Professor Thomas Richardson Seminar Jan 24 at 15

We welcome you to attend the international seminar series in statistics

Title: 

Generalizing Conditional Independence: Nested Markov Models

Speaker:  

Professor Thomas S Richardson

Department of Statistics

University of Washington, Seattle  

Time:  January 24, 2025, 15:00, Reception to follow

Location: Room 6, Floor 1, Building 35 on CSS campus (CSS 35.1.6)

Abstract: 

Graphical models based on directed acyclic graphs (DAGs), also known as Bayesian networks, have found application. This stems from their well understood Markov properties and intuitive causal interpretation under the assumption that there are no unmeasured common causes. However, it has also been known for more than 30 years that DAG models with hidden variables give rise to non-parametric (“Verma”) constraints that generalize conditional independence.

The nested Markov model is a class of graphical models associated with acyclic graphs containing directed and bidirected edges that encode all of the non-parametric equality constraints implied by DAGs with latent variables.  

In this talk I will first review the problem of causal identification from DAGs in the presence of hidden variables. This motivates a `fixing’ operation that may be applied to graphs and associated distributions. This operation leads to a simple reformulation of the ID algorithm of Tian & Pearl.

I will then show that the fixing operation may be used to define the nested Markov model and the associated global property. I will also describe simple preservation rules for reasoning with such constraints. Finally, (time permitting) I will outline a local property and sketch why this construction is more involved than for ordinary independence models.

[Joint work with  Robin J. Evans (Oxford),  James M. Robins (Harvard) and Ilya Shpitser (Johns Hopkins).]

Registration:  There is no need to register

Zoom link: upon request only 

If you have any questions, please contact Marie Krøger Pramming at marie.pramming@sund.ku.dk

Supported by DDSA and The SMARTbiomed Pioneer Center.