Connecting information professionals across upstate New York.

Categorized | Uncategorized

Doing library science research? Set your P-values right to ensure reproducibility

Just last week in Nature there was a discussion of the ‘plague of irreproducibility’ in much modern research–especially in the social sciences. Statistician Valen Johnson used a method of ‘uniformly most-powerful’ analysis of the statistical techniques used in a huge swath of studies to determine that many researchers were not setting their parameters tightly enough to guard against false positives. This issue may affect 17-25% of the studies analyzed, wherein the data may not support the conclusions and the procedure may thus not reproduce the results.

To guard against this problem, Johnson recommends that researchers analyze quantitative findings using much more-stringent P-value of .0005 rather than the more-traditional .05.

This obviously has big implications for both current and past authors of library science research that use traditional tools of statistical analysis.

The discussion of the article can be found in Nature with the original paper found inĀ Proceedings of the National Academy of Sciences.

Hayden, E.C. Nature. USA http://doi:10.1038/nature.2013.14131 (2013).

Johnson, V. E. Proc. Natl Acad. Sci. USA http://dx.doi.org/10.1073/pnas.1313476110 (2013).

 

 

 

Comments are closed.

Save the Date!

Mark your calendars for the Spring 2018 UNYSLA Conference: Lead From Where You Are

 

When: April 13th, 2018

Where: Rochester, NY

 

Check back soon for more details!

Get Involved with UNYSLA

There are several ways to get involved including conference planning, board positions, networking events, and so much more! Send any inquiries to anyone listed on our About page or fill out our Contact Us form.

Quick Links

Thank you to our sponsors!

Thanks to our Sponsor!


Thanks to our sponsor, Ebsco Health! Interested in becoming a sponsor? Find out how.

Archived Posts