, in such a way that Sanitas can at least occasionally complete the update process. If this is not possible, please contact us to discuss alternate methods of obtaining updates.

4) Can I install Sanitas on a network server?

By default, Sanitas installs on the local hard drive. It is not recommended to move it from its installation folder, nor is it typically required, because the software can be installed on unlimited machines and used simultaneously if desired.

4b) Can I use a VPN?

Beginning with Version 10, the answer is Yes! The new .Sanitas data file format is completely portable and self-contained, and we encourage you to locate data files on a shared server if this meets your needs. Sanitas will enforce that only one user at a time can access an individual data file.

5) What is the current version of Sanitas?

Version 10. If you did not receive an email upgrade notice, please contact us!

6) I understand that you can append data to existing files within Sanitas. What is the process?

Save your flat file as a "text (tab delimited)" file.
Proceed as with any translation, but choose a different menu item:
Within Sanitas, choose "File->Append Flat File data...".
Verify that Sanitas has chosen the appropriate settings for your file, and then click "Import".

7) What happens during an Append if constituent and/or well names are spelled differently?

If a the file you are appending has a constituent and/or well that is not in the constituents/wells in the original data file, you will be asked if you would like to Add or Ignore such items. Click Add, and then after translating, go to File->Edit Current Data File..., and on the Constituents tab, click the Aliasing button, where you can resolve spelling differences. The alias functionality is designed to handle occasional discrepancies; it may be more efficient to reconcile names prior to translation.

8) Text is running off of the page on the graphs.

To correct this, check "Wide Margins" on the Output tab of the Configure Sanitas Window. This is also recommended for any reports which will be placed in a binder. This will ensure all of the information and dates are visible.
If Wide Margins does not fix the problem, more formatting options are available in the .ini file. Please see the documentation or contact us for more details.

9) Can I save Sanitas reports to a PDF or other file?

There are two ways of working with Sanitas output other than printing a hardcopy.

1) Sanitas graphs can be copied to the Windows clipboard and/or saved to a file. To do so, hold down the Shift key and then click the mouse on the Print button. Images on the clipboard or in files can then be pasted or imported into applications such as Microsoft Word™ etc. If you want to edit the images themselves, we recommend a "draw" program such as Corel Draw™. You can also copy any print job to the clipboard using FinePrint, described below.

2) If you want to create a PDF or other electronic presentation of your reports, you must use a third-party software program for this purpose. Microsoft Print to PDF ships with MS Windows. Free programs such as CutePDF™ (http://www.cutepdf.com/) or print2PDF™ ("sponsored" version is free at www.software602.com/products/print2pdf/) are available.

10) I'm getting warnings about lines in my data file containing both Space and Tab characters.

This is just an extra level of error checking. It might be worth finding out why you have spaces in the data section of the file. Spaces are legal delimiters in a Sanitas data file, and to have both tab and space characters in the data could mean subtle formatting problems. If you're not sure what's going on with this, please send us your data file and we'll take a look.

11) When I bring up the online help, I get a page with no content.

This is a problem that occurred in older versions of Google Chrome™. Please update your browser to the latest version. If you continue to experience trouble, please contact us.

SUPPORT FAQ Cont.

WQStat Plus™

1) What's the best way to get my data into WQStat?

Sanitas and WQStat Plus provide the easiest import process on the market. If your data are in electronic format, chances are they're already in some kind of "flat file" format. If not it's generally a simple matter to produce a flat file (which is the most common data interchange format). And WQStat Plus can read ANY* flat file format.

*If the WQStat Plus Data Translator cannot read your file, or if you are unsure how to handle your data, please send us your file (see our contact page). This offer applies to Demo users as well as licensed users.

2) What does [Demo] mean in the user interface?

WQStat Plus v.9 is derived from the Sanitas™ program. Items marked [DEMO] in the user interface are features exclusive to the full Sanitas program which is licensed on a per-facility basis, and their use will cause the software to enter Demo mode. To return to default mode, restart the software. No permanent changes result from using Demo mode, and we invite you to explore these premium features.

3) I'm getting a warning on starting WQStat: Unable to check for updates.

WQStat Plus automatically compares itself to the latest version available over the Web. If it is out of date, it will prompt to download the update. If, however, an internet connection is not available, or a firewall prevents access, then this warning will appear. Some of the updates may be quite important, and it is highly recommended that this situation be resolved, in such a way that WQStat can at least occasionally complete the update process. If this is not possible, please contact us to discuss alternate methods of obtaining updates.

4) I have made changes to my data file, however, WQStat is not reading the changes.

WQStat Plus attempts to detect changes to the database, even if they were made directly through MS Access™ or another external editor. If you have made a change that is not appearing in the View, try re-selecting the constituent to cause the data to be re-read. If this is doesn't take care of it, or if the problem is recurring, you can show a "Reset" button by editing the line SHOW_RESET_BUTTON_IN_VIEW=false in the .ini file. See the documentation for details on editing the .ini file.

5) What is the current version of WQStat Plus?

Version 9.4 will be the final release of WQStat Plus. The program is no longer being sold or maintained. WQStat users are encouraged to consider upgrading to the Sanitas™ package, and are being offered substantial discounts for upgrading.

6) I understand that you can append data to existing files within WQStat. What is the process?

Save your flat file as a "text (tab delimited)" file.
Proceed as with any translation, but choose a different menu item:
Within WQStat Plus, choose "File->Import Data->Append Flat File data to Current Data File".
Verify that WQStat Plus has chosen the appropriate settings for your file, and then click "Import".

7) What happens during an append if constituent names are spelled differently?

If a the file you are appending has a constituent that is spelled unlike any of the constituents in the original data file, after translating go to Options->Alias Constituents and/or Stations... The alias functionality is designed to handle occasional errors; if you have a systematic renaming of constituents (or wells) it may be more efficient to reconcile names prior to translation.

8) Text is running off of the page on the graphs.

To correct this, check "Wide Margins" on the Output tab of the Configure WQStat Plus Window. This is also recommended for any reports which will be placed in a binder. This will ensure all of the information and dates are visible.
If Wide Margins does not fix the problem, more formatting options are available in the .ini file. Please see the documentation or contact us for more details.

9) Can I save WQStat Plus reports to a PDF or other file?

There are two ways of working with WQStat Plus output other than printing a hardcopy.

1) WQStat Plus graphs can be copied to the Windows clipboard and/or saved to a file. To do so, hold down the Shift key and then click the mouse on the Print button. Images on the clipboard or in files can then be pasted or imported into applications such as Microsoft Word™ etc. If you want to edit the images themselves, we recommend a "draw" program such as Corel Draw™. You can also copy any print job to the clipboard using FinePrint, described below.

2) If you want to create a PDF or other electronic presentation of your reports, you must obtain a third-party software program for this purpose. We use a package called FinePrint™ (www.fineprint.com has a free fully-functional demo)* as our default "printer", and then another "virtual printer" called print2PDF™ ("sponsored" version is free at www.software602.com/products/print2pdf/) to create PDF files. There is also a PDF-creation package bundled with FinePrint, Adobe sells this kind of software, etc.
There's something else you should know if you take this route. Frequently these PDF-creation "virtual printers" store each print job (i.e. each page) to a separate .pdf file. So you need a tool like FinePrint, which allows you to combine print jobs before sending them to the PDF-creation software. Please let us know if you need additional help with these issues.
*The total cost of licensing the software we recommend here is about $50.

10) I'm getting warnings about lines in my data file containing both Space and Tab characters. I've never received any errors with this data file in the past - why am I getting them now?

This is just an extra level of error checking that was added in WQStat Plus v.9. The data format requirements have not changed. But it might be worth finding out why you have spaces in the data section of the file. Spaces are legal delimiters in a WQStat Plus data file, and to have both tab and space characters in the data could mean subtle formatting problems. If you're not sure what's going on with this, please send us your data file and we'll take a look at it.

If your question is not among those listed, or for more information, please contact us.
  © Copyright 1999-2024 Sanitas Technologies. All Rights Reserved.