{"id":99,"date":"2014-01-16T18:57:25","date_gmt":"2014-01-16T18:57:25","guid":{"rendered":"http:\/\/labmath.org\/?p=99"},"modified":"2014-02-27T21:31:22","modified_gmt":"2014-02-27T21:31:22","slug":"great-stats-blog-site","status":"publish","type":"post","link":"http:\/\/labmath.org\/?p=99","title":{"rendered":"Great Stats Blog Site"},"content":{"rendered":"

A recent post<\/a>\u00a0on the Simply Statistics blog<\/a> takes on a sort-of-hot topic in statistics: what errors actually matter, and how are they best quantified and reported when you are using statistics to infer something about a population. \u00a0Best, in this case, means best at making accurate predictions. \u00a0The two camps are the Frequentists and the Bayesians. \u00a0(I gather from reading a bit that the debate had actually settled down until Nate Silver brought it up in his book The Signal and the Noise.) \u00a0Note – the disagreement is not about descriptive statistics, it is about inferential statistics, \u00a0so don’t worry if you are committed to box plots, frequency distributions, and\/or mean and standard deviation; they are very good for describing data. \u00a0The two approaches differ in what you are comparing your results to. \u00a0All interpretations are comparisons, implicit or explicitly, so what you compare your results to matters. \u00a0In one camp, you have people comparing their measurements to the null hypothesis which is that variation among your measurements arose due to random, natural variation in the measurand (the thing that is measured). \u00a0The other camp includes in its comparisons previous measurements of the measurand. \u00a0It does this by including consideration of what they call “priors.” \u00a0My “I’m-not-a-statistician-but-I-know-what-I-like” point of view on this is that each is good for particular things, which is why both approaches continue to be used. \u00a0For example, if you can not find a relevant prior, you can’t take it into account, so you have to compare your result to the null hypothesis. \u00a0As with many things, for example choosing effect size, your educated judgment has to inform the design of your analysis and thus the design of your experiments.<\/p>\n

 <\/p>\n","protected":false},"excerpt":{"rendered":"

A recent post\u00a0on the Simply Statistics blog takes on a sort-of-hot topic in statistics: what errors actually matter, and how are they best quantified and reported when you are using statistics to infer something about a population. \u00a0Best, in this case, means best at making accurate predictions. \u00a0The two camps are the Frequentists and the […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[10,4],"tags":[],"_links":{"self":[{"href":"http:\/\/labmath.org\/index.php?rest_route=\/wp\/v2\/posts\/99"}],"collection":[{"href":"http:\/\/labmath.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/labmath.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/labmath.org\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"http:\/\/labmath.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=99"}],"version-history":[{"count":9,"href":"http:\/\/labmath.org\/index.php?rest_route=\/wp\/v2\/posts\/99\/revisions"}],"predecessor-version":[{"id":102,"href":"http:\/\/labmath.org\/index.php?rest_route=\/wp\/v2\/posts\/99\/revisions\/102"}],"wp:attachment":[{"href":"http:\/\/labmath.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=99"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/labmath.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=99"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/labmath.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=99"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}