header image
Home arrow Tutorial arrow Introduction to Statistical Experimental Design
Introduction to Statistical Experimental Design PDF Print E-mail
Written by Johan Trygg   
Saturday, 02 September 2006
How shall I find the optimum? This is a common question everywhere in business. In research and development, often half of the resources are spent on solving optimization problems. With the rapidly rising costs of making experiments, it is essential that the optimization is done with as few experiments as possible. This is one important reason why statistical experimental design is needed. DoE originated in the 1920's by a British scientist, Sir R. A. Fisher, as a method to maximize the knowledge gained from experimental data and it has evolved over the last 70 years. Most experimentation involves several factors and are conducted in order to optimize processes and or investigate and understand the relationships between the factors and the characteristics of the process (reponses) of interest.

 
 
Last Updated ( Friday, 29 September 2006 )
< Prev   Next >
Search website

Editorial flash
Svante Wold's New Year Editorial 2004
The year 2003 has passed amazingly fast - I feel it was yesterday that I was struggling with last years New Year editorial. But actually the world has moved one year forward, and we now write January 2004. Chemometrics has had another good year with exciting and enjoyable conferences at, among others, Åland and Lisbon, displaying improved methodology, and interesting applications.
Read more...
News flash
Metabolomics 2010 meeting

www.metabolomics2010.com

June 27- July 1, 2010

Amsterdam, The Netherlands

Last chance for Abstract submission for ORAL presentations !!

The deadline for submitting abstracts for oral presentations is approaching rapidly! You have until Friday 23rd April.
We encourtage you all to submit your proposed contributions by then. After this date you can however still send in abstracts for posters.
As we have a limited space for just 400 posters we encourage everyone to submit their abstracts as soon as possible in order not to miss out.

To register and send in your abstracts for talks and posters click here

The Local Organisers

Thomas Hankemeier and Robert Hall

 

 
Tutorial flash
Model control of mathematical models
In the applied work with data we often formulate a mathematical model that is expected to be appropriate to the model. Data is used to estimate the unknown parameters in the model. The situation considered here is the case of regression analysis, where there are available data for the instrumental variables and the associated response values.
Read more...