Who's doing this...?

The MIX program has been developed by Leon Bax, with assistance from many beta-testers and colleagues in clinical epidemiology, medical statistics, and medical informatics. To ensure downloads and payments can be handled in a professional matter, BiostatXL was launched by Leon in 2009 and this is now the official entity that handles development and maintenance of MIX 2.0. 

Development of early versions of MIX (~1.7)

Even though numerous researchers in health care are confronted with or involved in meta-analyses, there has been a lack of software that can aid researchers in their learning phase. Existing software that is modern, both in terms of interface and in terms of computational and graphical options, is often commercial and can be rather expensive. The primary objective in setting up the MIX project was to develop a free yet comprehensive program for meta-analysis that could be applied in both analytical and educational settings. Because meta-analyses are still most often done with data from causal studies (therapeutic trials as well as etiologic cohorts and case-control studies), the initial focus was on causal meta-analysis.

Before the actual development, an inventory was made of the most important meta-analytical tests and approaches. Noriaki Ikeda, Ly-Mee Yu, and Carl Moons were the primary collaborators at this stage. Because the program was to be free, development and maintenance had to be relatively quick and easy. Therefore, our a priori idea was to use the Visual Basic Editor of Excel and create an Excel add-in. Although a rather unorthodox approach in this area (all existing meta-analysis programs are stand-alone programs and work independently of Microsoft Office), Excel provides a sophisticated calculation and graphics platform that is well-suited to many meta-analytical methods and at the programmer's disposal before any programming is done.

Since we wanted to move beyond the occasional spreadsheet that can perform meta-analytical calculations, we started by designing a programming structure in which the already existing Excel functionality could be exploited to its maximum. Sophisticated procedures were custom-programmed with Visual Basic in the Visual Basic for Applications (VBA) editor of Excel. The so-called front-loader (a start-up program initiated with an icon) and some small auxiliary programs (all being non-Excel entities) were developed with Visual Basic 6.0 (VB6). In October 2005, during the Cochrane Colloquium in Ottawa, MIX 1.0 became publicly available for download.

MIX 2.0

MIX 2.0 is the most recent version of MIX. MIX is totally rewritten and now compatible with Excel 2007 and Excel 2010. It uses the Ribbon as interface and contains many new features.

MIX 2.0 is distinctly different in many ways. First of all, it will be available in a free Lite version and a paid Pro version. The Lite version will contain most if not all features of the Pro version, except the functionality to create and load your own data sets. The Lite version, however, will contain many of the data sets used in a wide variety of books and methodological articles about meta-analysis and is therefore an ideal companion for learning and teaching. 

During early development of MIX 2.0 it became apparent that very few people were willing to give their time and expertise to the development of a program that would not create any revenue. Donations were sparse (20 US dollars in 5 years), so that was clearly not the way to go either. Selling or integrating the program in an existing organization seemed an option, but it became clear that that would not only lead to commercialization but also to loss of control for me (Leon). In early 2009, I decided to pursue further development of MIX on my own and create a free version for learning and teaching purposes (Lite) as well as a commercial version for professional purposes (Pro).