Hi Erick,
Thanks for your post and for writing "A Decidedly Insufficient Statistical Analysis." In response to your question, I have been an expert witness. I have presented model-based results in support of clients and in other cases I was asked to provide critiques of models developed by others.
You raise the question of the professional ethics involved in being an expert witness. I had the pleasure of chairing the ad hoc committee that developed the INFORMS Ethics Guidelines (INFORMS-Ethics-Guidelines). The Guidelines "recognize a responsibility to uphold high ethical standards on behalf of society, our organizations, and the profession." Following then President Brian Denton's charge, the Guidelines are intended to be aspirational rather than mandatory. So, regarding your question of ethics, if you are an expert witness the INFORMS Guideline recommend that you:
1. On behalf of society, be forthcoming, honest and objective
2. On behalf of the client you represent, be accurate, informed and rigorous
3. On behalf of the OR profession, be impartial, tolerant and vigilant
During the development of the INFORMS Ethics Guidelines the committee reviewed an interesting case that played out in the pages of Operations Research in the early 1970s. It involved two experts, one from MIT and one from the University of Chicago, regarding the vulnerability of U.S. anti-ballistic missiles (ABMs). One expert found the existing ABM system was vulnerable and required additional funding while the other expert found the opposite to be true. This prompted U.S. Senator Henry Jackson to write "Analysis, of course, varies greatly in quality. One often wishes that advisers with different points of view would confront each other directly and in public so that hidden or unstated assumptions could be revealed and the different modes of analysis explored." This, in fact, did happen as the two experts openly debated the topic in editorials in the New York Times.
The September 1971 issues of Operations Research dedicated 133 pages to the ABM topic, centered around a report by an ad hoc ORSA committee regarding an official exploration of the "professional conduct during the ABM debate." The ad hoc committee reported its findings to the ORSA Council, which led to the "Guidelines for the Practice of OR" being published in the journal. This in turn prompted another 42 pages of reactions in the February 1972 issue of OR. Among the reactions was the first ORSA President, Philip Morse, stating "I wish to dissociate myself from the action taken on behalf of the Society by the Council in approving the Report published in September 1971". Saul Gass stated, "Few if any professional societies are in a position to investigate the ethics and professional activities of any of its members or other persons involved in the society's area of interest."
If you have an opportunity to be an expert witness, I recommend reviewing the INFORMS Ethics Guidelines and establish what you consider to be ethical professional behavior. Perhaps it will help you avoid being called out by a Senator or setting off a debate about professional ethics.
Thanks again Erick for the post and the article.
Dave
------------------------------
David Hunt
Vice President
Oliver Wyman
Princeton NJ
------------------------------
Original Message:
Sent: 03-07-2023 09:05
From: Erick Wikum
Subject: A Decidedly Insufficient Statistical Analysis
The article describes legal proceedings that occurred after the 2022 Arizona gubernatorial election, won by Katie Hobbs, but contested by Kari Lake. Among the witnesses at a legal hearing was Richard Baris, director of Big Data Poll, who argued based on statistical analysis that but for problems with voting machines on election day, Kari Lake would have won. The title of my article was drawn from the legal opinion of the presiding judge, who did not find in Baris's or others' testimony clear and convincing evidence of misdeeds that affected the result of the election. That ruling was subsequently affirmed by the Arizona Court of Appeals.
How might statistical or other analysis provide clear and convincing evidence of anomalies or misconduct in an election sufficient to change the results?
Have you ever testified before a court of law, governmental agency, etc. concerning results of modeling or analysis? If so, please share a description of your experience. In testifying, what issues did you encounter regarding professional ethics?
I welcome your response, but request that in so doing, you refrain from political commentary.
------------------------------
Erick Wikum
Analytics Consultant
Wikalytics, LLC
Maineville OH
------------------------------