+ Reply to Thread
Results 1 to 5 of 5

Thread: Data Extrapolation for SEM

  1. #1
    Points: 70, Level: 1
    Level completed: 40%, Points required for next Level: 30

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Data Extrapolation for SEM




    Hi,
    I have a data of n=50. Is there any way in which I can extrapolate or simulate the data to n=2000, in order to carry out Structural equation modelling.

  2. #2
    Omega Contributor
    Points: 38,413, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,004
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Data Extrapolation for SEM

    Was your n=50 a random sample? You can do anything, the results are just limited. How many variables of interest are there?
    Stop cowardice, ban guns!

  3. #3
    Points: 2,462, Level: 30
    Level completed: 8%, Points required for next Level: 138

    Posts
    200
    Thanks
    20
    Thanked 48 Times in 43 Posts

    Re: Data Extrapolation for SEM

    Hi, in principle you can create a bigger sample by resampling these data based on Monte-Carlo simulations (drawing with replacement). But I can't imagine that the new data either increase stability/convergence or precision of the method, because you actually do not add additional information...
    Last edited by mmercker; 08-17-2016 at 07:57 AM.

  4. #4
    TS Contributor
    Points: 22,448, Level: 93
    Level completed: 10%, Points required for next Level: 902
    spunky's Avatar
    Location
    vancouver, canada
    Posts
    2,137
    Thanks
    166
    Thanked 537 Times in 431 Posts

    Re: Data Extrapolation for SEM

    No. n=50 is simply too small to do anything Structural Equation Modelling related. You'll simply need to choose another method, unless you find yourself in the incredibly good position of knowing the data-generation mechanism in which case you could simulate from it.

    But then again, if you knew it, you wouldn't need to do any modeling.
    for all your psychometric needs! https://psychometroscar.wordpress.com/about/

  5. #5
    Points: 70, Level: 1
    Level completed: 40%, Points required for next Level: 30

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Data Extrapolation for SEM


    Quote Originally Posted by hlsmith View Post
    Was your n=50 a random sample? You can do anything, the results are just limited. How many variables of interest are there?
    I thank you very much for your earlier reply.

    Let me add some points for better clarification
    1. the sample is random with the assumption of normality
    2. there are 5 variables and I would like to see the interaction among these 5 variables.

    Looking for your reply. Thanks in anticipation

+ 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