To your second point – you could certainly do that – essentially run star points of the design after running the factorial and the center. I strongly suspect that the results of the analysis will cause all concerned to loose interest in further replication and focus instead on model confirmation and process optimization. Once the results the design + one or two are in – analyze your data. DEGREES OF FREEDOME FULLYour strategy will be to first run a complete design and then pick one or two of the design points from the full replicate and run these. If you are uncomfortable with this idea then I’d recommend planning your experimental effort to budget for a single full replicate of the design. What this means is that all of the degrees of freedom associated with factors that aren’t significant get rolled into the final estimate of error for the study and the end result is a estimate of error with a reasonable number of degrees of freedom. While I can’t say this will never happen I can say I have never seen anything remotely resembling this situation. tests significant then you may want to worry about the number of degrees of freedom you have planned to allot to your error. I suppose if you have a situation where every single term in the design – mains, 2 way, 3 way, curvilinear, etc. To your first point you have to ask yourself the following: What is the purpose of your DOE? Are you running a design so you can get a great estimate of experimental error or are you running a design so you can identify those variables that are having a major impact on your process? With additional work you could get some estimate of the magnitude and direction of the variables effect on the outcome of interest but why bother with all of the extra work when regression will give that information to begin with? One could use ANOVA to analyze a design but this would only tell you that a variable was significant. In my experience a replication of one or two experiments in the design is all that is needed for an acceptable research effort.Īll of the work I’ve done with DOE has had as its focus the development of a predictive equation so the method of analysis has been regression. This gives you replication on the center, allows you to estimate and examine all of the mains, two way and the three way interaction, gives you an error estimate, and allows a check for possible curvilinear behavior. If all of the variables are continuous and if you have the time and money to spare my preference, in this case, would be to run two center points. A single replication of a single run – for a total of 9 runs will give you the estimate of the error term. I’ve had to do this in the past but it is not my preference. If you are really pressed for time and money you can run the single design without replicates and use the estimate of the 3 way for your error. Which one you use will depend on time/cost/efficiency constraints.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |