Mon, 20 May 2013 19:00:00 GMT
Fri, 17 May 2013 20:28:00 GMT
Mon, 13 May 2013 08:48:00 GMT
Additional Reviews: 2012 | 2011 | 2010 | 2009 | 2008 | 2006 | 2004 | 2003 | 2002 | 2001 | 2000 | 1999 | 1998 | 1997 | 1996 | 1995 | 1994
In an review of STATISTICA by Dr. Joseph M. Hilbe, software review editor for The American Statistician, the author states that "STATISTICA provides its users with a vast array of capabilities, some of which cannot easily be found elsewhere" and he praises the strengths of the STATISTICA package in a wide area of applications, including graphical analysis, data mining, Six Sigma methodology, quality control statistics, design of experiments, multivariate analysis, and non-parametric methods. Three examples of representative analyses, and accuracy tests were given and Dr. Hilbe has concluded that for those whose interest is in multivariate modeling and data mining "STATISTICA is truly a leader among statistical packages." The review also mentions that "the many cutting-edge techniques available to users should allow modeling of a wide range of data situations" and that such methods as neural networks, CHAID, C&RT which are part of STATISTICA are usually found in separate, standalone packages and having them included as part of one software system provides the user with a "variety of methods, just a keystroke apart...one can readily see why the package builds loyalty."
Back to Top
In a review of the recently released STATISTICA version 8, the Statistics Software Reviewer for Scientific Computing World describes the many areas of new functionality that have been added to STATISTICA, including new statistical procedures, graphics, and system features including the general usability . The author states that the new features are "substantial..and there is a good spread of on board additions to the statistics capabilities." Scientific Computing World plans on taking a more in depth look at the new STATISTICA Automated Neural Networks module later but the current review concludes after an initial set of tests that this new module provides both a "boost in capability" while also being a "considerable step forward in usability."
This review of STATISTICA 8 concludes by saying "at the bottom line this is an upgrade which will pay for itself in very short order through both enhanced capability and more, deeper, more intuitive usability."
In a Diplomarbeit (an equivalent of the US Masters Thesis) defended in February, 2007 at the Department of Economics and Applied Informatics at the University of Bielefeld (Germany), a quantitative, comparative study was conducted to assess the functionality and performance of STATISTICA Data Miner and another leading data mining application.***
In this comprehensive, 136-page technical report summarizing a meticulously performed study, the author, Patrick Goetze (under direction of Prof. Dr. Thorsten Spitta and Prof. Dr. Reinhold Decker) compared the two software programs on a large number of quantitatively defined dimensions, following criteria derived from ISO Software Quality Norms. The comparison includes three general categories of dimensions: "Usability" (ISO9126-1, ISO9241-10 and -11), "Overall Functionality" (ISO9126-1), and "Quality in Use" (ISO01, p.12). While the study refrains from concluding with an explicitly recommendation about the superiority of either application, adding the ratings assigned to the two programs across all dimensions makes STATISTICA Data Miner the clear overall winner.
*** The producer of this other data mining application has requested that their name not be publicized by the Department of Economics and Applied Informatics in context of this review but that name and the detailed results are still available to the public at the University of Bielfeld .
In an article on the use of mathematical and statistical software for finance and economics, F. Grant mentions the need for "speed, solidity and maintainability" - the needs which STATISTICA meets well. STATISTICA Data Miner is mentioned as having users in banking and finance, and its ability to access specialized R functions is discussed. Grant concludes by stating that "the extent of actual or potential scope for use of physical sciences models in finance and economics seems to be unlimited."
Synopsis of the article. This article discusses software applications in the fields of engineering and physics to aid the design and testing of products. The benefits of such simulation include improved design, lower production costs and greater efficiency As production processes generate more data than ever before, engineers require software that can efficiently analyze these this data and convert them into useful information. StatSoft offers software that can use those data and take a direct role in the experimental process of engineering. For example, designers of generators have used StatSoft software to simulate vibrations and deflections, coupling electromagnetism and solid mechanics. StatSoft's PROCEED was developed as part of a collaboration with Caterpillar, the mechanical engineering company, to calculate the optimum parameters in complex product (e.g., engine) design such as reliability, fuel usage, or power. It can do multiple simultaneous optimizations, and will optimize the parameters to a range of values, rather than a single value, which might be difficult and costly to implement. The statistical models used are often complex and non-linear. For this, STATISTICA uses data mining techniques including neural networks or recursive partitioning methods (tree methods) that are specifically geared to a large number of parameters. These powerful techniques could not have come at a better time for engineering. Robert Eames, Director of Business Development at StatSoft, says: 'We're at a critical point in history; this is the convergence point from a number of processes. So many processes pump data out at an enormous rate and every manufacturer has huge databases. Over the past decade data mining algorithms have progressed until the modeling of this data was possible.'