pg_0163

Process Improvement

5.4.

Analysis of DOE data

5.4.5.

How to interpret DOE results

Final model

used to

make

conclusions

and

decisions

Assume that you have a final model that has passed all the relevant tests

(visual and quantitative) and you are ready to make conclusions and

decisions. These should be responses to the questions or outputs

dictated by the original experimental goals.

Checklist relating DOE conclusions or outputs to experimental

goals or experimental purpose:

A checklist

of how to

compare

DOE results

to the

experimental

goals

Do the responses differ significantly over the factor levels.

(comparative experiment goal)

Which are the significant effects or terms in the final model.

(screening experiment goal)

What is the model for estimating responses.

Full factorial case (main effects plus significant

interactions)

Fractional factorial case (main effects plus significant

interactions that are not confounded with other possibly

real effects)

RSM case (allowing for quadratic or possibly cubic

models, if needed)

What responses are predicted and how can responses be

optimized. (RSM goal)

Contour plots

JMP prediction profiler

(or other software aids)

Settings for confirmation runs and prediction intervals for

results

5.4.5. How to interpret DOE results

http://www.itl.nist.gov/div898/handbook/pri/section4/pri45.htm [5/7/2002 4:02:07 PM]