+ Reply to Thread
Results 1 to 2 of 2

Thread: How to combine more datasets

  1. #1
    Points: 7, Level: 1
    Level completed: 13%, Points required for next Level: 43

    Thanked 0 Times in 0 Posts

    How to combine more datasets

    Hi everyone,
    I’m quite sorry for this very “beginner question” , but I’m stuck on it from several days.
    I got three experimental groups, four animals in each group and for each animals, I measure the length of 30 neurons. Obviously, I want to know if there is a difference between my three groups in term of neuronal length.
    But I don’t know how to handle my datasets:
    do I have to pull together the lengths from all the animals that belong to the same group or is better if I keep them separated? I have already checked the intra-group variability and I didn’t find any intragrups differences.
    Thanks in advance for any help.

  2. #2
    Points: 2,462, Level: 30
    Level completed: 8%, Points required for next Level: 138

    Thanked 48 Times in 43 Posts

    Re: How to combine more datasets

    Hi, your data are nested. Especially, neurons are nested within animal ID. Usually, lengths from the same animal are more similar compared to lengths between animals. If you want do include this design within a statistical test, you have to use a repeated-measures-ANOVA, where the group is the fixed effect predictor and the animal-ID is the random coefficient, because you have repeated measurements within each animal. An alternative to a rm-ANOVA is a linear mixed model. Also here, the group is the fixed effect predictor and the animal-ID the random coefficient.

    Don't put all the data from one group together without including the animal-ID as a repeated measure, in this case you violate the assumption of independene and your p-values are biased

+ 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