Skip to content

Varying slopes: single slope on one factor (V=1) — centering + back-transform (#59)#79

Merged
schroedk merged 1 commit into
feature/slopesfrom
slopes/59-single-slope
Jul 7, 2026
Merged

Varying slopes: single slope on one factor (V=1) — centering + back-transform (#59)#79
schroedk merged 1 commit into
feature/slopesfrom
slopes/59-single-slope

Conversation

@schroedk

@schroedk schroedk commented Jul 7, 2026

Copy link
Copy Markdown
Collaborator

Implements #59.

A design whose sole term carries one slope column (f[z] / f[[z]]) now solves:

Tested against per-level closed forms (Rust) and pyfixest computed at test time (Python).

@schroedk schroedk force-pushed the slopes/59-single-slope branch from 10b346f to 832f600 Compare July 7, 2026 19:33
…l reparametrization (#59)

A sole f[z] / f[[z]] term now solves: the slope column is centered against
the pinned intercept (skipped when absent) and weighted-normalized per level,
the solve runs in the whitened basis, and coefficients are mapped back to the
user's parametrization. Rank drops are detected structurally over
positive-weight rows and reported through the unidentified-directions
side-channel with an exact minimal-norm 0 in the coefficient slot.

Slopes alongside other terms (#61) and V>=2 per factor (#60) stay gated.
@schroedk schroedk force-pushed the slopes/59-single-slope branch from 832f600 to 9181725 Compare July 7, 2026 19:45
@schroedk schroedk merged commit ad28a14 into feature/slopes Jul 7, 2026
3 checks passed
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.

1 participant