iSixSigma

Paging Dr Bob, Mike C, Stan, etc…DOE Questions

Six Sigma – iSixSigma Forums Old Forums General Paging Dr Bob, Mike C, Stan, etc…DOE Questions

This topic contains 1 reply, has 2 voices, and was last updated by  Chad Taylor 12 years, 3 months ago.

Viewing 2 posts - 1 through 2 (of 2 total)
  • Author
    Posts
  • #47619

    annon
    Participant

    Are the following conclusions correct regarding blocking in a full or fractional factorial DOE?:

    Blocking nuetralizes the differences between the blocking factor in exchange for a confounding effect with the higher order interaction.
    Blocking provides the investigator with the luxury of exploring a stated noise variable (ie an adding an additional non-interactive pseudo-factor) without adding runs.
    A random blocked design is robust to an unstable process (RA Fisher).
    And how would you define the difference btw a blocking factor and a standard factor of interest?
    Thanks for the time everyone.
     

    0
    #158900

    Chad Taylor
    Participant

    Yes blocking reduces known irrelevant variation which in turn increases the precision in the estimation.
    Yes, but does not have to be a noise variable, can be any variable of like or similar variation.
    Not sure if “Random” would make more robust, seems like a role of the dice.
    I would define a blocking factor as a group of standard factors with similar properties.

    0
Viewing 2 posts - 1 through 2 (of 2 total)

The forum ‘General’ is closed to new topics and replies.