STATISTICA cited in prestigious journal
Mon, 14 May 2012 14:05:00 -0500
What American Women Do For Work, via NPR
Fri, 04 May 2012 14:00:00 -0500
STATISTICA Enterprise™ Helps Enhance the Operational Process Flow at Instrumentation Laboratory, a Global Medical Device Manufacturer
Fri, 27 Apr 2012 17:49:00 -0500
Additional reviews: 2012 | 2011 | 2010 | 2009 | 2008 | 2007 | 2004 | 2003 | 2002 | 2001 | 2000 | 1999 | 1998 | 1997 | 1996 | 1995 | 1994
In a review written for users of statistical software in biological science, Dr. Graham Smith (a Senior Lecturer at Bath Spa University, UK) praised virtually all aspects of STATISTICA - its analytical comprehensiveness, graphics, and UI/system features. The graphics in STATISTICA were praised as "excellent and clearly outperform the perfectly functional, but more limited, graphics capability of " other applications. It was also noted that the "full analytical power of STATISTICA is excellent." Dr. Smith notes that in STATISTICA, the graph and analytical output is managed in sophisticated multi-tabbed tree-based workbooks or reports and as an OLE server (i.e., STATISTICA graphs can be embedded and edited from inside other applications). Smith goes on to say that the StatSoft website has an excellent on-line statistics manual and the STATISTICA help is particularly good for the statistical novice.
Back to Top
Leading manufacturers are looking for ways to apply advanced quantitative analysis and modeling techniques to help their employees create better products. This in-depth article describes how Caterpillar, Inc. - one of the leaders in manufacturing technology - used predictive data mining on their mountains of data that they have been already collecting to uncover the manageable process parameters most important to the quality outcomes of finished products.
Like many large companies, Peoria, Illinois-based Caterpillar has developed sophisticated data-collection techniques. A single manufacturing plant can use thousands of gages, sensors and other automated devices to collect data from machines and other manufacturing equipment. However, much of the massive amounts of data the company collected for monitoring hundreds of process parameters went largely unused.
Caterpillar has recognized that certain combinations of settings of process variables could potentially produce highly desirable outcomes, but the "rules" that govern the relations between the settings and their outcomes are usually very complex and not known to even experienced engineers. What combinations of knobs need to be turned and in which direction? What design features need to be modified and by how much? What exactly in the manufacturing "stream" needs to get adjusted, altered, tuned or tweaked to positively affect the quality and compliance outcomes?
Building on years of experience with SPC and Six Sigma quality initiatives, engineers at Caterpillar are now deploying PROCEED - a cutting edge data-mining and modeling software developed with StatSoft Inc. ( www.statsoft.com) - that empowers enterprise wide quality control and improvement. The software has helped Caterpillar's manufacturing and design engineers use empirical data to achieve significant quality and performance improvements.
A breakthrough in PROCEED overcomes a critical barrier in deploying data mining in manufacturing: making the specific recommendations from the predictive models relevant to practical implementation. Included with PROCEED is not only a highly intelligent computational engine that searches for root causes and optimizes process parameters but also a set of graphical tools to help users interact with the virtual process models. The user interface offers a mechanism that allow engineers to "poke" the model with what-if scenarios so that they can see the implications of their actions in a safe (virtual) environment.
For example, the software has managed to identify a subset of variables that caused trim balance outcomes during finished product testing - a very complex problem that could not be solved using traditional methods. "The model allowed the Caterpillar team to determine that a reduction in run-out of two interacting features on the assembly would reduce [the occurrence of] trim balance problems by approximately 50 percent," says Bill Matthews, a manufacturing engineer at Caterpillar. Click here to read the entire article
StatSoft is pleased to announce that STATISTICA has been chosen as the top statistical software provider by Scientific Computing in their annual Reader's Choice Awards.
Each year since 1992, Scientific Computing magazine has asked readers to vote for technical computing products that they deem to be the very best. Scientific Computing's readers are challenged to consider such factors as product quality, reliability, ease-of-use, technical support, and value.
Win Noren, International Operations director for StatSoft, notes that, “This is an honor for StatSoft and it speaks to the quality of our development, service, and sales teams. We're very pleased that readers have given STATISTICA a gold ranking, which is the highest ranking for analytical software.”
This article provides an in-depth look at the PROCEED software platform and how it is currently being used by large manufacturing companies such as Caterpillar. The review details PROCEED's analytical approaches, the various ways in which they can be applied, and the optimal outcomes that the software produces. “Until now, data analysis techniques have been limited to one or two variables. That has changed thanks to new software developed by Caterpillar and StatSoft Inc…Together, the two companies created PROCEED software…for the modeling, optimization, and simulation of complex manufacturing processes…"PROCEED software goes beyond the traditional methodologies to link variables from three or more facets of a given process. The higher-order analysis helps produce "actionable information" that allows engineering and production managers to create and compare what-if scenarios.”
Caterpillar's Tony Grichnik states that PROCEED's “key is gaining insight from the data's knowledge and then coupling the knowledge to actions.”
The article discusses how PROCEED uses “traditional knowledge extraction methods to help manufacturers derive and validate simple to complex causal relationships between manufacturing processes and product quality outcomes...PROCEED software provides an interactive software environment to optimize the production process to achieve the best results along multiple outcomes...The software also reduced the expensive and time-consuming finished product testing at Caterpillar. The ROI is derived from decreased invetment in test equipment and personnel to perform the test, increased product throughput from the reduction of the time-consuming testing, and reduction of expensive rework and scrap by reducing the rate of product failures.”
In March 2006, Dr. Robert Nisbet reviewed six leading data mining applications and rated them according to a comprehensive list of analytical functions and data management capabilities. STATISTICA has received the highest total number of points (1,950). Dr. Nisbet's concludes that using STATISTICA Data Miner is "almost a no-brainer! Non-statisticians and/or non-data miners take heed! This system takes most of the 'magic' out of data mining ...for the vast majority of potential users among business analysts, it is a great blessing."
Review a table of rankings for STATISTICA Data Mining.
In a comprehensive comparative classification of statistical software published by Dr. J. A. Wass (a statistician at Abbott Laboratories), 11 featured general statistics packages were divided into three categories based on the functionality that they offer:
While the review offers no comparative ratings or rankings within each of the three categories, Dr, Wass praised not only the comprehensiveness of STATISTICA and its "we do it all" approach (he states that it took him the entire evening just to go over the list of features of STATISTICA), but also the menu-driven user interface of the application that makes all the extensive functionality so easily accessible to the user.