Statistically Borderline failed studies [Regulatives / Guidelines]
Dear Sandeep,
in the recent past regulators generally became more and more strict. One the other hand see this thread.
You can try. If the metric was AUC and the acceptance range was fixed at 80.00–125 % in the protocol I’m afraid cards are stacked against you. If the PE was not too far away from 1 (=the study likely failed due to higher CV than anticipated) you may consider repeating it in a larger sample size. If you wait until getting a deficiency letter your timeframe will be rather close.
If the metric was Cmax and the study is not intended for submission in the US, EU, Australia, or New Zealand, you have more headroom for starting an argument (some countries still accept a range wider than 80.00–125 %). Even if not stated in the protocol, try to get some references on safety (because upper CL > upper AL). Discuss the relevance.
Good luck.
in the recent past regulators generally became more and more strict. One the other hand see this thread.
❝ Say for e.g. if the 90% CI upper limit is 125.51.
You can try. If the metric was AUC and the acceptance range was fixed at 80.00–125 % in the protocol I’m afraid cards are stacked against you. If the PE was not too far away from 1 (=the study likely failed due to higher CV than anticipated) you may consider repeating it in a larger sample size. If you wait until getting a deficiency letter your timeframe will be rather close.
If the metric was Cmax and the study is not intended for submission in the US, EU, Australia, or New Zealand, you have more headroom for starting an argument (some countries still accept a range wider than 80.00–125 %). Even if not stated in the protocol, try to get some references on safety (because upper CL > upper AL). Discuss the relevance.
Good luck.
—
Dif-tor heh smusma 🖖🏼 Довге життя Україна!![[image]](https://static.bebac.at/pics/Blue_and_yellow_ribbon_UA.png)
Helmut Schütz
![[image]](https://static.bebac.at/img/CC by.png)
The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Dif-tor heh smusma 🖖🏼 Довге життя Україна!
![[image]](https://static.bebac.at/pics/Blue_and_yellow_ribbon_UA.png)
Helmut Schütz
![[image]](https://static.bebac.at/img/CC by.png)
The quality of responses received is directly proportional to the quality of the question asked. 🚮
Science Quotes
Complete thread:
- Statistically Borderline failed studies drsinghs 2011-11-09 12:45
- Statistically Borderline failed studiesHelmut 2011-11-09 13:26
- Statistically Borderline failed studies drsinghs 2011-11-10 05:14
- Statistically Borderline failed studies Helmut 2011-11-10 13:51
- Statistically Borderline failed studies drsinghs 2011-11-11 04:52
- Statistically Borderline failed studies Helmut 2011-11-10 13:51
- Statistically Borderline failed studies drsinghs 2011-11-10 05:14
- Statistically Borderline failed studiesHelmut 2011-11-09 13:26
