304-305 / 1676
•
Disadvantages:
–
Correct identification of patients (retrospective)
•
Incorrect recording
•
Missing data
–
Assessment of outcome:
•
Straightforward endpoints → e.g. survival
–
Missing data
•
Difficult retrospective endpoints:
–
Functional status (e.g. performance status): “is OK”
–
Toxicity
–
Limited numbers (low power)
20
Retrospective cohort study