+ Reply to Thread
Results 1 to 2 of 2

Thread: what is the best test

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

    Thanked 0 Times in 0 Posts

    what is the best test


    I'm not the best at statistics. I understand the theory but I am still uncertain about choosing the appropriate test.

    I am doing a study on antibiotic cure rates for a disease in cows. I wanted to see if there is an association between the colony number and the outcome (success to the treatment or not). I have put the colonies in categories: 1 if its 19 colonies or less and 2 if its 20 or more colonies. My outcomes are either 0 (success) or 1 (disease). I am comparing two variables to see if there is an association. I was thinking t-test but that calculates the difference between means and since I have categories and not continuous data I dont feel like this would give me much. The chi2 goodness of fit measures proportions, so I feel like that too isn't good for me. Can I use ANOVA?

    QUESTION: what test will show me if there is an association between my two groups?

  2. #2
    TS Contributor
    Points: 12,227, Level: 72
    Level completed: 45%, Points required for next Level: 223
    rogojel's Avatar
    I work in Europe, live in Hungary
    Thanked 332 Times in 312 Posts

    Re: what is the best test

    I would keep the colony numbers . Do you have a single outcome ( like succes or failure) per colony or do you have more detailed information (like percentage cured)? Some type of regression seems to me to be the right tool, either logistic or simple.


+ 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