Comparing fixed PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
 Steven Lancaster posted on Wednesday, November 28, 2018 - 12:07 pm

In the Topic 3 Short Course Video, Part 2, at 7:45 in you state that you can compared the difference between 4.00 and 4.095 and divide by the standard error .042 to determine if 4.095 is different from 4. However, I am not sure what statistic this is. Is difference/SE a t-score or something else?
 Bengt O. Muthen posted on Wednesday, November 28, 2018 - 5:06 pm
It's a z-score assuming that the ratio is approximately normally distributed.
 Steven Lancaster posted on Wednesday, November 28, 2018 - 5:49 pm
OK, that makes sense. However, wouldn´t that be significant then (.095/.042 = 2.26)? Perhaps there is a multiple comparisons correction I am missing? Thanks for the quick reply!!
 Bengt O. Muthen posted on Thursday, November 29, 2018 - 11:03 am
It was a mis-speak - it is indeed significantly different from 4.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message