Message/Author |
|
|
Hello, I am running path analysis, and in the output Mplus automatically run with statements among endogenous variables. Is it common? And what does covariance among endogenous variables mean? I think it means residual covariance among the variables, but I am not sure how to interpret it (or what is difference from covariance among endogenous variables). model: y1 y2 y3 y4 on x1 x2 x3; In the output,there were results of y1 with y2 y3 y4 y2 with y3 y4 y3 with y4 And they were all significant,and much improved the model. Thanks. |
|
|
The Mplus default is to estimate residual covariances for dependent variables that do not influence any other variable. Without these residual covariances, the model would most likely be misspecified because these residuals are most often correlated in practice.. See Chapter 13 of the Mplus User's Guide for a full description of the Mplus defaults. |
|
Dana Wood posted on Friday, January 23, 2009 - 9:59 am
|
|
|
Hi! Is there any way to get Mplus to provide the variance for the intercept term in multiple regression models? Thank you! |
|
|
Standard errors are given for all parameters. They are in the second column of the output. |
|
Dana Wood posted on Thursday, February 12, 2009 - 10:40 am
|
|
|
Thanks for your response! I actually needed the variance out to many more decimal places than can is provided in the regular output. I was able to obtain this using TECH3. |
|
|
TECH3 does not contain parameters estimates and their standard errors. It contains covariance and correlation matrices of the parameter estimates. If you want more decimals for the results, you can obtain them using the RESULTS option of the SAVEDATA command. |
|
Back to top |