m

F Nous contacter

0
     
Post-edited

H 2 The power of heterogeneous large-scale data for high-dimensional causal inference

Auteurs : Bühlmann, Peter (Auteur de la Conférence)
CIRM (Editeur )

Loading the player...
big data causal inference genomics inappropriateness of regression graphical and structural equation models invariant prediction invariance assumption identifiability statistical confidence gene perturbation experiments nonlinear structural equation models questions of the audience

Résumé : We present a novel methodology for causal inference based on an invariance principle. It exploits the advantage of heterogeneity in larger datasets, arising from different experimental conditions (i.e. an aspect of "Big Data"). Despite fundamental identifiability issues, the method comes with statistical confidence statements leading to more reliable results than alternative procedures based on graphical modeling. We also discuss applications in biology, in particular for large-scale gene knock-down experiments in yeast where computational and statistical methods have an interesting potential for prediction and prioritization of new experimental interventions.

Codes MSC :
62Fxx - Parametric inference
62H12 - Multivariate estimation
62Pxx - Applications of statistics

    Informations sur la Vidéo

    Langue : Anglais
    Date de publication : 18/02/16
    Date de captation : 03/02/2016
    Collection : Research talks
    Format : MP4 (.mp4) - HD
    Durée : 01:02:17
    Domaine : Probability & Statistics
    Audience : Chercheurs ; Doctorants , Post - Doctorants
    Download : http://videos.cirm-math.fr/2016-02-03_Buhlmann.mp4

Informations sur la rencontre

Nom du congrès : Thematic month on statistics - Week 1: Statistical learning / Mois thématique sur les statistiques - Semaine 1 : apprentissage
Organisteurs Congrès : Ghattas, Badih ; Ralaivola, Liva
Dates : 01/02/16 - 05/02/16
Année de la rencontre : 2016
URL Congrès : http://conferences.cirm-math.fr/1615.html

Citation Data

DOI : 10.24350/CIRM.V.18918403
Cite this video as: Bühlmann, Peter (2016). The power of heterogeneous large-scale data for high-dimensional causal inference. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.18918403
URI : http://dx.doi.org/10.24350/CIRM.V.18918403

Bibliographie

  1. [1] Hauser, A., Bühlmann, P. (2015). Jointly interventional and observational data: estimation of interventional Markov equivalence classes of directed acyclic graphs. Journal of the Royal Statistical Society, Series B, 77(1), 291-318 - http://dx.doi.org/10.1111/rssb.12071

  2. [2] Hauser, A., & Buhlmann, P. (2012). Characterization and greedy learning of interventional Markov equivalence classes of directed acyclic graphs. Journal of Machine Learning Research, 13(1), 2409-2464 - http://dl.acm.org/citation.cfm?id=2503308.2503320

  3. [3] Kalisch, M., Machier, M., Colombo, D., Maathuis, M.H., & Buhlmann, P. (2012). Causal inference using graphical models with the R package pcalg. Journal of Statistical Software, 47(11), 1-26 - http://dx.doi.org/10.18637/jss.v047.i11

  4. [4] Maathuis, M.H., Colombo, D., Kalisch, M. & Buhlmann, P (2010). Predicting causal effects in large-scale systems from observational data. Nature Methods, 7(4), 247-248 - http://dx.doi.org/10.1038/nmeth0410-247

  5. [5] Maathuis, M.H., Kalisch, M., & Buhlmann, P. (2009). Estimating high-dimensional intervention effects from observational data. Annals of Statistics, 37(6A), 3133-3164 - http://dx.doi.org/10.1214/09-aos685

  6. [6] Meinshausen, N., Hauser. A. Mooij, J., Peters, J., Versteeg, P. & Bühlmann, R. (2015). Causal inference from gene perturbation experiments: methods, software and validation. Preprint. -

  7. [7] Peters, J., Bühlmann, R, & Meinshausen, N. (2015). Causal inference using invariant prediction: identification and confidence intervals. - http://arxiv.org/abs/1501.01332v3

  8. [8] Stekhoven, D.J., Morass, I., Sveinbjornsson, G., Hennig, L, Maathuis, M.H., & Buhlmann, P (2012). Causal stability ranking. Bioinformatics, 28(21), 2819-2823 - http://dx.doi.org/10.1093/bioinformatics/bts523



Ressources Electroniques

Books & Print journals

Recherche avancée


0
Z