StepIII_stepwise function

Step III: Stepwise on the consolidated output from different GDS runs

Runs the stepwise regression on the output received from top models of the consolidated output of different GDS runs. With n being the number of runs, the stepwise regression starts with at most (n-3) selected effects from the previous step. The remaining effects from the previous step as well as all main effects are given a chance to enter into the model using the forward-backward stepwise regression.

Source

Singh, R. and Stufken, J. (2022). Factor selection in screening experiments by aggregation over random models, 1--31. tools:::Rd_expr_doi("10.48550/arXiv.2205.13497")

StepIII_stepwise(
  xstart,
  xremain,
  Xmain,
  Xint,
  Y,
  cri.penter = 0.01,
  cri.premove = 0.05,
  opt.heredity = "none"
)

Arguments

• xstart: a vector with effects' names corresponding to the starting model.
• xremain: a vector with effects' names corresponding to the remaining main effects and other effects that needs to be explored with stepwise regression.
• Xmain: a $n x m$ matrix of m main effects.
• Xint: a matrix of m choose 2 two-factor interactions.
• Y: a vector of n responses.
• cri.penter: the p-value cutoff for the most significant effect to enter into the stepwise regression model
• cri.premove: the p-value cutoff for the least significant effect to exit from the stepwise regression model
• opt.heredity: a string with either none, or weak, or strong. Denotes whether the effect-heredity (weak or strong) should be embedded in GDS-ARM. The default value is none as suggested in Singh and Stufken (2022).

Returns

A list returning the selected effects as well as the corresponding important factors.