SCS: Seminars

From MathWiki

This page is for links to materials for the SCS seminars in 2005-06. Please feel free to add anything that is relevant. You can use the 'discussion' page by clicking on the tab above for meta discussion. Contact Georges Monette ( if you would like an account for yourself or someone else.

SCS: Seminars 2007-08

Table of contents

Day 1 (October 20)

  1. Holland, P. (1986). Statistics and Causal Inference, J.Am.Statist.Assoc., 81, No. 396, 945-960.  (
  2. Chapter 2 of Berk's (2004) Regression Analysis: a constructive critique
  3. SCS Seminars: Measurement error

Day 2 (November 3)

We plan to discuss:

  1. Chapters 3 and 4 of Berk's book
  2. The paper handed out at the first meeting: Rubin, D. R. (2004). "Teaching Statistical Inference for Causal Effects in Experiments and Observational Studies." Journal of Educational and Behavioral Statistics, 29, 343-367. [Recent issues not available online at York. In stacks: Scott LB 2846 J68]


Day N (February 24, 2006)

We discussed Rosenbaum and Rubin (1983) on propensity scores and decided to have a look at something more recent with a more applied slant, namely

Another interesting link I found yesterday is:

The article addresses two issues:

  • the propensity score must be based on prediction of the treatment indicator with 'pretreatment' variables
  • by using a technique like boosting, one can regress on a large number of covariates but reduce error of prediction if it is likely than many covariates will have small partial effects

Finally, at the seminar we discussed a linear analogue to the propensity score. There is a discussion in Statistics:_Propensity_scores

Comments on Berk's book

SCS: Seminars comments on Berk's book

Richard Berk (2004) Regression Analysis: a constructive critique, Sage.

  • Web page (
  • Preface (
  • Reviews (


  1. Prologue: Regression Analysis as Problematic
  2. A Grounded Introduction to Regression Analysis
  3. Simple Linear Regression
  4. Statistical Inference for Simple Linear Regression
  5. Causal Inference for the Simple Linear Model
  6. The Formalities of Multiple Regression
  7. Using and Interpreting Multiple Regression
  8. Some Popular Extensions of Multiple Regression
  9. Some Regression Diagnostics
  10. Further Extensions of Regression Analysis
  11. What to Do

Some links on Rubin's causal model

Any additions, annotations, etc., are welcome. The list does not yet include introductory expository articles

A bibliography on causal inference

From [1] ( Feel free to add other items, to add brief comments and perhaps links to more extensive comments and to add links to URLs


(1) Angrist, J, Imbens, G., Rubin, D. (1996). ``Identification of Causal Effects Using Instrumental Variables, J.Am.Statist.Assoc., 91, No. 434, 444-455. JSTOR Stable URL (

Note: Comments need to be viewed separately:
Robins and Greenland (
Heckman (
Moffit (
Rosenbaum (
Rejoinder (

(2) Balke, A and Pearl, J. (1997) "Bounds on treatment effects from studies with imperfect compliance." Journal of the American Statistical Association, 92, 1171-1178.

(3) Copas, J.B. and Li, H.G. (1997). "Inference for Non-random Samples," J.R.Statist.Soc.B, 59, 1, 55-95. Stable URL (

(4) Cox, D.R. (1992). "Causality: Some Statistical Aspects," J.R.Statist.Soc.A, 155, 2, 291-301. Stable URL (

Abstract: After some brief historical comments on statistical aspects of causality, two current views are outlined their limitations sketched. One definition is that causality is a statistical association that cannot be explained away by confounding variables and the other is based on a link with notions based in the design of experiments. The importance of underlying processes or mechanisms is stressed. Implications for empirical statistical analysis are discussed.

(?) Dawid, A. P. (2000). "Causal inference without counterfactuals." Journal of the American Statistical Association, 94, 407-424 [With discussion]. Unstable URL (!xrn_6_0_A63841133?sw_aep=yorku_main)

Phil Dawid takes a contrarian view. Discussants are D. R. Cox, George Casella and Stephen P. Schwartz, Judea Pearl, James M. Robins, Sander Greenland, Donald B. Rubin, Glenn Shafer and Larry Wasserman. A better summary than the abstract is the end of Dawid's rejoinder:
After this lengthy article, discussion, and rejoinder, it may be helpful for the reader to attempt to plot each contributor in a multivariate space of attitudes to counterfactuals, having the following dimensions:
  • Fact-Fiction. Are counterfactuals to be regarded as genuine features of the external world, or are they purely theoretical terms?
  • Real-Instrumental. Can any inferences based on counterfactuals be allowed, or should they be restricted to those that could in principle be formulated without mention of counterfactuals?
  • Clear-Vague. Do counterfactual terms in a model have a clear relationship with meaningful aspects of the problem addressed? Can counterfactual constructions and arguments help to clarify understanding?
  • Helpful-Dangerous. Can use of counterfactuals streamline thinking and assist analyses, or do they promote misleading lines of argument and false conclusions?

(5) Frangakis, C. and Rubin, D. (2002). "Principal stratification in causal inference," Biometrics, 58, No. 1, 21-29.

(6) Glym our, C. and Spirtes, P. "Latent variables, causal models and overidentifying constraints," J. Econometrics (1988), 39, 175-198.

(7) Holland, P. (1986). ``Statistics and Causal Inference, J.Am.Statist.Assoc., 81, No. 396, 945-960. Stable URL (

(8) McKim, V. R. and S. P. Turner, Eds. (1997). Causality in Crisis? Notre Dame, Indiana, University of Notre Dame Press.

(9) Mealli, F., and Rubin, D. (2002). ``Assumptions allowing the estimation of direct causal effects, J. Econometrics, 112, 79-87.

(10) Pearl, J. (1995). "Causal diagrams for empirical research," Biometrika, 82,4, 669-710.

(11) Rosenbaum, P. and Rubin, D. (1983). ``The central role of the propensity score in observational studies for causal effects, Biometrika, 70, 1, 41-55. Stable URL ( [Note: This is the paper to which I referred. John.]

(12) Rosenbaum, P. (1984). ``From Association to Causation in Observational Studies: The Role of Tests of Strongly Ignorable Treatment Assignment, J.Am.Statist.Assoc., 79, No. 385, 41-48.

(13) Rosenbaum, P. and Rubin, D. (1985). "Constructing a Control Group Using Multivariate Matched Sampling Methods That Incorporate the Propensity Score," Am. Statist., 39, 1, 33-38.

(14) Rubin, D.R. (1991). "Practical Implications of Modes of Statistical Inference for Causal Effects and the Critical Role of the Assignment Mechanism," Biometrics, 47, 1213-1234.

(?) Rubin, D. R. (2004). "Teaching Statistical Inference for Causal Effects in Experiments and Observational Studies." Journal of Educational and Behavioral Statistics, 29, 343-367. [Recent issues not available online at York. In stacks: Scott LB 2846 J68]

(15) Stone,R. (1993). "The Assumptions on which Causal Inferences Rest," 'J.R.Statist.Soc.B,' 55, No. 2, 455-466.Stable URL (

(?) Wilkinson, L. and the Task Force on Statistical Inference (APA Board of Scientific Affairs) (1999). "Statistical Methods in Psychology Journals: Guidelines and Explanations," American Psychologist, 8, 594-604. Stable URL (

This article has a section entitled "Causality" presenting the group's reccomendations for publications in journals in psychology. The recommendations stress the concept of potential outcomes. The task force included Cohen, Rubin, Mosteller, Tukey, Wainer and Cronbach among its members or advisors.


(1) Cole, S.R. and Hernan, M.A. (2002). "Fallibility in estimating direct effects," Inter. J. Epidem., 31, 163-165.

(2) Gilbert P., et al. (2003). "Sensitivity Analysis for the Assessment of Causal Vaccine Effects on Viral Load in HIV Vaccine Trials," Biometrics, 59, 531-541.

(3) Greenland, S. (2000). "Causal analysis in the health sciences." Journal of the American Statistical Association 95: 286-289.

(4) Halloran, M. and Strutchiner, C. (1995). "Causal Inference in Infectious Diseases," Epidemiology, 6, 2, 142-151.

(5) Herting, J.R. (2002). "Evaluating and Rejecting True Mediation Models: A Cautionary Note," Prevention Science, 3, 4, 285-289.

(6) Kaufman, J.and Kaufman, S. (2002). "Commentary: Estimating causal effects," Int J. Epidem., 31, 2, 431-432.

(7) Kaufman, J. and Poole, C. (2000). "Looking back on "causal thinking in the health sciences"," Annual Rev. Pub. Health, 21, 101-119.

(8) Kraemer, H.C., et al. (2001). "How Do Risk Factors Work Together? Mediators, Moderators, and Independent, Overlapping, and Proxy Risk Factors," Am. J. Psychiatry, 158, 848-856.

(9) Kraemer, H.C., et al. (2002). "Mediators and Moderators of Treatment Effects in Randomized Clinical Trials," Arch. Gen. Psychiatry, 59, 877-883.

(10) Lavori, P., Dawson, R., and Mueller, T. (1994). "Causal Estimation of Time-Varying Treatment Effects in Observational Studies - Application to Depressive Disorder," Statist. Med., 13, 11, 1089-1100.

(11) Little, R. and Rubin, D. (2000). "Causal effects in clinical and epidemiological studies via potential outcomes: Concepts and analytical approaches," Annual Rev. Pub. Health, 21, 121-145.

(12) Little, R., Yau, L. (1998) "Statistical techniques for analyzing data from prevention trials: Treatment of no-shows using Rubin's causal model," Psychol. Meth., 3, 147-159.

(13) Olsen, J. (2003). "What characterises a useful concept of causation in epidemiology?" J. Epidem. Pub. Health, 57, 2, 86-88.

(14) Ten Have, T., et al. (2004). "Causal Models for Randomized Physician Encouragement Trials in Treating Primary Care Depression," J. Am. Statist. Assoc., 99, 465, 16-25.

(15) Tschacher, W. (1996). "The dynamics of psychosocial crises - Time courses and causal models," J. Nerv. and Mental Disease, 184,3, 172-179.

(16) Wilson, S. (1998). "Mind, meaning and mental disorder: The nature of causal explanation in psychology and psychiatry," Brit. J. Psychiatry, 172, 545-554.

  • Zanutto, Elaine L. (2006) "A Comparison of Propensity Score and Linear Regression Analysis of Complex Survey Data," Journal of Data Science, 4, 67-91. URL (