The README should contain some information on how to open the project and build it for a device. After cloning, the project is unable to be run by Android Studio; the README should clarify such.

The documentation in fit_GCOMP() for stratifyQ_by_rule says,

Set to 'TRUE' for stratifying the fit of Q (the outcome model) by rule-followers only.

Does this mean that non-rule-followers are excluded at each time point from the hazard estimate? I don't see separate "stratified" estimates.

Thanks,

For instance, stepwise file input could have a button to remove the filepath (thus passing NULL, i.e. no file selected, if so desired by the user)

A recent email alerted me to this issue. In our datasets the ID is always the first column so this doesn't arise. Using UniqueVariables for the survival and baseline components means it doesn't occur for those. However the longitudinal data has a requirement (implicit) that the ID is first and the sampling (in the bootstrap) fails otherwise. Should be a trivial solve.

Walls and such we can adjust with a different background, to make them stand out from the rest of the tiles. I'm sure we can make more of these kind of improvements on other tiles to make the game more clear to the player where he should go and easier to find the objects he is looking for.