View Only

Principle F: Responsibilities to Other Statisticians or Statistics Practitioners

By Michael Hawes posted 10-17-2018 16:31

   
The ASA Committee on Professional Ethics seeks input on the Ethical Guidelines for Statistical Practice, which are permanently linked here:
http://www.amstat.org/ASA/Your-Career/Ethical-Guidelines-for-Statistical-Practice.aspx

If you would like to contribute a recommendation for revision to the Guidelines, or for a comment for the linked discussion, we have created discussion threads for each of the Guidelines' individual principles. Please comment on the principle(s) most directly related to your suggestion(s).

Your suggestions should be as specific and complete as possible so that the Committee or its designated Working Group can review and consider your suggestions and input. All suggestions received through these discussion threads will be considered by the Committee.

The practice of statistics requires consideration of the entire range of possible explanations for observed phenomena, and distinct observers drawing on their own unique sets of experiences can arrive at different and potentially diverging judgments about the plausibility of different explanations. Even in adversarial settings, discourse tends to be most successful when statisticians treat one another with mutual respect and focus on scientific principles, methodology and the substance of data interpretations.  Out of respect for fellow statistical practitioners, the ethical statistician:

  1. Promotes sharing of data and methods as much as possible and as appropriate without compromising propriety. Makes documentation suitable for replicate analyses, metadata studies, and other research by qualified investigators.
  2. Helps strengthen the work of others through appropriate peer review; in peer review, respects differences of opinion and assesses methods, not individuals. Strives to complete review assignments thoroughly, thoughtfully, and promptly.
  3. Instills in students and non-statisticians an appreciation for the practical value of the concepts and methods they are learning or using.
  4. Uses professional qualifications and contributions as the basis for decisions regarding statistical practitioners' hiring, firing, promotion, work assignments, publications and presentations, candidacy for offices and awards, funding or approval of research, and other professional matters.
​
2 comments
20 views

Related Content

Permalink

https://community.amstat.org/ethics/blogs/michael-hawes/2018/10/17/principle-f

Comments

Rochelle Tractenberg
06-24-2019 17:41

I have an additional (or, alternate) suggestion to the one I posted 29 Jan 2019, relating to adding an element in these GLs that articulate an obligation of all practicing statisticians/data scientists (and those who practice stats/data science, but do not have this job title or self-identify as practitioners).  I recommend adding the following, to either Principle F - as part of their obligations to other practitioners - or Principle A -as part of their professional integrity: 
“Each ASA member should encourage and support, to the extent possible, adherence to the ASA Ethical Guidelines by all statistics practitioners regardless of ASA membership.”

("Each ASA member should" could be replaced by "The ethical statistician will...")

As currently written (adopted in 2018), the GLs *suggest* that the ASA as an organization does not intend for membership in the ASA to be contingent on following the ASA GLs. That is,  the ASA does not describe failures to follow the ASA GLs as “inconsistent with ASA membership”. This tends to undermine the need to follow these guidelines - suggesting that they are only "norms" for those who are interested in following them, and not the ethical norms that should be expected by all ASA members and statistics practitioners. By contrast, the Royal Statistical Society in the UK (http://www.rss.org.uk/Images/PDF/join-us/RSS-Code-of-Conduct-2014.pdf) states in their 2014 revision that their “code of conduct” “defines the actions and behavior expected of RSS fellows practicing in their everyday professional life and has been drawn up to reflect the standards of conduct and work *expected of all practicing statisticians* " (emphasis added). By contrast, the ASA GLs’ Preamble (purpose of the GLs) suggest (but never assert) that *the ethical practitioner follows the ASA GLs*, although there, and throughout the GLs it is implied that, if the practitioner does not follow the ASA GLs, then they would not considered “the ethical statistician…”. The ASA GL Preamble states, “The principles expressed here should guide both those whose primary occupation is statistics and those in all other disciplines who use statistical methods in their professional work.” If all practitioners should follow the GLs, then failing to follow them is plausibly inconsistent with ASA Membership - but this is not stated. The Association for Computing Machinery Code of Ethics (also 2018) states in 4.2, “Each ACM member should encourage and support adherence by all computing professionals *regardless of ACM membership* ”, emphasis added. The ACM also states that its Code is intended for all those who use computing in an impactful way (i.e., whether or not they are called "computing professionals" or are members of the ACM). 

So my suggestion is to specify a responsibility to follow the GLs and encourage others who practice statistics to do so; and for the committee to consider stating that failures to follow the GLs are inconsistent with membership in the ASA.

Rochelle Tractenberg
01-29-2019 15:35

I have a suggestion for revising element 3 of Principle F. I believe that practitioners bear a responsibility - to the practicing community - to follow these Guidelines (GLs) to the best of their ability. None of the GL principles suggests this is a responsibility, and I think at least one should do so. I would suggest amending element 3 so that instead of saying what it says now (2018 revision): "Instills in students and non-statisticians an appreciation for the practical value of the concepts and methods they are learning or using" it would say instead, "Instills in students and non-statisticians an appreciation for the practical value of the concepts and methods they are learning or using, as well as a sense of their obligation to follow these Guideline Principles throughout their practice."