+ Reply to Thread
Results 1 to 6 of 6

Thread: ANOVA 2x6 Question

  1. #1
    Points: 2,121, Level: 27
    Level completed: 81%, Points required for next Level: 29

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    ANOVA 2x6 Question




    I'm looking at doing a project where I have participants view images of people with different emotional and facial expressions. I would display the image and time how long it takes to enter a response. The actors in the image would vary in ethinicity (caucasian or hispanic). plus the actors would have 6 different possible emotional expressions (anger, fear, disgust, happiness, sadness, or surprise)

    After looking at my design and methodology, it looks like I would have 2(ethinicity) x 6 (emotional expression) ANOVA.

    What are the drawbacks, of having a 2x6 ANOVA? Correct me if I'm wrong but if I remember correctly each additional factor in an ANOVA increases the error and requires more of an effect to find significance?
    My concern is that with so many factors, one could argue the experiment would never be able to find significance.

    Is there a different way of doing this experiment or analyzing the data that I overlooked?

  2. #2
    Super Moderator
    Points: 20,485, Level: 90
    Level completed: 27%, Points required for next Level: 365
    bugman's Avatar
    Posts
    1,916
    Thanks
    206
    Thanked 243 Times in 195 Posts
    I think you are confusing levels and factors.
    This to me looks like a two way ANOVA:

    2 factors: Ethinicity and Emotion expression with 2 and 6 levels respectivley. Y=response time.

    The model looks fine and should be easy to interpret. Run your overall test then look at pariwise comaprisons - if this is part of the design.

    Phil

  3. #3
    Points: 2,121, Level: 27
    Level completed: 81%, Points required for next Level: 29

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts
    You're right. I was confusing levels with factors.
    Thanks for the reply. This clears things up for me.

  4. #4
    Points: 1,642, Level: 23
    Level completed: 43%, Points required for next Level: 58

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    number of subjects

    How do you know how many subjects you will need to conduct a rigorous experiment with a 2 X 6 factorial design?

  5. #5
    Super Moderator
    Points: 20,485, Level: 90
    Level completed: 27%, Points required for next Level: 365
    bugman's Avatar
    Posts
    1,916
    Thanks
    206
    Thanked 243 Times in 195 Posts

    Talking

    Look at previous studies in the area for an idea of how much variation you can expect and conduct pilot studies.

    Money will often be the deciding factor.
    The earth is round: P<0.05

  6. #6
    Points: 1,642, Level: 23
    Level completed: 43%, Points required for next Level: 58

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Haha, thanks
    This is an actual homework question I have, that for the life of me I cannot find anything about in my textbook. It states:

    For a 2 X 6 factorial design . . . .
    How many independent variables are there? (my answer) 2

    How many dependent variables are there? (my answer) 1 if it's an ANOVA

    *Approximately how many subjects will you need to conduct a rigorous experiment?* (my answer)I have no clue!

+ Reply to Thread

           




Similar Threads

  1. ANOVA -- what is this question asking for?
    By a7890 in forum Statistics
    Replies: 5
    Last Post: 03-18-2011, 11:44 AM
  2. A question about when two way ANOVA is appropriate
    By DanielAurelius in forum Statistics
    Replies: 2
    Last Post: 02-09-2011, 03:03 PM
  3. ANOVA question
    By mrtnduff in forum Statistics
    Replies: 1
    Last Post: 11-25-2010, 11:21 AM
  4. ANOVA Question
    By adi in forum SAS
    Replies: 1
    Last Post: 10-25-2010, 12:41 AM
  5. Question about ANOVA
    By foxer9r in forum Statistics
    Replies: 0
    Last Post: 03-09-2009, 02:09 PM

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