# Biostatistics book for mathematician

It would be great if you could recommend me some books on biostatistics for people with a solid background in mathematics.

I have an MSc in mathematics and a PhD in bioinformatics/machine learning, with additional post-doc experience in mathematical/computational biology. Since I don't find many bioinformatic jobs in the industries in Europe, I am thinking of selling myself as a biostatistician.

• – cardinal Feb 11 '15 at 0:05

In addition to the already recommended Frank Harrell's nice book (which I look forward to reading), I would like to share the following - and hopefully relevant - resources:

• Book "Regression Methods in Biostatistics: Linear, Logistic, Survival, and Repeated Measures Models". The examples are in Stata, in case, if you care about that. Here's the Amazon link - by the way, this is the Hardcover edition, which is strangely cheaper than Paperback one.

• Some interesting general and focused statistical recommended reading sources, shared by Vanderbilt University's Department of Biostatistics.

• Information from selected biostatistics classes, shared by professor Ingo Ruczinski at Johns Hopkins University (Bloomberg School of Public Health's Biostatistics Department).

• In regard to job search, recently I've run across several positions at Google (yes, that's right!) in bioinformatics, biostatistics and related areas. For example, see this position and this position (keep in mind that those positions are not located in Europe, but in Silicon Valley).

• Thank you for your links. Ingo slides seem very interesting at a first look. – Igor Fobia Jan 4 '16 at 18:08
• @IgorFobia: You're very welcome. Enjoy! – Aleksandr Blekh Jan 5 '16 at 1:04

you mention at the end of your Q that "I am thinking of selling myself as a biostatistician" in the industry in europe. In that case, it would make more sense to read the regulatory guidelines and books about the drug development process, and to sharpen your SAS skills and knowledge of cdisc, sdtm, adam. Large randomised controlled trials tend not to demand sophisticated, complex analyses. A pharma company will want a simple, cogent, unambiguous analysis to persuade the fda after all. They spend \$ running trials which means issues such as missing data, which can complicate the analysis, are minimised (by data monitoring). There is also a fondness for convention in the industry because convention leads to efficiency (eg re-using sas code and much standardisation). Therefore you'd do better to read a simple book like pocock's book on clinical trials, and if you're ambitious then stephen senn's statistical issues in drug development. That would bring you up to speed. And spend the time you save reading points to consider documents on the EMA website: EMA guidelines

You need to start with something on the applied side, like Frank Harrell: "Regression Modeling Strategies: With Applications to Linear Models, Logistic Regression, and Survival Analysis (Springer Series in Statistics) "

Then you can go deep into the underlying mathematics wih somethingh like PER KRAGH ANDERSEN and Ørnulf Borgan: "Statistical Models Based on Counting Processes (Springer Series in Statistics)"

and maybe supplement this with some book about R.