With experimental design you can get the information you need with minimal effort. You reduce development costs and save time by testing multiple combinations at the same time.

Good design and proper analysis will help you decide optimal solutions. DOE can be used both when developing new products and when improving existing ones.

Significant resources can be saved by designing efficient design of experiments. Lean Tech has experienced that 1100 trials could be reduced to 150 trials, revealing the same result. If you start with a few trials based on your assumptions, you can always increase the number of tests based on your experience. However, there is no need to start with too many tests.

Lean Tech can help you design DOE and analyze the result or you can learn it yourself by joining DOE training. You need a statistical tool like JMP, Minitab or SigmaXL

When the level of a factor is random, such as raw material batch, reactor, instrument, operator, day, etc., Analysis of Variance (ANOVA) / Components of Variance is more applicable than design of experiment (DOE).

While the levels of a DOE are controlled, ANOVA determine how much various factors contribute to the overall variation based on their natural variation. In a DOE the level setting of a factor tends to be more extreme to decide the effect of a factor.

ANOVA can be used to develop new products and to improve existing ones. ANOVA can help you decide; How much do different factors like raw materials, reactors, machines and instruments contribute to variation of product quality? How is the within batch variation compared to the between batch variation?

Follow the link to see example of ANOVA for weight measurements. How much variation is due do measurement error and variation within a day?

Lean Tech arranges ANOVA training based on request and helps you with design and analysis if needed.