Mirror of the best candidate showers page.
I implemented a Kolmogorov-Smirnov Test in HitLogLikelihood_Primitive. (Code.)
I updated the write-up of what is going on in the code to include a description of the KS test (page 2).
It took about 2 hours to reconstruct one shower, but the result came out looking quite reasonable. It is hard to see from the graphs, because of the accidentals, but the numbers for the 4 sites 99, 108, 133, and 112 are ok. Right now I am looking for ways to speed up the code enough for me to test it on more showers in a reasonable amount of time...
