support sum(w) < 0 in binned fits #1022
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
HDembinski
force-pushed
the
negative_sum_of_weights
branch
from
22787da to
565fcc0
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This patch makes it possible to fit histograms with negative bin entries with
ExtendedBinnedNLLandBinnedNLL. These occur, for example, when sweighted samples are histogrammed. This patch implements an extension of the Bohm-Zech approach for this case. The ideas behind this extension are compiled in a write-up that can be found in the documentation under "Studies: Fitting weighted histograms".The PR also fixes a mistake in
BinnedNLL, which used the wrong cost function for weighted histograms, for ordinary histograms there is no change. This is a side result from thinking deeply about fitting weighted histograms. The old cost function lead to biased estimates, while the new one is now almost unbiased and performs even better thanExtendedBinnedNLLin application to weighted histograms.Other changes: