On 18/10/2025 14:49, Sven Schreiber wrote:

Jack mentioned that the approach is a generalization of fixed-effects regression, and that the foundation is through the Frisch-Waugh-Lovell theorem. So I wonder whether one should go one step further and also attempt to cover non-qualitative control variables.

The speed advantage you get in this case with the Frisch-Waugh approach is linked to the additional regressors being a set of exclusive dummies. I doubt that there is anything better than the QR approach (that we already use) for generic control variables, but of course I may be wrong.
-------------------------------------------------------
  Riccardo (Jack) Lucchetti
  Dipartimento di Scienze Economiche e Sociali (DiSES)

  Università Politecnica delle Marche
  (formerly known as Università di Ancona)

  r.lucchetti@univpm.it
  http://www2.econ.univpm.it/servizi/hpp/lucchetti
-------------------------------------------------------