This page contains a Flash digital edition of a book.
statistics in manufacturing industry


the same journey. Data warehousing is now commonplace; a small precision engineering company for which I recently did consultancy work has 11 employees and a multi-terabyte historical data store into which new cases flow by the second and to which new variables are regularly added. Tat small company is also giving


serious consideration to environmental sustainability – ‘not’, as its owner/manager succinctly told me, ‘because we’re tree huggers, but because environmental sustainability has become a hard matter of commercial sustainability.’ A large part of my task there was to advise on choice of soſtware and methods with which to make good use of the mushrooming data pool – or, as the proprietor simply put it, ‘stop drowning in the numbers and start turning them into brass tacks.’ Quite apart from the other growth


problem of ‘the supply line ecosystem’, mentioned earlier, this matter of larger and expanding data sets is the crucial dividing fault line between small and scalable data analytic systems, in manufacturing as elsewhere. It produces much soul searching as enterprises either grow, or increase their


commitment to, statistical resources. Many products are limited to the number of data points which can be stored in available operational RAM. Te omnipresent spreadsheet, never the ideal statistical tool but much loved and clung to for its familiar face, almost always has a systemic limit on the number of cases and (less restrictively) the number of variables, regardless of total data point count. If my small engineering client switches to an expandable soſtware product capable of handling their whole data store, the price of that soſtware would be swamped by the collateral costs of implementation. On the other hand, a make-


Further information:


Camo Software: Unscrambler www.camo.com


Georgia Technology Institute: various applications www.gatech.edu


Jeffress Engineering: BevScan www.bevscan.com


Kovak Computing: XLStat and MVSP www.kovcomp.co.uk


do-and-mend strategy postpones those costs to a future when the problems will have increased in magnitude. In this particular case, the answer was to work smarter rather than bigger: switching to a product which would give them true multivariate reach but learning to use only relevant subsets, and using designed samples rather than whole populations for analysis. One day, though, the problem will have to be revisited.


References and Sources For a full list of the references and sources cited in this article, please visit www.scientific-computing.com/ features/referencesfeb12.php


MathStatica: mathStatica info@mathStatica.com


Minitab: Minitab sales@minitab.com


nGimat: nanotechnology www.ngimat.com/contact


StatSoft: Statistica Data Miner info@statsoft.co.uk


Wolfram Research: Mathematica info@wolfram.co.uk


Bring data to life


YOUR DATA MIGHT BE COMPLEX, BUT YOUR SOFTWARE SHOULDN’T BE.


The Unscrambler® X combines advanced


multivariate data analysis with exceptional ease of use. It gives manufacturers deeper insights and process understanding, from product development to end-product quality control.


Download a free trial at www.camo.com





Cutting through complex data sets to underlying structures…is simplicity itself.


22 SCIENTIFIC COMPUTING WORLD


www.scientific-computing.com





Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48
Produced with Yudu - www.yudu.com