Bioequivalence and Bioavailability Forum

Missing values [Study Per­for­mance]

posted by Helmut  – Vienna, Austria, 2008-04-02 16:54 (6245 d 08:58 ago) – Posting: # 1751
Views: 17,392

Dear Ratnakar,

I think your approach is reasonable, but consider also:

• Giving reasons for exclusion in the statistical report in order to keep transparency of decisions.
  
• In the region of C_max even one missing data point may ruin the study!
  
• If missing data points are scattered throughout the profile in uncritical regions, why not allow for >2?
  
• Data imputation by interpolation (linear in the rising part, log/linear after t_max). Tricky at presumed t_max (smoothing splines).
  
• If a few samples are missing in the late part consider truncation of AUC for both formulations at the latest complete time point for that subject; C_max-data is complete anyhow (don't simply drop the subject!)…

❝ But one of our sponsor says that we should have a priori criteria in percentage. For example if he had completed 90% of samples then he will be included and if not then will be excluded from the analysis.

I would call this some kind of formalistic nonsense.
Imagine the situation of a delayed release formulation which shows a lot of variability in t_lag due to gastric emptying. Rate of absorption and elimination are pretty nicely stable within subjects. If we have 18 sampling points, the first two after the predose sample are missing (e.g., vial broken in centrifugation) and the next two samples are still BLQ (due to t_lag), your sponsor would really want to exclude the subject and decrease the power of the study?

—
Dif-tor heh smusma 🖖🏼 Довге життя Україна! 
Helmut Schütz


The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes

Complete thread:

• Missing values ratnakar1811 2008-04-02 14:07 [Study Per­for­mance] 
  • Missing valuesHelmut 2008-04-02 14:54
    • Missing values atish_azad 2008-07-29 11:03
      • Missing values ElMaestro 2008-07-29 11:21
        • Missing values Helmut 2008-07-29 21:40
          • Missing values ElMaestro 2008-07-31 10:38
            • Missing values Helmut 2008-07-31 14:36
      • Missing values Helmut 2008-07-29 21:18
  • Missing values martin 2008-07-29 13:56
    • Missing values Helmut 2008-07-29 22:18
      • Missing values martin 2008-07-30 10:28
        • ITT vs. PP data sets Helmut 2008-07-30 13:30
        • Missing values d_labes 2008-07-30 13:39
          • Missing values Helmut 2008-07-30 14:34
          • Missing values martin 2008-07-30 14:50
            • Missing values Helmut 2008-07-30 17:14
              • Missing values d_labes 2008-07-31 09:18