Vignette Improvement suggestion

[shug0131]

Many thanks for creating rpsftm - great package (wish I had your intelligence).

One thing I would like to suggest, which hopefully helps lesser brained individuals like myself, is that you alter the simulated dataset, immdef, so that there are some censored patients where their censoring occurs because they drop out of the study themselves, not because they reach the study end-date. As it currently stands all patients who are censored have a censoring time, progyrs = censyrs (maximum possible if go right through to end of study). I know this because of the definition of censyrs in the dataset "censoring time, in years, corresponding to the close of study minus the time of entry for each participant".

Understanding the purpose of re-censoring is difficult - my interpretation (which could be wrong) is that for patients who experienced a switch then later drop out of the study themselves but before the study end-date, should have the rpsftm function argument "censor_time" set at the actual censoring time (i.e. progyrs and not censyrs when prog=0) but I am unable to check if my theory is correct by looking at your examples applied to immdef data (given they equal each other). Making the suggested changes to the dataset would allow me to work it out for myself. I actually think it would be worth stating in the vignette explicitly what the case should be in this instance. Can you please put me out of my intellectual misery and let me know if my interpretation is correct?