Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: some details about gllapred and gllasim

From   Sophia Rabe-Hesketh <[email protected]>
To   [email protected]
Subject   Re: st: some details about gllapred and gllasim
Date   Fri, 10 Oct 2003 14:49:59 +0100

Dear Shige Song,

gllapred is for prediction and gllasim for simulation.

gllasim simulates responses and/or latent variables
from the model using pseudorandom numbers (giving
different results each time, unless you set the 
random number seed). This can be used to generate 
data from a model, for instance to check how close
the estimates for the simulated data are to the truth.

gllapred predicts responses/and or latent variables
(giving the same result each time). Loosely speaking,
a prediction is a 'best guess' of the realization
of a random variable, based on the model and (other)

See for information on these 

Best wishes,


At 11:03 PM 10/9/2003 -0700, you wrote:
>Dear All,
>I am using GLLAMM to do a two-level logisgic model and how tring to plot
>some predicted values using gllapred. I realized there is another progrmam
>called "gllasim", which looks quite similar to what gllapred. Can anyone
>provide more details on what these two commands are designed for and how
>to choose between them? Thanks!
>Shige Song
>Department of Sociology, UCLA
>*   For searches and help try:
*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index