+ Reply to Thread
Results 1 to 2 of 2

Thread: Interpretation histogram - normal versus logged variable

  1. #1
    Points: 839, Level: 15
    Level completed: 39%, Points required for next Level: 61

    Thanked 0 Times in 0 Posts

    Interpretation histogram - normal versus logged variable

    For the histogram of my variable 'ambidexterity,' I predicted the data to have something like two normal distributions for this variable, one at the left side of the variable series, with lower values, and one at the right side, with higher values, and in between those two distributions low or no values at all.

    If I look at the distribution of the values of 'ambidexterity,' the data is positively skewed. However, there is on the left side (compared to the one on the right) a huge distribution of ambidexterity values, and a very small one on the right.

    Since the data is positively skewed, I also made a histogram of the logged values of 'ambidexterity.' Maybe not surprisingly at all, but the small distribution on the right is completely absorbed in the newly normal distribution of the logged values.

    Enclosed you can find the two histograms.

    My question is, how can I know whether there are two distributions for this variable, or just one? (E.g. Which histogram is appropriate in this scenario, or is there maybe a statistical test for it?)

    Thanks a lot
    Attached Files

  2. #2
    Omega Contributor
    Points: 38,432, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Not Ames, IA
    Thanked 1,186 Times in 1,147 Posts

    Re: Interpretation histogram - normal versus logged variable

    What is your hypothesis for the cause of the two distributions? Can you just stratify on that to show the two distributions seperated out?
    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