Occassional thoughts about orienteering

Monday, July 16, 2012

SPROUT overview


Trying to predict US team results at the WOC was an experiment.  In part, I wanted to see if a really simple model would work.  In part, I'm always interested in ways of thinking about how a team is doing and trying to understand if a race is "good" or "bad."

SPROUT predicts the place of each US runner in each WOC qualifying race.  After 17 results, I think SPROUT worked pretty well:

4 times the prediction and the actual results matched
3 times the prediction and the actual results were 1 place apart
3 times the prediction and the actual results were 2 places apart
3 times the prediction and the actual results were 3 places apart

So, of 13 of 17 results were within 3 places.  The median difference was 2 places.

The worst prediction was off by 10 places.  Ali Croker's sprint qualifying result was much better than SPROUT expected.

The graph shows the difference between SPROUT and actual results.  You can see that the difference clusters around 2, with two outliers.

SPROUT is incredibly simple.  All it takes are a ranked list of the runners on the team (I used WRE points to put the runners in order) and a "normal  US place" and a number to add to or subtract from the normal US place.  I think a small tweak - looking at the actual values of the ranking list, not just the order - might have improved SPROUT a little bit.

Back to okansas.blogspot.com.

posted by Michael | 7:39 PM


Very interesting and remarkably good!

I challenge you to predict the relay results of the peer nations with SPROUT. Is there a chance that this works too?
I think an even simpler system might work for relays. I'll take a look and come up with some predictions.

Hi! Now I am very curious about the SPROUT analysis. :) Is that a formal method? The plots remind me of R plots. Which software have you used? :) I hope I am not asking too much! Thanks!

Just noticed Duska's comment.

I would say that it is a formal method, but it is very simple. It is described in a bit more detail here:


And I am using R for the plots.

Post a Comment
March 2002April 2002May 2002June 2002July 2002August 2002September 2002October 2002November 2002December 2002January 2003February 2003March 2003April 2003May 2003June 2003July 2003August 2003September 2003October 2003November 2003December 2003January 2004February 2004March 2004April 2004May 2004June 2004July 2004August 2004September 2004October 2004November 2004December 2004January 2005February 2005March 2005April 2005May 2005June 2005July 2005August 2005September 2005October 2005November 2005December 2005January 2006February 2006March 2006April 2006May 2006June 2006July 2006August 2006September 2006October 2006November 2006December 2006January 2007February 2007March 2007April 2007May 2007June 2007July 2007August 2007September 2007October 2007November 2007December 2007January 2008February 2008March 2008April 2008May 2008June 2008July 2008August 2008September 2008October 2008November 2008December 2008January 2009February 2009March 2009April 2009May 2009June 2009July 2009August 2009September 2009October 2009November 2009December 2009January 2010February 2010March 2010April 2010May 2010June 2010July 2010August 2010September 2010October 2010November 2010December 2010January 2011February 2011March 2011April 2011May 2011June 2011July 2011August 2011September 2011October 2011November 2011December 2011January 2012February 2012March 2012April 2012May 2012June 2012July 2012August 2012September 2012October 2012November 2012December 2012January 2013March 2013April 2013May 2013July 2013September 2013