Ron Sandland recently wrote about the new phenomenon of 'big data' - weighing up the benefits and concerns. Terry Speed reflected on the same issue in a talk earlier this year inGothenburg, Sweeden noting that this is nothing new to statisticians. So what's all the fuss about? Here's another take on the 'big data' bandwagon.
Statisticians and (eco)Toxicologists Unite! January 5, 2016
As debates about the legitimacy of NOECs and NOELs continue unabated, we believe it's well and truly time to establish a sub-discipline of Statistical (eco)toxicology.
In a recent review, Hothorn (2014) concluded "still today remarkable contradictions for statistics in toxicology exist". Compared to the illustrious early beginnings when problems in (eco)toxicology piqued the interest of great statistical minds such as Fisher, Bliss, and Berkson, the present ecotoxicological landscape is statistically depauperate. Like some disappearing Elvis - statistics has left the ecotox. building.
Of course, it's not all bad. There are groups of highly talented and highly-credentialed quantitative biologists, ecologists, ecotoxicologists, chemists and even statisticians scattered around the globe who are working on complex issues, developing new tools and generally advancing ecotoxicological practice. But there is a certain stasis that prevents the discipline from shrugging off outdated, inferior, and at times, utterly bankrupt practices. If Hothorn (2014) is to be believed, part of the reason is due to publication bias - "the unwillingness of editors of toxicological papers to accept statistical publications". It is a claim supported by Fox and Landis who have called for improving the disciplinary interactions through the creation of statistical ecotoxicology as a recognized sub-discipline of ecotoxicology. Whether or not this suggestion gains any traction remains to be seen. In the meantime, we continue to counter the entrenched views that seek to maintain the status quo by elevating awareness, highlighting difficulties and providing signposts for future engagement.
Hothorn, LA. 2014. Statistical evaluation of toxicological bioassays - a review. Toxicology Research 3:418-432