Follow up on: Group-Based Multi-Trajectory Modeling with lcmm Package #119

CecileProust-Lima / lcmm

R package lcmm

https://CecileProust-Lima.github.io/lcmm/

54 stars 13 forks source link

Follow up on: Group-Based Multi-Trajectory Modeling with lcmm Package #119 #240

Closed zyddmn closed 7 months ago

zyddmn commented 7 months ago

Hi! I have the same question when using this package for multi-trajectory modeling. When I use mpjlcmm for my outcomes with no survival part in the model, a warning will pop out: "No time-dependant variable should appear in survival nor in classmb". The code I use looks like this: mms1 <- mpjlcmm(longitudinal = list(mcrp1, mfac1), subject = "ID", ng = 1, data = df_long_new)

VivianePhilipps commented 7 months ago

Hi,

sorry, I can't answer this issue without more details. Does a similar example with the paquid data work? If you have a reproducible code, this would help. Please make sure that :

you are using the latest lcmm version (commit [14af85a])
your data are stored in a data frame (not a tibble)
your subject variable is numeric (These are the usual reasons why lcmm fails...)

Viviane