R package for determining whether the parameters of mixed graphical model are identifiable from the resulting data distribution.

(With Mathias Drton.)

Papers:

Half-trek criterion for generic identifiability of linear structural equation models (Rina Foygel, Jan Draisma, Mathias Drton).

Global identifiability of linear structural equation models (Mathias Drton, Rina Foygel, Seth Sullivant).

For code to implement methods and reproduce experiments from individual papers, links to code are placed next to each paper title (go to the Papers tab).

### SEMID: Identifiability of linear structural equation models

### Knockoff filter for controlling FDR in sparse linear regression

R package and Matlab package implementing the knockoff filter for false discovery rate control when selecting variables in a lineaer regression.

(With Emmanuel Candès and Evan Patterson.)

Paper:

Controlling the False Discovery Rate via Knockoffs (Rina Foygel Barber and Emmanuel Candès).

Slides from a talk are here. (Note that the slides include a video which may not play in some PDF viewers. On a Mac, it works in Adobe Reader but not in Preview.)

(With Emmanuel Candès and Evan Patterson.)

Paper:

Controlling the False Discovery Rate via Knockoffs (Rina Foygel Barber and Emmanuel Candès).

Slides from a talk are here. (Note that the slides include a video which may not play in some PDF viewers. On a Mac, it works in Adobe Reader but not in Preview.)