Skip to content

Conversation

@davidwalter2
Copy link
Collaborator

@davidwalter2 davidwalter2 commented Jan 4, 2026

For completeness, the BB full with gamma distributed beta parameters is implemented. This requires explicit parameters.

  • One parameter per bin is introduced defined as $n_\beta = \sum_j n_j \beta_j / \sum_j n_j $, to decouple the system of equations, the solution for each $\beta_j$ parameter is then computed analytically.
  • The $n_\beta$ are appended to the end of the fitter.x tensor
  • Impacts and global impacts are implemented for this mode by stripping off the additional parameters
  • The EDM for beta parameters in the full scheme is fixed by masking bins/processes that don't contribute


if self.binByBinStat:
if self.binByBinStatType == "gamma":
if self.binByBinStatMode == "full":
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Isn't this PR implementing it ?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is w.r.t. the toys, I'm not sure but I think one would need to compute and vary the $n_\beta$ parameters here.

@davidwalter2 davidwalter2 mentioned this pull request Jan 6, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants