{"generator":"GNU social 1.2.0-beta4","title":"Conversation","totalItems":1,"items":[{"actor":{"id":"https:\/\/mamot.fr\/users\/rfortunes","displayName":"RFortunes","status_net":{"avatarLinks":[{"url":"https:\/\/social.giorgiocomai.eu\/avatar\/1973-original-20181005080006.png","rel":"avatar","type":"image\/png","width":120,"height":120},{"url":"https:\/\/social.giorgiocomai.eu\/avatar\/1973-96-20181005084658.png","rel":"avatar","type":"image\/png","width":96,"height":96},{"url":"https:\/\/social.giorgiocomai.eu\/avatar\/1973-48-20181005084658.png","rel":"avatar","type":"image\/png","width":48,"height":48},{"url":"https:\/\/social.giorgiocomai.eu\/avatar\/1973-24-20181005084658.png","rel":"avatar","type":"image\/png","width":24,"height":24}],"profile_info":{"local_id":"1973"}},"image":{"url":"https:\/\/social.giorgiocomai.eu\/avatar\/1973-96-20181005084658.png","rel":"avatar","type":"image\/png","width":96,"height":96},"objectType":"person","summary":"A collection of fortunes from the R community. Bot built by @koantig@mamot.fr, from Achim Zeileis'  R package \"fortunes\". Nothing official. Updated twice a day.","url":"https:\/\/mamot.fr\/@rfortunes","portablecontacts_net":{"preferredUsername":"rfortunes","displayName":"RFortunes","note":"A collection of fortunes from the R community. Bot built by @koantig@mamot.fr, from Achim Zeileis'  R package \"fortunes\". Nothing official. Updated twice a day."}},"content":"<p>Usually (but not always) doing tests of normality reflect a lack of understanding of the power of rank tests, and an assumption of high power for the tests (qq plots don't always help with that because of their subjectivity). When possible it's good to choose a robust method. Also, doing pre-testing for normality can affect the type I error of the overall analysis.<br \/>  -- Frank Harrell<br \/>     R-help (April 2005) <a href=\"https:\/\/mamot.fr\/tags\/rstats\" class=\"mention hashtag\" rel=\"tag\">#<span>Rstats<\/span><\/a><\/p>","generator":{"id":"tag:status.net,2009:notice-source:ostatus","objectType":"application","status_net":{"source_code":"ostatus"}},"id":"https:\/\/mamot.fr\/users\/rfortunes\/statuses\/100666441955623633","object":{"id":"https:\/\/mamot.fr\/users\/rfortunes\/statuses\/100666441955623633","objectType":"note","content":"<p>Usually (but not always) doing tests of normality reflect a lack of understanding of the power of rank tests, and an assumption of high power for the tests (qq plots don't always help with that because of their subjectivity). When possible it's good to choose a robust method. Also, doing pre-testing for normality can affect the type I error of the overall analysis.<br \/>  -- Frank Harrell<br \/>     R-help (April 2005) <a href=\"https:\/\/mamot.fr\/tags\/rstats\" class=\"mention hashtag\" rel=\"tag\">#<span>Rstats<\/span><\/a><\/p>","url":"https:\/\/mamot.fr\/@rfortunes\/100666441955623633","status_net":{"notice_id":89660},"tags":[{"objectType":"http:\/\/activityschema.org\/object\/hashtag","displayName":"rstats"}]},"to":[{"objectType":"http:\/\/activitystrea.ms\/schema\/1.0\/collection","id":"http:\/\/activityschema.org\/collection\/public"}],"status_net":{"conversation":"tag:social.giorgiocomai.eu,2018-09-04:objectType=thread:nonce=c750ddde6a3f9a00","notice_info":{"local_id":"89660","source":"ostatus"}},"published":"2018-09-04T08:00:03+00:00","provider":{"objectType":"service","displayName":"social.giorgiocomai.eu","url":"http:\/\/social.giorgiocomai.eu\/"},"verb":"post","url":"https:\/\/mamot.fr\/@rfortunes\/100666441955623633"}],"links":[{"url":"https:\/\/social.giorgiocomai.eu\/conversation\/71848","rel":"alternate","type":"text\/html"}]}