%0 Journal Article %1 Wilks2016The %A Wilks, D. S. %D 2016 %I American Meteorological Society %J Bull. Amer. Meteor. Soc. %K skill statistics verification %N 12 %P 2263--2273 %R 10.1175/bams-d-15-00267.1 %T "The Stippling Shows Statistically Significant Grid Points": How Research Results are Routinely Overstated and Overinterpreted, and What to Do about It %U http://dx.doi.org/10.1175/bams-d-15-00267.1 %V 97 %X AbstractSpecial care must be exercised in the interpretation of multiple statistical hypothesis tests?for example, when each of many tests corresponds to a different location. Correctly interpreting results of multiple simultaneous tests requires a higher standard of evidence than is the case when evaluating results of a single test, and this has been known in the atmospheric sciences literature for more than a century. Even so, the issue continues to be widely ignored, leading routinely to overstatement and overinterpretation of scientific results, to the detriment of the discipline. This paper reviews the history of the multiple-testing issue within the atmospheric sciences literature and illustrates a statistically principled and computationally easy approach to dealing with it?namely, control of the false discovery rate.

@article{Wilks2016The, abstract = {AbstractSpecial care must be exercised in the interpretation of multiple statistical hypothesis tests?for example, when each of many tests corresponds to a different location. Correctly interpreting results of multiple simultaneous tests requires a higher standard of evidence than is the case when evaluating results of a single test, and this has been known in the atmospheric sciences literature for more than a century. Even so, the issue continues to be widely ignored, leading routinely to overstatement and overinterpretation of scientific results, to the detriment of the discipline. This paper reviews the history of the multiple-testing issue within the atmospheric sciences literature and illustrates a statistically principled and computationally easy approach to dealing with it?namely, control of the false discovery rate.}, added-at = {2018-06-18T21:23:34.000+0200}, author = {Wilks, D. S.}, biburl = {https://www.bibsonomy.org/bibtex/282b206c5e7233eadc201d54af6279d72/pbett}, citeulike-article-id = {13980542}, citeulike-linkout-0 = {http://journals.ametsoc.org/doi/abs/10.1175/BAMS-D-15-00267.1}, citeulike-linkout-1 = {http://dx.doi.org/10.1175/bams-d-15-00267.1}, day = 9, doi = {10.1175/bams-d-15-00267.1}, interhash = {de4b53e39f40f7273b2f32adcc799a4e}, intrahash = {82b206c5e7233eadc201d54af6279d72}, journal = {Bull. Amer. Meteor. Soc.}, keywords = {skill statistics verification}, month = mar, number = 12, pages = {2263--2273}, posted-at = {2016-03-15 15:21:44}, priority = {2}, publisher = {American Meteorological Society}, timestamp = {2020-04-24T11:24:10.000+0200}, title = {"The Stippling Shows Statistically Significant Grid Points": How Research Results are Routinely Overstated and Overinterpreted, and What to Do about It}, url = {http://dx.doi.org/10.1175/bams-d-15-00267.1}, volume = 97, year = 2016 }