An Introduction to this Website
James J. Heckman
August 3, 2006
At a symposium on “Norms and Conditions of Engagement” in scientific disputes to be held August 8 in Wisconsin, my recent written exchange with Michael Sobel, published in the most recent issue of Sociological Methodology, will be a focus of attention. An important feature of the symposium is to expose students to what currently goes on in scientific disputes and how such disputes are resolved. It is in everyone’s interest to have full information about the case studies used by the sponsors of this symposium. To this end, I want to provide the participants in this symposium with some factual background material that will enable them to more accurately evaluate the “dispute” I had with Rafe Stolzenberg and Michael Sobel.
Background
In 2004, I was asked by Rafe Stolzenberg to contribute a paper to Sociological Methodology. I agreed to write a paper on causality, under the condition that I would be assigned a discussant with world-class credentials. We specifically discussed Nancy Cartwright (a professor of philosophy at the London School of Economics) with whom I taught a course at Oxford in the summer of 2005. I also suggested James Robins (a professor of epidemiology and biostatistics at Harvard University) as an alternate.
I was surprised to learn, in June 2005, that neither Cartwright nor Robins was my discussant. Instead, Michael Sobel, a professor of sociology at Columbia University was assigned as discussant. While I was greatly disappointed by this choice and felt it violated my agreement with Stolzenberg, I did not formally object. I received his comment in July 2005 and responded by September 2005. I received no editorial or substantive comments from Stolzenberg on my paper or my response to Sobel, nor did we ever dispute the intellectual content of my paper. Indeed, I was surprised and disappointed that I received no editorial comments from Stolzenberg about the content of my paper.
The Problem
When the proofs arrived in October 2005, the situation worsened. The article was badly typeset and, as my assistant can testify, there were hundreds of errors in the typeset paper and response to Sobel. Because many of the errors were substantial and not just cosmetic, I asked to be given a chance to review a second set of galleys. My request for a chance to inspect and edit a revised manuscript was
refused. In such cases, it is customary for editors and journals to give authors the chance to review revised galleys.
I appealed to the Publications Committee at the ASA and ASA Executive Director Sally Hillsman who supported Stolzenberg's decision to proceed with publication without letting me check that my corrections were made. At that point I asked for the right to withdraw my paper from the volume. My request was refused in a letter delivered by FedEx the day before Thanksgiving. I consulted a friend who is an attorney to see if it was possible to get an order blocking publication. He thought it possible. However, I decided against this action. No such order was ever issued. No legal fees were paid or legal action taken. My only request was to withdraw my paper. This request was refused because I had signed a publication agreement and was being held to it.
A Bigger Problem
While the problem of checking proofs was still unresolved, a friend sent me a copy of Sobel’s comment that was scheduled for publication. I was shocked to see that it was substantially altered from the document I received in July 2005 in a way that removed erroneous statements in his paper that I had pointed out in my rejoinder. His revised comment added material that responded to my initial rejoinder. As a result of these changes, my original rejoinder looked foolish. Stolzenberg planned to publish my original rejoinder without informing me of the changes Sobel made. Stolzenberg claims that Sobel never saw my rejoinder, and while I cannot prove that Sobel saw my rejoinder, I ask dispassionate readers to look at his original discussion, look at my rejoinder and compare his original with his final discussion and judge for themselves how credible this claim is. My paper, Sobel’s initial discussion, my response to Sobel, Sobel’s revised discussion, an email documenting the substantial changes to Sobel’s initial discussion sent to Sally Hillsman, Sobel’s initial and revised discussion (highlighted to show his changes) and my revised rejoinder are all posted at this website.
When I became aware of Sobel’s revision, I contacted Sally Hillsman who turned the matter over to the ASA Publications Committee. Again, I asked to withdraw my paper to escape this drain on my time.
Instead, I was offered the right to revise my rejoinder under the protection of the ASA Publications Committee. I revised my response with the promise that Sobel would not be permitted to revise his discussion further. This was the promise Stolzenberg originally granted me, as can be seen in his email to me.
Intellectual Disagreement?
At no time did I have an intellectual disagreement about this paper with Stolzenberg. No issue of scholarship or science was raised by him. As I noted before, Stolzenberg never gave me comments on my paper or my response to Sobel. I was disappointed that neither Nancy Cartwright nor James Robins was the discussant since that was part of my terms of engagement with Sociological Methodology. I was angry that I was not allowed to read a second round of galley proofs. I was shocked that professional ethics were violated in allowing Sobel to revise his original discussion--apparently in light of access to my rejoinder--and that I was not even told by Stolzenberg about the Sobel revision or given the right to revise my rejoinder to his revised comments. I wasted an enormous amount of time negotiating with Sally Hillsman, the president of the ASA and the Publications Committee. All I ever wanted was to withdraw. I certainly disagreed with both of Sobel’s comments as my responses to each document. Nowhere in the published exchange is there any unprofessional remark. I sent several emails to Sobel asking him to defend factually erroneous statements but he never responded.
Lurid Fantasies
I will not comment on the lurid fantasies posted on the symposium website except to say that I deeply respect life and would never destroy it or threaten to destroy it.
Guide to This Website
For the benefit of dispassionate observers, I have posted the following materials at this website, in this order:
- My published paper.
- My emails to and from Rafe Stolzenberg, the publishers and the ASA office regarding the badly typeset galley proofs.
- Sobel’s first comment on my paper dated July 28, 2005.
- A marked up copy of his comments showing his deletions and points of insertion in his second comment on my paper.
- My rejoinder to Sobel’s first comment.
- Email correspondence to the ASA Executive Office regarding Sobel’s altered discussion.
- Sobel’s second comment with Sobel’s additions to the first comment marked in yellow. These are also documented in one email in file (6).
- My revised rejoinder to Sobel’s revised comment.
- Supporting papers for my revised response.
Relevant Documents
 Heckman, James J., "The Scientific Model of Causality," Sociological Methodology, 35(1): 1-97.
Email correspondence regarding review of proofs
Sobel, Michael. "Discussion of 'The Scientific Model of Causality,'" version of July, 2005
Sobel, Michael. "Discussion of 'The Scientific Model of Causality,'"
version of July, 2005 with deletions marked in yellow.
Heckman, James J. "Rejoinder: Response to Sobel," version of September, 2005.
Email correspondence regarding discussion
Sobel, Michael. Discussion of "The Scientific Model of Causality," version of December, 2005, with Sobel's additions marked in yellow.
Heckman, James J. "Rejoinder: Response to Sobel," final version.
Supporting Materials
Heckman, James J. (1974). "Shadow Prices, Market Wages, and Labor Supply," Econometrica 42(4): 679-694. Heckman, James J. (1976). "The Common Structure of Statistical Models of Truncation, Sample Selection and Limited Dependent Variables and a Simple Estimator for Such Models," Annals of Economic and Social Measurement 5(4): 475-492.
Heckman, James J. (1978). "Dummy Endogenous Variables in a Simultaneous Equation System," Econometrica 46(4): 931-959. Heckman, James J. (1979). "Sample Selection Bias as a Specification Error," Econometrica 47(1): 153-162.
Heckman, James J. (1980). "Addendum to 'Sample Selection Bias as a Specification Error'," in Evaluation Studies Review Annual, Volume 5, edited by E. Stromsdorfer and G. Farkas. Beverley Hills: Sage Publications.
Heckman, James J. (1987). "Selection Bias and Self-Selection," in The New Palgrave: A Dictionary of Economics, edited by J. Eatwell and M. Milgate and P. Newman. London: Palgrave Macmillan Press. pp. 287-297. Heckman, James J. (1992). "Randomization and Social Policy Evaluation," in Evaluating Welfare and Training Programs, edited by C. Manski and I. Garfinkel. Cambridge, MA: Harvard University Press. pp. 201-230.
Heckman, J., R. LaLonde and J. Smith (1999) "The Economics and Econometrics of Active Labor Market Programs", O. Ashenfelter and D. Card (eds.), Handbook of Labor Economics, (North Holland, Vol. 3), Section 5: Social Experiments. Part 1, Part 2.
Heckman, James J. and Salvador Navarro. (2004). "Using Matching, Instrumental Variables, and Control Functions to Estimate Economic Choice Models," Review of Economics and Statistics 86(1): 30-57.
Heckman, James J. and Salvador Navarro. (2006). "Dynamic Discrete Choice and Dynamic Treatment Effects," forthcoming in Journal of Econometrics.
Heckman, James J. and Edward Vytlacil. (1999). "Local Instrumental Variables and Latent Variable Models for Identifying and Bounding Treatment Effects," Proceedings of the National Academy of Sciences 96(April): 4730-4734.
Heckman, James J. and Edward Vytlacil. (2001). "Local Instrumental Variables," in Nonlinear Statistical Modeling: Proceedings of the Thirteenth International Symposium in Economic Theory and Econometrics: Essays in Honor of Takeshi Amemiya, edited by C. Hsiao, and K. Morimue, and J. Powell. New York: Cambridge University Press.
Heckman, James J. and Edward Vytlacil. (2005). "Structural Equations, Treatment Effects and Econometric Policy Evaluation," Econometrica 73(3): 669-738.
|