How to extract random slope and intercept for analysis? Growth curve model

[Shuping Lim]

Hi everyone,

I am currently evaluating the sex differences in the trajectory of depression over time measured at 3 timepoints with non-linear model. I've converted my data to the long format. Here is my syntax:

mixed depression sex age age2 || subjectid: age age2, covariance(unstructured) mle

age: the age at which depression symptoms were measured
age2: is squared of age

I then entered:

predict traj, fitted

to predict individual-specific trajectories of depression with the individual intercept and slopes. However, I would like to see if maternal depression measured prenatally is associated with individual slopes. Can anyone please give advice on how I can do that on STATA?

Thank you!

[Joseph Coveney]

I am currently evaluating the sex differences in the trajectory of depression over time measured at 3 timepoints . . .

mixed depression sex age age2 || subjectid: age age2, covariance(unstructured) mle

age: the age at which depression symptoms were measured

. . . I would like to see if maternal depression measured prenatally is associated with individual slopes.

So is sex the sex of the parent (i.e., father, mother) and age is gestational age, or what? What are we looking at here?

Anyway, to get at your objective and assuming that that's what the variables are (and that the mother is coded sex = 1 and father coded as sex = 0), you could try something like the following (untested inasmuch as there are no data to work with).

mixed depression i.sex##c.age##c.age || subjectid: c.age##c.age, covariance(unstructured) mle
predict double xbu, fitted
graph twoway line xbu age if sex, lcolor(black) ylabel( , angle(horizontal) nogrid) ///
    scheme(s2color) by(subjectid)

[Shuping Lim]

Hi Joseph,

These are the variables for my study:

1. Depression_age9 (continuous variable)
2. Depression_age10 (continuous variable)
3. Depression_age13 (continuous variable)
4. Sex
5. Prenatal maternal mood

Thank you for your quick reply. Sorry I wasn't very clear in my post. The purpose of my study is to examine if prenatal maternal mood predicts the trajectory of child depressive symptoms from age 9 to 13, hence I want to use the depression variables measured across the 3 timepoints to model a growth curve for each sex. Looking at the mean of the depression scores of each timepoints, the depression scores are lowest at the second time point, so I want to do a non-linear growth curve model for my analysis. How can I extract the rate of change in trajectory for each participant on STATA? I want to do a regression analysis to see if prenatal maternal mood is associated with the variability in the rate of change in depression across the 3 timepoints.

Thank you for taking time to reply, I am still new to growth curve modelling, greatly appreciate it!