"Have you looked at John Cornell's work on mixture models? It consists of almost exactly this kind of problem. He uses regression, but it should be straightforward to add regularization."
AnalyticBridge
A Data Science Central Community
John Johnson's Page
Latest Activity
John Johnson replied to Vincent Granville's discussion Linear regression on an usual domain, hyperplane, sphere or simplexJohn Johnson replied to Andrew Paul Acosta's discussion Comparing JAGS to BUGS in the group Bayesian Modeling"From my limited experience, there are differences enough to be annoying (and where you have to be careful), but not too huge a gap. You should be able to use your BUGS books with JAGS. And it goes without saying that your results may be a little…"
John Johnson commented on Vincent Granville's blog post Analytics used to avoid traffic tickets and DUI arrests"CB radio of the 21st century!"
Vincent Granville left a comment for John Johnson"Yes John, my mentor at UNC Chapel Hill and Cambridge University was Prof. Richard L. Smith."
John Johnson left a comment for Vincent Granville"Vincent,
I thought you looked familiar. I just saw that you worked with Richard Smith back in 1996. That's when I joined the stat dept. at UNC. Nice to meet up with more fellow Tar Heels!"
John Johnson replied to Justin Boland's discussion Statistical Best Practices"Are you looking for something beyond ICH E9?"
John Johnson left a comment for Stephan Ogenstad"Stephan,
Thanks for the welcome.
On your question about adaptive designs and the FDA, I've found in general the FDA is cautiously accepting of adaptive designs. (CDRH more warmly than CDER/CBER.) Trials using these designs need to have a lot…"
Stephan Ogenstad left a comment for John Johnson"Hello John,
Welcome to Statistical Consulting. I see that you have great experience in modeling, simulation and specialty designs such as adaptive methods. What is your experience with using adaptive methods when presenting the methods to the FDA?…"
John Johnson replied to Vincent Granville's discussion Five best SAS books in the group SASnetwork.com"If you are looking into being a SAS programmer in the pharmaceutical/device industry, I recommend SAS Programming in the Pharmaceutical Industry by Jack Shostak. This book covers the tasks you would want to perform in the industry: analysis…"
Ok, finally got my Twitter feed integrated here. Enjoy. On occasion, blog links will be posted.(via Status)
Profile Information
- Short Bio:
- I am the Associate Director of Statistics at REGISTRAT-MAPI, a leader in late phase drug research, with 13 years experience in statistics (over 9 in health care). My specialty is the planning and design of clinical trials, modeling and simulation, observational studies, and weird problems. I work in strategic drug development planning, negotiate with the FDA on behalf of clients, and manage a very good group of biostatisticians and programmers.
- My Website or LinkedIn Profile (URL):
- http://realizationsinbiostatistics.blogspot.com
- Field of Expertise:
- Biostatistics, Statistical Programming, Statistical Consulting, Medical Statistics, SAS
- Years of Experience in Analytical Role:
- 13
- Professional Status:
- Director
- Interests:
- Networking
- Your Company:
- REGISTRAT-MAPI
- Industry:
- Pharmaceuticals, Biotech, and Medical Device
- How did you find out about AnalyticBridge?
Websites
Comment Wall (2 comments)
- At 12:31pm on April 15, 2009, Vincent Granville said…
- Yes John, my mentor at UNC Chapel Hill and Cambridge University was Prof. Richard L. Smith.
- At 7:24am on April 13, 2009, Stephan Ogenstad said…
- Hello John,
Welcome to Statistical Consulting. I see that you have great experience in modeling, simulation and specialty designs such as adaptive methods. What is your experience with using adaptive methods when presenting the methods to the FDA? Are they open and willing to embrace these methods?
Best
Stephan
Stephan Ogenstad, PhD
President & CEO
Statogen Consulting, LLC
http://www.statogen-consulting.com
Follow Us
On Data Science Central
On DataViz
On Hadoop
© 2018 AnalyticBridge.com is a subsidiary and dedicated channel of Data Science Central LLC
Powered by
Badges | Report an Issue | Privacy Policy | Terms of Service
