This DoE 2^k-p is a practice and replicate of the experiment using R software from a article that was run in Minitab in Minitab. But the results I'm finding are not totally the same when I do the regression model using coefficients of linear model.
How did they build this equation regression? If this equation is made using the regression beta coefficients of the T statistic, the values found are different.
Please, access this link for more information, images and code about this question.
https://stats.stackexchange.com/questions/349501/why-these-the-results-in-factorial-2k-experiment-analysis-with-r-are-different-o
Hey Silva,
Please see the link below and I am hopeful it will help you out:
https://newonlinecourses.science.psu.edu/stat503/node/34/
Best of luck
Thanks for the info, Khan,
But note that if the regression model is generated from the information in the T statistic I will not get the same response from the estimated values.
Dear Brenner
When constructing a regression model for a 2^n-k fractional factorial design, usually the regression coefficients beta's are divide by 2, as they are measuring 2-units change (from lower level -1 to upper level +1). So a regression coefficient is actually one-half of corresponding effect estimate.
Regards
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R