Added an option (-P) which will cause, for each dataset being used in the fit, two additional fits to be performed, one with that dataset scaled down one sigma and one with that dataset scaled up one sigma. The difference in the results for that dataset are then displayed as an additional "parametric" error.
added ability to fix some distributions
The fit function now weights each histogram by the reciprocal variance to take into account the error of each MC sample.
added new formatting features
Made the legend titles bold. Impossible to do? MYTH BUSTED
Perform the full weighting at merging instead of splitting it between the merging and plotting steps.
First commit of script for fitting MC normalizations to data.
This form allows you to request diffs between any two revisions of this file. For each of the two "sides" of the diff, select a symbolic revision name using the selection box, or choose 'Use Text Field' and enter a numeric revision.