Mathematically it would if be a conditional function, so if you are testing if something is greater than:

if Ha > Ho: “two-tailed p-value” * 2 = “one-tailed p-value”

else: 1 – (“two-tailed p-value”*2) = “one-tailed p-value”

There is probably a flag to do this in Stata, but I don’t know it offhand.

]]>I am pretty sure you are talking about a model to say why a particular row belongs to a latent group. Check out the “Time-Stable Covariates” section in this document, https://ssrc.indiana.edu/doc/wimdocs/2013-03-29_nagin_trajectory_stata-plugin-info.pdf.

You put in your early risk factors into the “risk(x1 x2 )” part of the function.

]]>Thanks! The html monster did eat whatever you were trying to share, but I saw the setAxisMargin lines in your template file, so I can riff on those — perhaps mine needs some combination of axis characteristics other than the obvious one (categorical FALSE role Y) — I’ll try popping some other lines in as well.

I’ve tried different positions, nothing changed, but I’ll pop the new set to the top just in case.

Again, thanks!

]]>Somenthing Else! I already have my trajectories (wheezing trajectories) and also the posterior probabilities of assignment for each group. Now I want to investigate the associations of these trajectories with early risk factors using multinomial logistic regression. However I would like to weight these analyses with the posterior probabilities. It seems that researches are doing this as a way to “account” for uncertainty of assignment. Just to be more “accurate”. It seems that is possible to do it, cause I’ve read it in a paper, but I couldnt find a way to include the weights in the regression! Thank you so much!

]]>If you got that far not sure if I can give much helpful advice. (I have also found all sorts of things do not behave as expected, and sometimes change behavior in different versions.)

My tags for that look like (hopefully HTML does not eat it):

and a bunch of those tags for different categorical true/false and role (x,y,x2,y2). It is also specified at the beginning of my sgt file (some things seem to take precedence if they are specified in different order in the sgt file, so experiment with the order).

About the only other piece of advice I can think to give is that I am not 100% sure of what is exactly cut off in your chart. For long labels you can sometimes insert line breaks into the string via “\n”, so it may be the best solution is to script up something to prevent really long strings for labels here, and not worry about putzing with the finicky sgt file.

]]>Not 100% sure what you mean — you mean you want to predict the probability of belonging to a latent class based on time-invariant characteristics? (Or something else?)

]]>I am having a weird issue with the setAxisMargin tag in my sgt files — it doesn’t seem to do anything!

I have been trying to modify the margin for my clustered horizontal bar charts, but no change I make to the XML setting seems to have any effect on the output. Consequently, the value labels (positioned positive/outside) are sometimes lopped off on the longest data bar in a chart.

Any thoughts? I really don’t relish modifying the margins by hand for every chart of this type.

]]>I want to use weighted multinomial logistic regression (weights based on posterior probabilities). I know it has been done with latent class analysis which gives you the probabilities at an individual level. Do you know how I can do it with GBTM? I haven’t found the commands in Stata, so I have no idea how to include the weights in the regression! Thank you very much for your attention and shared knowledge

]]>