Our nine-point guide to spotting a dodgy statisticJuly 18, 2016 Tim WorstallNewspaper Watch8 CommentsSee it being used in The Guardian. So, what were the other 8 points? previousGood luck there I have to saynextMore Brexit idiocy about food 8 thoughts on “Our nine-point guide to spotting a dodgy statistic” Bloke in North Dorset July 18, 2016 at 7:26 am 2. They come from a politician. Dongguan John July 18, 2016 at 7:40 am This 60 year old book is still fantastically appropriate: https://en.wikipedia.org/wiki/How_to_Lie_with_Statistics The pdf is available somewhere online; I downloaded it before. dearieme July 18, 2016 at 9:31 am No need for the pdf: we own two copies. 🙂 Fen Tiger July 18, 2016 at 11:31 am There are many formats here. djc July 18, 2016 at 11:38 am Three must reads in statistics: Huff. How to Lie with Statistics Tukey. Exploratory Data Analysis Tufte. The Visual Display of Quantitative Information dearieme July 18, 2016 at 11:56 am Agreed, djc. Plus that last also gives an aesthetic thrill. dearieme July 18, 2016 at 11:58 am On the subject of dodgy statistics, or at least dodgy statisticians: trust no statistician who, writing for the lay public, uses “significant” or “explains” without any warning about their technical meanings. Bloke in Malta July 19, 2016 at 6:40 pm https://www.theguardian.com/technology/2016/jul/19/uk-digital-skills-lagging-behind-other-countries-barclays-report 37% of workers in India would be comfortable building a website. Basically everyone who has access to the internet in the country then. Leave a Reply Cancel replyYour email address will not be published. Required fields are marked *Comment Name * Email * Website Save my name, email, and website in this browser for the next time I comment.