|
|
Confidence intervals of estimates |
|
Message/Author |
|
Anonymous posted on Saturday, December 08, 2012 - 12:50 am
|
|
|
Supposing I fit a logistic regression with two continuous explanatory variables, X and Y. From this I can estimate logit(p) for any given values of X and Y. I now wish to obtain a 95% confidence interval for the estimated value of logit(p). Can I do this in Mplus? |
|
|
You can use MODEL CONSTRAINT to create a new parameter logit = b1*x + b2*y and substitute whichever values you want for x and y. You can use the standard error you obtain to create a confidence interval. |
|
Back to top |
|
|