There is something wrong in the state of scientific research. It would be nice if it was not significant, but in fact it is. In fact, those words are apt choices as a paper in Nature has reported on misuse of significance tests. Basically if something passes a significance test and something fails a significance test, you cannot say that the difference between the two levels of significance is, of itself, significant. (with me?). However, this error turns up repeatedly. The subject matter is neuroscience, but why should it just occur in this field? I bet a lot of researchers are checking through their work.
The original paper is here:
http://www.nature.com/neuro/journal/v14/n9/full/nn.2886.html
Commentary from Bad Science is here:
http://www.badscience.net/2011/10/what-if-academics-were-as-dumb-as-quacks-with-statistics/#more-2405
This blog focuses on dentistry. Articles on leadership and innovation etc. will now be posted to our sister blog at Milford (http://milforduk.wordpress.com) Paul Kelly also works as a locum dentist. Details for this are on the Dental Business Innovation website (see link in side bar). We also run training courses for dental teams in the areas of leadership, innovation and business skills, and these are all detailed on our website www. milford-uk.com You can follow me on Twitter @paulkelly2012
No comments:
Post a Comment