Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • R-squared change statistics (R-squared delta) after using mi impute

    Hello!

    I am using Stata 14.1 on Windows (Citrix, so not sure which version). I am new to stata, but I enjoy learning new things. I have used mi impute to create multiple imputated datasets. I ran mibeta to get information on my models and adjusted R-squared. However, I would like to run a F-test to examine if the changes in R-squared are significant after adding variables to my model. I tried running the example code (after swapping the variable names for my own):
    Code:
    mi estimate: regress y x1 x2 x3 x4 
    mi test x2 x3 x4
    from the mimitest Stata manual but Stata gives an error after running the second part, saying x2 is not found (I double checked, but it gives this message even after copying the var names from the first line of command).

    I also tried running nestreg:
    Code:
    mi estimate, cmdok: nestreg regress y x1 x2 x3
    yet Stata does not accept this (" " found where ':' expected, an error occured hen mi estimate executed nestreg on m=1). I think the mi test command should work and it's a simple fix, but I am not seeing it. Any help is greatly appreciated, as I am stuck.

    Kind regards,
    Elise
Working...
X