# Design and Test Correlation

Six Sigma – iSixSigma › Forums › General Forums › Methodology › Design and Test Correlation

- This topic has 4 replies, 3 voices, and was last updated 1 year, 7 months ago by Robert Butler.

- AuthorPosts
- June 21, 2018 at 6:57 am #56028

AurelianParticipant@Relufff**Include @Relufff in your post and this person will**

be notified via email.Hello everyone, what is the best tool that could be used to predict most favorable outcome of a test when I have already data collected? I have 5 different inputs and combinations of those give 1 output. 27 data points, 5 inputs and 1 output how can i figure the best combination to provide the best directional output?

Thank you!0June 21, 2018 at 8:13 am #202713

Mike CarnellParticipant@Mike-Carnell**Include @Mike-Carnell in your post and this person will**

be notified via email.@Reluff I get the 5 inputs give you 1 output. The 27 are what?

0June 21, 2018 at 8:37 am #202714

AurelianParticipant@Relufff**Include @Relufff in your post and this person will**

be notified via email.Hi Mike … 27 data points each one has 5 inputs and 1 output. Thanks

0June 25, 2018 at 4:44 am #202730Accoding to my understanding of this problem,

I think multiple linear regression can be helpfull in this case, the equation obtianed by this can be used for prediction.But first you have to ensure that none of your inputs are correlated to each other.if correlation exsits between any two inputs than you have eliminate one by physical reasoning and common sense.0June 26, 2018 at 2:26 pm #202735

Robert ButlerParticipant@rbutler**Include @rbutler in your post and this person will**

be notified via email.So you have 5 different inputs in 27 different experimental combinations, and a single output. What kind of combinations? Is this an experimental design or is it just running 27 WGP’s (Wonder Guess Putter)?

If it is a design then what terms does the design allow you to investigate?

If it is a design then backward elimination linear regression on the terms allowed by the design should get you where you want to go.

If it is a WGP then you will have to determine what terms you can actually include in the model and have them independent of one another before running a regression analysis.

If you have the design matrix (the list of the 27 experiments and the levels of the 5 inputs – no labels or units are necessary) post it on this forum and I’ll take a look at it.0 - AuthorPosts

You must be logged in to reply to this topic.