11.07.2015 Views

2DkcTXceO

2DkcTXceO

2DkcTXceO

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

R.A. Irizarry 173FIGURE 16.1Illustration of gene expression data before and after microarrays.cer recurrence gene expression assays making it possible to identify patientsat risk of distant recurrence following surgery (van’t Veer, 2002).When biologists at Johns Hopkins first came to our department for helpwith their microarray data, Scott put them in touch with me because I hadexperience with (what was then) large datasets (digitized music signals arerepresented by 44,100 points per second). The more I learned about the scientificproblems and the more data I explored, the more motivated I became.The potential for statisticians having an impact in this nascent field was clearand my department was encouraging me to take the plunge. This institutionalencouragement and support was crucial as successfully working in thisfield made it harder to publish in the mainstream statistical journals; an accomplishmentthat had traditionally been heavily weighted in the promotionprocess. The message was clear: having an immediate impact on specific scientificfields would be rewarded as much as mathematically rigorous methodswith general applicability.As with my thesis applications, it was clear that to solve some of the challengesposed by microarray data I would have to learn all about the technology.For this I organized a sabbatical with Terry Speed’s group in Melbournewhere they helped me accomplish this goal. During this visit I reaffirmed mypreference for attacking applied problems with simple statistical methods, asopposed to overcomplicated ones or developing new techniques. Learning thatdiscovering clever ways of putting the existing statistical toolbox to work wasgood enough for an accomplished statistician like Terry gave me the necessaryconfidence to continue working this way. More than a decade later thiscontinues to be my approach to applied statistics. This approach has beeninstrumental for some of my current collaborative work. In particular, it ledto important new biological discoveries made together with Andy Feinberg’slab (Irizarry, 2009).

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!