Closed alexadima closed 3 years ago
if I make it "as.numeric" before calculating, it does recognise it. doh! maybe write 'your FUW start variable is not numeric, make it numeric and it will all be OK'. just in case there are other silly people like me?
Fixed: now, timediffs are automatically converted to numbers as appropriate given the time units
when calculating CMA with variable name for days since/before first event
cmasimplu <- CMA9(data=testdata1pat, ID.colname = "CHI", event.date.colname = "DisDate", event.duration.colname = "MinDuration", event.daily.dose.colname = "Min", medication.class.colname = "AdhereRLabel", carry.only.for.same.medication=FALSE, consider.dosage.change=FALSE, followup.window.start= "FUstartdays", followup.window.start.unit = "days", followup.window.duration = 365*2, followup.window.duration.unit = "days", observation.window.start= 0, observation.window.start.unit= "days", observation.window.duration=365, date.format="%Y-%m-%d");
I get warning messages:
Warning messages: 1: In .report.ewms("time.interval to '.add.time.interval.to.date' must be a positive integer.\n", : time.interval to '.add.time.interval.to.date' must be a positive integer.
2: In .report.ewms(paste0("The observation window is not within the follow-up window for participant(s) ", : The observation window is not within the follow-up window for participant(s) 18014359390 !
If I replace the variable name with the actual number of days, it calculates and plots OK.
test dataset in shared private folder