Causal inference, sparse graphs and genomics


METADATA ONLY
Loading...

Author / Producer

Date

2010

Publication Type

Other Publication

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Understanding cause-effect relationships between variables is of interest in many fields of science. The standard method for determining such relationships uses randomized controlled perturbation experiments. In many settings, however, such experiments are expensive and time consuming. Hence, it is desirable to obtain causal information from observational data obtained by observing the system of interest without subjecting it to interventions. We are primarily interested in this problem for estimating intervention effects (and planning new perturbation experiments) in genomics.

From a statistical point of view, when assuming no or little information about (causal) influence diagrams, the problem in its full generality is ill-posed. However, will show how graphical modeling and intervention calculus can be used for quantifying useful bounds for causal effects, even for the high-dimensional, sparse case where the number of variables can greatly exceed sample size. The statistical method is validated with gene intervention experiments in yeast and arabidopsis.

Publication status

published

External links

Editor

Book title

Journal / series

Volume

Pages / Article No.

Publisher

Stanford University, Health Research and Policy

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03502 - Bühlmann, Peter L. / Bühlmann, Peter L. check_circle

Notes

Lecture on 2 December 2010.

Funding

Related publications and datasets