Hello everyone, I have a dataset where each patient (represented by ID) is prescribed a medication (represented by dose) over different time periods. Here is an example of my data, where for particular purposes each patient does not have a fixed dose on each day: id date dose 1 1/17/2008 7.5 … … … 1 2/5/2008 8 1 5/7/2008 5 … … … 1 6/15/2008 7 2 2/2/2008 10 … … … 2 3/17/2008 10 … … … I also have another dataset of patients experiencing events (i.e., hospital readmission) at different times. Here is an example: id date1 date2 date3 date4 date5 … date20 1 2/20/2008 4/17/2008 … … … … … 2 4/27/2008 6/7/2008 9/11/2008 … … … … … where each patient might experience different number of events, and the maximum number of events occurred for any patient in my database is 20 (that's why I have "data20" as my last variable in the second table). Now, for each patient, I want to measure the average dose used between each two consecutive events. Here are a couple of points: The average is measured by taking the cumulative dose in that period and dividing it by the total number of days in that period. If an event occurs for the first time, then two conditions may happen: whether the event occurs before or after the time of the first dose. For the former, the average dose in that period will be 0. For the latter, the average will be measured from the time of the first dose until that event. It's possible that, for a patient, no event occurs. In this case, I take the average for the period between the first and last dose. Finally, I'd be very thankful if the code can accommodate reading two separate data files (like the tables above). Thank you very much in advance!
... View more
