Introduction

StatTools is a collection of statistical programs that were used in clinical research and quality assurance. These have accumulated over the years in response to needs, requests, and enquiries, from colleagues and students.   They should therefore be viewed more as a handy set of tools, all of which were found to be needed or useful by some clinicians or researchers. Users should therefore search through StatTools to see if a program that is useful to them exists, but should not see StatTools as a structured set of instructions or a system of teaching.

StatTools contains no original algorithms or statistical theories. All the programs in StatTools have been described in statistical packages, text books, published papers, and on web sites in the public domain. What we did was to study the materials, write the programs that convert the maths into a usable program, and place these in a user friendly format on the Internet. Although StatTools provides a quick solution and easy calculation that may immediately solve a problem, users are nevertheless encouraged to follow the reference trail provided, accessed the original materials, and learn in details what a particular program is all about, how the results should be interpreted, and what the pitfalls are.

StatTools originated as a resource for inexperienced researchers on the website of the Department of Obstetrics and Gynaecology Chinese University of Hong Kong, and existed on the Internet for over 20 years. It became popular, and at one stage it received a few thousand hits per month, and its pages were linked to many other sites. The original StatTools site still exists, but there was no further addition or changes made to it since 2002 when I retired from the university.

Between 2002 and 2007 StatTools were recompiled as JAVA applets and presented on the website of the Mater Research Support Centre. Working with two statisticians, Scott Pain and kristen Gibbons, we added a lot of details to existing programs, and increased the number of programs, particularly those calculating sample size requirements.

Since my retirement in 2007, I have recompiled the programs using PHP, adding to them a graphic capability, and added a number of new algorithms (particularly programs using sequential analysis and quality controls), and placed them on my personal website. As there are increasing hits and enquiries recently, in August 2010 I have placed the programs on this stand alone site.

StatTools has received much feedback from users, and this helped to correct errors and improve presentations and explanations. I hope users will continue to offer feedbacks to these pages.

In November 2011 StatTools received some 600 hits per day, and these increased steadily and by April 2012 StatTools received about 2800 hits per day. Feedback and questions have also increased from one every couple of months to one to two per week.

Disclaimer

During the development of the programs, the results of the calculations were checked against text book examples and the output from statistical packages.  Users and colleagues have also provided feedback, pointing out corrections and enhancements needed, so that the pages have improved with usage.   Although these efforts should make errors unlikely, it is still not possible to rule them out entirely.

Organisation of the pages

Web site level

The appropriate information and programs can be accessed via one of the two methods provided

• The StatTools index file StatToolsIndex.php. The programs are indexed under the headings of sample size, concordance, correlation and regression, non parametric and parametric statistics, plotting graphics, prediction statistics, meta-analysis, sequential statistics, probability, and useful utilities.
• The key word search engine StatToolsKeySearch.php. Keywords are organised in alphabetical order, and relevant programs are listed under the keywords.
• Links to the index and keyword search pages are available on the top of every page.

Subject or problem level

Information and calculations for each statistical problem of program is divided into a number of sub programs.

• problem_Exp.php is the introduction and explanation page. It introduces the the subject, describes how data entry should be handled, interprets the results produced, provides examples where it is appropriate, and lists the references
• problem_Pgm.php is the program page. As this page is sent out each time a calculation is performed, there is a need to reduce band width, so this page is terse. It contains text boxes and buttons and a minimum explanation for data entry. When the data is submitted, the server performs the calculation and the results are presented.
• problem_Tab.php contains the statistical table associated with the problem, and problem_App contains the Java applet if one is needed. Tables are only available or needed in a small proportion of the problems, and JAVA applets are rarely used, as they are only needed for long recursive calculations and there are only very few of them.

A typical example is the z test, so the zTest_Exp.php introduces and explains the z test, zTest_Pgm.php calculates probability of z, and zTest_Tab.php presents the standard table of probability of z.

On each page

Three sets of information are available at the top of each page

• The page header announces what the page is about
• StatTools links, these are useful links for users and consists of the following.
  • Link to the home page (this page)
  • The StatTools index and the key word search engine from which the appropriate pages can be found and accessed
  • Explanation and advice on input and output, data input and result retrieval
  • Explanation and advice on how to use the graphic utilities provided, data input, changing size, color and style of graphic components, and retrieval of the result bitmap.
  • Contact web master. Contact is always welcomed, and allows users to make suggestions and requests, ask questions, and provide feedbacks.
• Links to related pages. As explained previously, each subject is divided into the explanation, program, table, and other pages. Links to each other in the same subject is provided.

The content of each page are divided into sections, the sections are separated by horizontal lines, and each section has a sub heading linked to a list near the top of the page.