Journal Club: Hot Ideas in Statistics

Statistics 36-825

Instructors:
Rob Tibshirani (tibs at stanford dot edu)
Ryan Tibshirani (ryantibs at cmu dot edu)

Class time: Wednesdays 1-2:30pm, Baker 232M
Fridays 1:30-3pm, Porter A18C

Office hour: Mondays 1:30-2:30pm, Baker 228A or 229B

We will critically read and discuss hot papers in statistics. These papers can be new and potentially influential works, or they can be older important works that you may not have seen in other classes.

Participation

Each week, a pair of students will lead the presentation and discussion of the paper. Rough format: ~30 minutes paper summary, and ~50 minutes class discussion. Sign up here in pairs to lead one of the sessions.

In addition, the pair of students will produce scribed notes of their led session. This is to be submitted (by email to the instructors) no later than 1 week after the session. Rough format: overview of the paper, small simulations or examples if possible, comprehensive summary of the points made during the class discussion. Aim for 4-10 pages. Click here for the Latex template.

Paper list

  1. Statistical Modeling: The Two Cultures by Leo Breiman, 2001

    ----- Golden Oldies -----

  2. Regression Models and Life-Tables by David Cox, 1972

  3. The Central Role of the Propensity Score in Observational Studies for Causal Effects by Paul Rosenbaum and Don Rubin, 1983

    ----- False Discovery Rates -----

  4. Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing by Yoav Benjamini and Yosef Hochberg, 1995

  5. Sequential Selection Procedures and False Discovery Rate Control by Max Grazier G'Sell et al., 2014

    ----- Testing and Correlation -----

  6. Capturing Heterogeneity in Gene Expression Studies by Surrogate Variable Analysis by Jeff Leek and John Storey, 2007

  7. A Kernel Two-Sample Test by Arthur Gretton et al., 2012
  8. Brownian Distance Covariance by Gabor Szekely and Maria Rizzo, 2009

    ----- High-dimensional Inference -----

  9. Confidence Intervals and Hypothesis Testing for High-Dimensional Regression by Adel Javanmard and Andrea Montanari, 2014
  10. Exact-Post Selection Inference for Forward Stepwise and Least Angle Regression by Jonathan Taylor et al., 2014
  11. Controlling the False Discovery Rate via Knockoffs by Rina Foygel Barber and Emmanuel Candes, 2014
    ----- Supervised Learning -----

  12. Stability Selection by Nicolai Meinshausen and Peter Buhlmann, 2010
  13. Dropout Training as Adaptive Regularization by Stefan Wager and Sida Wang and Persy Liang, 2013
  14. Why Does Unsupervised Pre-training Help Deep Learning? by Dumitru Erhan et al., 2010
    ----- Reproducibility -----

  15. Why Most Published Research Findings are False by John Ioannidis, 2005