V12N2-2

factor at a time, run the experiment, observe the results, and move on to the next factor. This approach has several shortcomings.

This approach takes much longer and uses up
more resources.
The optimum combination of all variables may
never be revealed
The interaction between factors may never be
revealed.

By using statistically designed experiments we can achieve the following benefits;

Many factors can be examined simultaneously

Some input factors which cannot be controlled,
which are called noise factors, can influence the
output, however other input factors can then be
controlled to reduce the effect of this noise.
In depth statistical knowledge is not necessary to perform these tests and reap their benefits.
Relatively few experiments can look at a large number of factors and separate the trivial from the important.
Quality and reliability can be improved without increasing cost in most cases.

Experimental design was developed in England and the US many years ago however, it was aimed at statisticians and engineers were not exposed to it until a Japanese engineer by the name of Genichi Taguchi took the method and adapted it for use by Japan's engineering community. In the 1980's as Japan was fast becoming a world economic leader, American's noticed the Japanese using a powerful new tool. It was referred to as the Taguchi method. Taguchi published a book on the subject in 1987.

2 of 16