Andrew Orloski mangles the extrapolation of figures from a Forrester study to conclude that iTunes sales are ‘collapsing’. Ironically, buried in the piece is this quote: “Forrester analyst Josh Bernoff warned against extrapolating too much from the figures.” I do not care if iTunes sales collapse (except for my friends who are songwriters), however I do care when individuals who likely did everything possible to avoid taking a statistics course in college attempt to cherry pick and mash up unrelated numbers into an argument.
permalink | categories: statistics |
December 13th, 2006 at 3:44 pm
[...] Is this something unique to online media or the blogosphere? Hardly. Newspapers and TV networks do this kind of thing all the time. Staci at PaidContent is right that Rex Hammock had the best line: “Reporters’ inability to interpret statistics is ’sky-rocketing’.” [...]
December 13th, 2006 at 4:38 pm
[...] Yesterday, I pointed out how a statistics-challenged reporter had mangled the extrapolation of a model-challenged analysis that included the logic-defying claim that iTunes sales dropped by 65% in the first half of 2006. As I’ve said here ad nauseum, giving reporters statistics is like handing a loaded pistol to a three-year-old. (Actually, I haven’t said that, but things like that.) The notion that iTunes sales could have dropped by 65% and a Forrester analyst would be the person to uncover it (and not, for example, being discovered by record companies screaming over why their revenues from Apple had fallen by 65%) is enough to make your BS-dar ping. Despite the dubious nature of the statistic, so-called news services picked it up. [...]