« Occupational hazards in data science | Main | Statistics as inverse probability »


Feed You can follow this conversation by subscribing to the comment feed for this post.


You are being a bit hard on the FDA. These drugs are the same chemical, in the same or similar binder materials, and would already have had chemical tests. They allow plus or minus 20% bio-availability, so it would be very surprising if they weren't found equivalent. Some of the more radical changes such as changes between oral and injectable are more difficult but there would already be a lot of data guiding the required ratio between the two delivery methods. Also a lot of this equivalence testing is a waste of time, as doses don't matter or can be titrated anyway.


Ken: Thanks for the comment. I think there are two separate issues here: you're arguing that most of the bioequivalence testing is pointless, which may be true; and if the margin of error is allowed to be 20%, it in fact may just be a public relations vehicle. Separately, though, given that a policy has been established in which such testing is required to gain approval, I still find it revolting that the entire process seemed to have been usurped and turned into a farce.


Yes, I had thought that the FDA policy would be that anyone caught cheating should have a prison sentence.

My assumption is that the FDA would have based it's decision on there being some data, just not as much as they thought, that it is not strictly necessary for generics which are identical compounds, and the drugs were already on the market. Regulators have a bad habit of expecting to see tests that they didn't really need.

The requirement for bio-equivalence which is 80-125%, is actually a bit more strict because it is the 90% CI that must lie within those values. It does mean that individuals can have ratios well outside. The only one I did, there were some subjects where the absorption of the generic was much lower, probably due to diet and the generic not having the same physical properties. The average was still within the limits so it was OK. It had actually got through he regulatory process, somehow, but the question was raised about equivalence because of pricing. A cheap drug isn't so cheap if you need more of it.

Drug Test Friend

This doesn't surprise me at all. The FDA has always worked in the best interest of the big pharmaceutical companies.

The comments to this entry are closed.

Get new posts by email:
Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR, Wired.

See my Youtube and Flickr.


  • only in Big Data
Numbers Rule Your World:
Amazon - Barnes&Noble

Amazon - Barnes&Noble

Junk Charts Blog

Link to junkcharts

Graphics design by Amanda Lee

Next Events

Jan: 10 NYPL Data Science Careers Talk, New York, NY

Past Events

Aug: 15 NYPL Analytics Resume Review Workshop, New York, NY

Apr: 2 Data Visualization Seminar, Pasadena, CA

Mar: 30 ASA DataFest, New York, NY

See more here

Principal Analytics Prep

Link to Principal Analytics Prep