Modeling with Time-Varying Covariates PreviousNext
Mplus Discussion > Growth Modeling of Longitudinal Data >
Message/Author
 Bengt O. Muthen posted on Tuesday, August 05, 2008 - 3:04 pm
This exercise considers growth in mathematics achievement over grades 7, 8, 9, and 10 in U.S. public schools for a sample of 3,102 students. The data are from the Longitudinal Study of American Youth (LSAY). The data structure is multilevel with students clustered within schools, but for the purpose of this assignment this complication can be ignored.

The research question is how the time-varying covariate of math course taking influences the math achievement growth. The variables in the attached LSAY data set are shown in the attached Mplus input for a BASIC analysis. Here, the math course taking variable is labeled mthcrs7-mthcrs10 and is recorded as follows:

mthcrs7-mthcrs12 = Highest math course taken during each grade
! (0 = no course, 1 = low, basic, 2 = average, 3 = high,
! 4 = pre-algebra, 5 = algebra I, 6 = geometry,
! 7 = algebra II, 8 = pre-calc, 9 = calculus)

For simplicity, this variable may be treated as continuous.

The exercise consists of using Mplus to find a good time-varying covariate growth model by exploring conventional approaches with fixed and random coefficients, as well as innovative alternatives. Individuals with little Mplus growth modeling experience may consult chapter 6 of the Mplus Version 5 User’s Guide (see www.statmodel.com).

Although it is not possible for the Mplus team to look at individual solutions, the Mplus course at Johns Hopkins University on Thursday August 21, 2008 will present several solutions for this exercise.


Bengt Muthen
 Scott Smith posted on Friday, October 18, 2013 - 1:13 pm
Hello,

I am trying to model a growth curve model with a count dependent variable. I have four waves of data but I am using an accelerated cohort design. I already have my data wide. I want to use both time-varying and time-invariant covariates. I used example 6.10 as a guide. If I only have the time-invariant variable in the model (i.e. gender) the model will run. When I start to add the time-varying covariates (i.e. drug use at each time point) I get the following message:


*** ERROR
There is at least one count variable that has only one unique value.
Please check your data and format statement.
*** ERROR
One or more variables in the data set have no non-missing values.
Check your data and format statement.

This is my syntax


model:
i s| dv16@0 dv17@1 dv18@2 dv19@3 dv20@4 dv21@5 dv22@6 dv23@7;
i s ON female;
dv16 ON drugs16 ;
dv17 ON drugs17 ;
dv18 ON drugs18 ;
dv19 ON drugs19 ;
dv20 ON drugs20 ;
dv21 ON drugs21 ;
dv22 ON drugs22 ;
dv23 ON drugs23 ;

Thank you for any advice can give me.
 Bengt O. Muthen posted on Friday, October 18, 2013 - 8:52 pm
Perhaps you have a lot of missing data on drugs16-drugs23. If this is the cause of your problem and the missingness causes missing also on the corresponding dv's, we can give you a solution.
 Scott Smith posted on Saturday, October 19, 2013 - 9:08 am
I believe you are right because I am using an accelerated cohort design. What would you suggest I do to help with the missing data? I really appreciate any advice.
 Bengt O. Muthen posted on Saturday, October 19, 2013 - 3:33 pm
Don't use a missing data flag for the time-varying covariates; use some other number. If the tvs is missing at time t and the outcome at the corresponding time is missing, such timepoints still won't contribute to the likelihood computations. By not using a missing data flag, you avoid deleting subjects who have missing on any tvcs.
 Scott Smith posted on Saturday, October 19, 2013 - 5:12 pm
That makes sense. I will give it a try. Thank you for your timely feedback.
 ZHANG Liang posted on Monday, March 09, 2015 - 6:04 am
I have the same question, and

Then what should I do with the missing values on TVCs? Should I just leave them as blanks in .dat file while missing values on other variables are represented as missing data flag?
 Bengt O. Muthen posted on Monday, March 09, 2015 - 6:08 pm
Just use some other value like 888 instead of 999.
 ZHANG Liang posted on Friday, March 13, 2015 - 4:45 am
Dear professors:

I think I know well how latent growth modeling with TVC works, but I'm not sure how to interpret its meaning properly in research papers.

As the first post of this thread said, the research question is "how the time-varying covariate of math course taking influences the math achievement growth". Suppose that at each time point, course taking affect math achievement positively, how should I answer the research question? I don't think just say "time-varying course taking influence growth of math achievement positively" is enough. Can you propose an interpretation more in detail that can reflect some of the rationale of this model?

And, can I understand TVC model as an extension of LGM by adding TVCs as predictors of growth besides calendar time (i.e., growth is joint function of both time and tvc)? Or,the term "growth" has to be a function of time exclusively, and TVC is just a correlate of growth?

Thx!
 Bengt O. Muthen posted on Friday, March 13, 2015 - 8:34 am
This general question is more suited for SEMNET.
 nidhi gupta posted on Wednesday, March 08, 2017 - 4:52 am
Hi
I am also using latent growth modelling to model accelerometer-data on each weekday and this is my model

Model: %OVERALL%
i s | t1@0 t2@1 t3@2 t4@3 ;

When i do this i get this error

*** ERROR
One or more variables in the data set have no non-missing values.
Check your data and format statement.

Continuous Number of
Variable Observations Variance

**T1 0
**T2 0
**T3 0
**T4 0
I replaced missings with the number 8888 but it still does not help.
Could somebody help?
 Linda K. Muthen posted on Wednesday, March 08, 2017 - 8:13 am
Some observations having missing values on all analysis variables. These are eliminated from the analysis. If you can't see the issue, send the data, output, and your license number to support@statmodel.com.
 Emma C Burns  posted on Monday, October 02, 2017 - 9:18 pm
For LGM with TVCs, is it possible to examine a factor (for example self-efficacy) as both a time variant and time invariant factor within a single model? By this I mean T1 self-efficacy can be used as both a predictor of the intercept and slope, but also as a direct predictor of the T1 outcome factor. The model converges, but I don't know if this makes theoretical sense.
 Bengt O. Muthen posted on Tuesday, October 03, 2017 - 11:48 am
I think it makes sense - you are not stating that the self-eff influences the factors at all time points - which would not be identified beyond its influence on intercept and slope - but influences the T1 outcome factor beyond the influence that goes through intercept and slope.
 Hillary Gorin posted on Wednesday, April 10, 2019 - 7:09 pm
Hello,

I tested whether or not I had time varying covariates in a growth curve model in Mplus. In the model, I examined change in maladaptive parenting over 3, 4, and 5 years of age.

I wanted to control for SES so I tested whether or not SES was a time varying or time invariant covariate by comparing a model with SES unconstrained vs the model with SES constrained over 3, 4, and 5 years. Syntax for constraining SES (setting it to equal) was as follows:

Parenting3years on SES(C);
Parenting4years on SES(C);
Parenting5years on SES(C);


When I did so, the chi-square difference test was not significant, suggesting that the time varying covariate and time invariant covariate were not significantly different. Thus, I do not need to constrain SES to equal over 3, 4, and 5 years, correct?

In other words, I can use the following syntax in my growth curve model?
Parenting3years on SES;
Parenting4years on SES;
Parenting5years on SES;

Thanks!
Hillary
 Hillary Gorin posted on Wednesday, April 10, 2019 - 11:36 pm
Also, if I made an error here, would it drastically alter my findings? Could I justify that it will not be significantly different either way?
 Bengt O. Muthen posted on Thursday, April 11, 2019 - 10:27 am
This general analysis strategy question is suited for SEMNET.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: