DN has published an article by Pressens Mediaservice, some news agency (I haven't looked into it very much). The article is about the failure of Radiohead's latest CD release which was available for free, on line. You could chose to pay if you wanted to. The article deems this as a failure, since 62 percent chose not to pay.
Now, 62 percent is a lot, but it's not even close to what we would need to know in order to deem it a failure. How many downloaded it? How much did they earn? How much do they usually earn? How much does an old-fashioned way of distributing a CD cost? Perhaps knowing this and probably even more, we will have knowledge enough to judge whether it was a success or not. As it is now, the company who carried out the analysis (Comscore, and if they judged it a failure based on only these numbers it's time to give a free and mandatory course in statistics to each and every employee) or a journalist at Pressens Mediaservice have taken misuse of statistics to a whole new level. Statistics is a powerful tool, but one is not to take only so much that it provides a point of view that you want to present or that you feel comfortable with. Stay true to the data, at all costs, data never lies, people do.
Link to the article in DN (Swedish).
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment