{"id":900,"date":"2016-08-23T12:36:46","date_gmt":"2016-08-23T16:36:46","guid":{"rendered":"http:\/\/www.chiplynch.com\/wordpress\/?p=900"},"modified":"2016-08-25T14:00:29","modified_gmt":"2016-08-25T18:00:29","slug":"horses-and-olympians-and-data-and-such","status":"publish","type":"post","link":"https:\/\/www.chiplynch.com\/wordpress\/?p=900","title":{"rendered":"Horses and Olympians and Data and Such"},"content":{"rendered":"

I pick on Aaron Carroll<\/a>\u00c2\u00a0a lot, and it’s really not that he deserves picking on, it’s in fact because he writes so much good stuff that I like that I am compelled to\u00c2\u00a0investigate\u00c2\u00a0at length. \u00c2\u00a0Fortunately this time he actually asked for comments, so here we are…<\/p>\n

He recently posted a simple question (itself based upon a piece by Ben Rosen<\/a>): \u00c2\u00a0“Why are people getting so much faster, but not horses?”<\/a>\u00c2\u00a0on The Incidental Economist<\/a> blog, which you should read (the post, the site, all of it).<\/p>\n

It has two pretty charts , and otherwise it’s very short. \u00c2\u00a0But he asks for an answer to the question. \u00c2\u00a0First, the charts… one depicting the wining Kentucky Derby time over 60ish\u00c2\u00a0years and the next depicting the world record human\u00c2\u00a01-Mile running record:<\/p>\n

\"Charts<\/a>

Charts from\u00c2\u00a0Ben Rosen<\/a><\/p><\/div>\n

So, without the raw number or validating the trend lines, sure… the chart on the left shows a pretty even-keel trend (note the axis labels — the deviation\u00c2\u00a0is less than 5%, even though it looks spikey), while the one on the right shows a clearly, quickly, decreasing line.<\/p>\n

Of course, the error is easy to spot, and I’m sure Aaron was being coy about it… you can’t compare best times at one race against a world record history. \u00c2\u00a0The right hand chart is NECESSARILY going to go down all the time. \u00c2\u00a0It would be astounding if the left hand chart did… if every single race beat the best time of the previous race. \u00c2\u00a0And remember, the right hand chart is the aggregation of hundreds, possibly thousands of races competing for that best race. \u00c2\u00a0It’s apples to oranges, and that explanation fits in a tweet:<\/p>\n

\n

@aaronecarroll<\/a> I’m guessing breeding vs. training, but comparing a monotonically decreasing record to best times in one race is misleading.<\/p>\n

\u00e2\u20ac\u201d Chip Lynch (@chipmonkey75) August 22, 2016<\/a><\/p><\/blockquote>\n