+ Reply to Thread
Results 1 to 4 of 4

Thread: Factors and Responses

  1. #1
    Points: 3,112, Level: 34
    Level completed: 42%, Points required for next Level: 88

    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Factors and Responses



    I am trying to find the factors and responses in the following statement but am having some trouble deciphering it:

    "You wish to investigate the corrosion rate of copper. You want to test hard and soft tempered copper in two different alloys for exposure to the following natural gas contaminants: H2S, Mercaptan, O2, and CO2."

    I was thinking that there might be 8 factors, the gases and the temper and alloys but I am not quite sure. I was also thinking that the response was the corrosion rate of copper.

    Thanks

  2. #2
    TS Contributor
    Points: 13,042, Level: 74
    Level completed: 48%, Points required for next Level: 208
    Awards:
    User with most referrers
    JohnM's Avatar
    Posts
    1,948
    Thanks
    0
    Thanked 4 Times in 4 Posts
    Yes, the response is corrosion rate.

    There are 3 factors:

    temper (hard, soft)
    alloy (1, 2)
    gas contaminant (H2S, Merc, O2, CO2)

    In a full factorial design, there would be 2 x 2 x 4 = 16 treatment combinations.

  3. #3
    Points: 3,112, Level: 34
    Level completed: 42%, Points required for next Level: 88

    Posts
    6
    Thanks
    0
    Thanked 0 Times in 0 Posts
    Great thanks, makes much more sense now, I was only thinking of 2 factor levels. Just curious, I know that with 3 factor levels the coded levels are -1,0,1 but how would you start the set up of four factor levels in a coded table?

  4. #4
    TS Contributor
    Points: 13,042, Level: 74
    Level completed: 48%, Points required for next Level: 208
    Awards:
    User with most referrers
    JohnM's Avatar
    Posts
    1,948
    Thanks
    0
    Thanked 4 Times in 4 Posts

    Never really bothered with coding issues, but this page shows dummy and effect coding for a 4-level factor:

    http://www.gseis.ucla.edu/courses/ed...s1/orthog.html

+ Reply to Thread

Similar Threads

  1. How to measure coherence of responses on surveys
    By greg.neyman in forum Psychology Statistics
    Replies: 3
    Last Post: 03-07-2011, 05:50 AM
  2. Replies: 1
    Last Post: 11-04-2010, 01:00 AM
  3. multiple groups & dichotomous responses
    By pjotr66 in forum Statistical Research
    Replies: 8
    Last Post: 07-16-2010, 10:29 AM
  4. Chi square ok for questionnaire responses?
    By BJ82 in forum Statistics
    Replies: 2
    Last Post: 04-03-2009, 03:04 PM
  5. Likert scale. can i sum the responses?
    By frekenSnork in forum Statistics
    Replies: 2
    Last Post: 05-07-2008, 05:12 AM

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts








Advertise on Talk Stats