+ Reply to Thread
Results 1 to 3 of 3

Thread: Question about Methodology

  1. #1
    Points: 4, Level: 1
    Level completed: 7%, Points required for next Level: 46

    Posts
    1
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Question about Methodology




    Hi everyone! I'm new here, and wanted some advice on a methodology I'm using for a study of mine. Due to some confidentiality requirements, I can't go into specifics, so I hope you'll bear with me as I explain this in a dessert-themed analogy.

    Let's say I'm studying cake recipes, and I'm looking at several different several different ingredients in a recipe (variables include Eggs, Sugar, Salt, Baking Powder, etc, coded as 0 for absent and 1 for present). There is also a variable for the type of cake being made (cupcake, bundt cake, etc, each coded with a unique number). I also have Success as a variable, with 0 being that the cake did not bake correctly, and 1 being that it did bake correctly. I want to analyze which ingredients most significantly affected outcomes of success. So far I've been using one way ANOVAs for Success with each variable as a factor. Is this correct, or is there a better analysis I could be using? Note that for the ingredient variables, they are not all completely independent of each other (for example, Baking Powder is more effective with Salt as an ingredient).

  2. #2
    Points: 612, Level: 12
    Level completed: 24%, Points required for next Level: 38

    Posts
    17
    Thanks
    2
    Thanked 3 Times in 3 Posts

    Re: Question about Methodology

    Hei

    Since you're working with binary data, it would be more suitable to use logistic regression or discriminant function analysis. An ANOVA is used for continuous data.
    Hope that helps a bit

  3. #3
    Omega Contributor
    Points: 38,253, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    6,989
    Thanks
    397
    Thanked 1,185 Times in 1,146 Posts

    Re: Question about Methodology


    If variables are associated with each other (correlated), you may also want to examine Variance inflation Factors (VIF).
    Stop cowardice, ban guns!

+ Reply to Thread

           




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