Biostatisticians are the shepherds (and the police) that guide the science of developing new therapies for disease. They come in several different flavors:
Those involved in gathering information, designing experiments and analyzing data at the drug discovery stage – trying to sort out what works and what doesn’t, and learning which research directions have potential
Those involved in designing, implementing, analyzing and reporting on randomized clinical trials
Those involved in analyzing observational data (not the result of experiments), often data that have previously been published (this is the field of epidemiology)
Those in the first group have a diverse set of skills and tasks, and play supporting roles to basic scientific research. Moreover, the term “biostatistician” is not generally used to describe those involved doing statistical analysis in the exploding arena of genomics and big data (bioinformatics is a term you will see more often for them).
Those in the second group, by contrast, play a leading role in clinical trials. If the statistical design is not sound at the front end, and the concluding analytical report for regulatory authorities not solid, a billion dollar investment may be lost. Biostatisticians in leadership roles in these groups generally have PhD’s.
Epidemiologic statisticians will typically have a public health background. They work in non-profit research organizations and universities, in contrast to pharmaceutical companies, where most of those in groups 1 and 2 work.
In short – biostatistics has long been a great job sector for statisticians, drawing statistics graduate students into the U.S. from other countries. Lately, the fastest growth in the medical sector has been in bioinformatics; these roles are accessible as lateral moves for statisticians who become educated in genomics and/or big data analytics.