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.
The statistics of climate change February 15, 2010
So who do you believe when it comes to climate change?
I don't wish to enter the debate because I'm not a climate scientist, nor have I analyzed climate records. But as statisticians currently look inward asking themselves why we have apparent image and credibility problems (see sidebar article "The Future of Statistics and Statisticians") the debates continue about whose analysis of the (climate) data is credible and defensible. In a recent on-line article Ross McKitrick says (emphasis added):
"I have been probing the arguments for global warming for well over a decade. In collaboration with a lot of excellent coauthors I have consistently found that when the layers get peeled back, what lies at the core is either flawed, misleading or simply non-existent. The surface temperature data is a contaminated mess with a significant warm bias, and as I have detailed elsewhere the IPCC fabricated evidence in its 2007 report to cover up the problem. Climate models are in gross disagreement with observations, and the discrepancy is growing with each passing year. The often-hyped claim that the modern climate has departed from natural variability depended on flawed statistical methods and low-quality data. The IPCC review process, of which I was a member last time, is nothing at all like what the public has been told: Conflicts of interest are endemic, critical evidence is systematically ignored and there are no effective checks and balances against bias or distortion."
Who do you believe???
One thing that did emerge from the National Academy of Sciences review (available here) of the controversial "hocky stick" graph was that:
"We note that there is no evidence that Dr. Mann or any of the other authors in paleoclimatology studies have had significant interactions with mainstream statisticians"
This is perhaps another instance of what Fox (2010) refers to as the "statistical hormetic effect".
Chicken and the egg:
Conclusion #3 of the NAS review states:
"As statisticians, we were struck by the isolation of communities such as the paleoclimate community that rely heavily on statistical methods, yet do not seem to be interacting with the mainstream statistical community. The public policy implications of this debate are financially staggering and yet apparently no independent statistical expertise was sought or used."
So the obvious question is "why not?" Clearly something's wrong with connections between statisticians and the rest of the scientific community. David Fox's anecdote in the companion news item (click here) might shed some light.