Nature Methods Starts Statistics Column

By Steve Pierson posted 09-04-2013 12:19

  
With the title, "Let’s give statistics the attention it deserves in biological research," Nature Methods Chief Editor Daniel Evanko announced in their blog the launch of "Points of Significance," a new monthly column devoted to statistics, "a topic of profound importance for biological research, but one that often doesn’t receive the attention it deserves." The Editorial for the September issue of  Nature Methods, Matters of significance, is also devoted to statistics with the subtitle, "Sound experimental design and analysis require improved statistical training."

Evanko describes Points of Significance as a natural complement to the well-received "Points of View" column - described as "one page a month dedicated to practical advice for researchers on how to create accessible and accurate visualizations of their data" - writing,
a truth about data visualization is that no matter how good the visualization, if the experiment wasn’t appropriately designed and the data wasn’t analyzed correctly, the resulting visual depiction of the data will be inherently flawed.
He also noted the new column is consistent with  the recent changes the Nature journals have made to improve data and methods reporting as part of a reproducibility initiative.

The monthly column will be co-authored by an author of the visualization column, Martin Krzywinski, and Penn State Statistics Professor (and ASA Member) Naomi Altman and will be designed to build on prior columns. The first column, Points of significance: Importance of being uncertain, discusses populations and sampling and the October Points of Significance article will be on error bars and confidence intervals. "Points of Significance" will be two pages instead of the one page allotted for "Points of View" and will frequently have an Excel spreadsheet associated with it. In addition, each column will be free to access for the first month it is published.

In a private communication, Evanko said statistics outcompeted a number of other topics for the new column. He also stressed the philosophy behind the statistics and visualization columns is to present to researchers a topic in an accessible, digestible and concise way. While the topics are covered in books or courses, researchers are busy and so the Nature Methods columns try to deliver the content in an easy way that accumulates over time. 

Through emails with Altman and Evanko, I also learned that Thomas Jefferson University Biostatistics Professor (and ASA Member)Terry Hyslop serves as a Statistical Adviser to the Nature Editorial Board. In this role Hyslop helps establish a cadre of statistical reviewers, develop educational ideas, and raise the profile of statistics within the life sciences.
 
In addition to Evanko's blog entry, "Let’s give statistics the attention it deserves in biological research," I urge you to see the September Editorial,  Matters of significance, and the first "Points of Significance" column, Importance of being uncertain.

Some of you may recall I did a December blog entry - Statistical Guidance for Experimental Biologists: What would a statistician write? - on a December 13 Nature opinion piece whose subhead read, "Experimental biologists, their reviewers and their publishers must grasp basic statistics, or sloppy science will continue to grow." It's great to see the attention Nature is giving to statistics.

Finally, I would be remiss not to mention that Evanko points out the appropriateness of starting the statistics column during the International Year of Statistics!

[Columns added as they appear - including the September column mentioned above (see also this Genome Sciences Center website):  See other ASA Science Policy blog entries. For ASA science policy updates, follow @ASA_SciPol on Twitter.

0 comments
463 views

Related Content