Study: Debunking ‘Fake News’ in the Post-Truth Era
New study exposes statistical incompetence in public investment projects; research is being contaminated by subjective bias. Too much research work does not meet basic standards of validity and reliability.
Posted July 10, 2019 by Elsevier in papers.ssrn.com is ‘On De-Bunking ‘Fake News’ in the Post-Truth Era: How to Reduce Statistical Error in Research‘ which addresses the crisis of modern scientific research for ‘garbage in, garbage’ data misuse.
Below are excerpt, the full paper is at papers.ssrn.com
Abstract: The authors note with alarm that statistical noise caused by statistical incompetence is
beginning to creep into research on cost overrun in public investment projects, contaminating research with work that does not meet basic standards of validity and reliability. The paper gives examples of such work and proposes three heuristics to root out the problem. First, researchers who are not statisticians, or do not have a strong background in statistics, should abstain from doing statistical analysis, and instead rely on more experienced colleagues, preferably professional statisticians. Second, journal referees should clearly state their level of statistical proficiency to journal editors, so these can set the right referee team. Finally, journal editors should make sure that at least one referee is capable of reviewing the statistical and methodological aspects of a paper. The work under review would have benefitted from observing these simple heuristics, as would any work based on statistical analysis.
…… The editors of Transportation Research Part A recently received a comment by Peter Love, Lavagnon Ika and Dominic Ahiaga-Dagbui (2019) as a rejoinder to our critique (Flyvbjerg et al., 2018) of a paper by Love and Ahiaga-Dagbui (2018). However, as the rejoinder came in the form of a new paper, the editors kindly offered us the possibility of a re-rejoinder, which follows below.
One Error Covertly Corrected, 13 Overtly Ignored In Flyvbjerg et al. (2018: 177-78, tables 1 and 2) we rejected four postulated myths, one by one, and identified 14 serious statistical errors in the earlier paper by Love and Ahiaga-Dagbui (2018). Two mathematical statisticians helped us identify the mistakes.
…..
How to Get More Signal and Less Noise in Research
We would like to end by asking, at a more general level, how statistical errors like those committed by Peter Love and his colleagues may be reduced in research. Gigerenzer (2004), Taleb (2007), and others (McGregor 1993, Leek et al. 2017, Gelman 2018) have long argued that statistical incompetence is a problem in research on human affairs, and that such research therefore often produces spurious results, sometimes with negative consequences for policy and practice. It is crucial for any academic field, including transportation research and project management, to root out such incompetence. If this does not happen, it will become increasingly difficult to distinguish between signal and noise in research results, which will undermine the value of research and trust in it.
Read more at papers.ssrn.com/sol3/papers.cfm?abstract_id=3416731
PRINCIPIA SCIENTIFIC INTERNATIONAL, legally registered in the UK as a company 
incorporated for charitable purposes. Head Office: 27 Old Gloucester Street, London WC1N 3AX.
Please DONATE TODAY To Help Our Non-Profit Mission To Defend The Scientific Method.
Trackback from your site.