Implementation of Guidelines for Ethical Statistical Practice Illustrated (February 26, 2021)

Rochelle Tractenberg (Georgetown University) walks through how to use a stakeholder analysis template during the session.Rochelle Tractenberg (Georgetown University) presents steps necessary to make and then support a decision.

Rochelle Tractenberg (Georgetown University) was the instructor of the seventh of a series of tutorials that focus on topics that are essential for all statisticians and data scientists to be familiar with.  While this topic may not involve the technical methods, software or coding of previous tutorials, ethical practice is not to be ignored.  In this tutorial Rochelle provided a careful and deliberate approach to what are often subtle decisions that arise in the work of all statisticians and data scientists.

“When an ethical challenge arises, it must be recognized and a decision must be made.”
Rochelle Tractenberg (Georgetown University)

The Topics

In the first segment of this tutorial Rochelle laid out the seven tasks in “the data science pipeline”.  And, through the use of a poll Rochelle had the attendees make obvious that statisticians and data scientists are involved in all of these tasks in their work. These tasks include:

  1. Planning/Designing
  2. Data collection/munging/wrangling
  3. Analysis (perform or program to perform)
  4. Interpretation
  5. Documenting your work
  6. Reporting your results/communication
  7. Engaging in team work

Next, through a series of exercises she demonstrated how the ASA’s Guidelines on Ethical Practice (below) are relevant in every step of this process.  

  1. Professional Integrity and Accountability
  2. Integrity of data and methods
  3. Responsibilities to Science/Public/Funder/Client
  4. Responsibilities to Research Subjects 
  5. Responsibilities to Research Team Colleagues
  6. Responsibilities to Other Statisticians or Statistics Practitioners
  7. Responsibilities Regarding Allegations of Misconduct
  8. Responsibilities of Employers, Including Organizations, Individuals, Attorneys, or Other Clients Employing Statistical Practitioners

Rochelle helped make it clear by asking participants to connect aspects of the guidelines to the type of work that is being engaged in. Recognizing how the Guidelines can map to actual aspects of work can lead to a better understanding of the relevant ethical issues, and ethical statistical and data science practice in general.  More importantly, Rochelle demonstrated how better understanding and ownership of how these ethical aspects come into play enables decision making as to how one can move forward in an ethical manner.

In addition, Rochelle provided attendees with a framework for stakeholder analysis.  She featured a template that can be used to map out all the possible ways in which opportunities for ethical issues may come into question.  She demonstrated how using this framework as part of the research process, even in a simple way, can help researchers anticipate where decisions may need to be made in order to mitigate unwanted interference.

During the final segment of the tutorial Rochelle reviewed ethical reasoning — methods that one can use to help identify and evaluate alternative decisions when confronted with ethical issues — along with the steps that are necessary to make a decision but also to support this decision once it is made.  She reviewed an array of possible options such as doing nothing (not an ethical option, but it is an option), consulting with a peer or supervisor, using professional guidelines or other resources, to reporting the violations of policy, ethical guidelines or law.

“Because society depends on informed judgments supported by statistical methods, all practitioners of statistics—regardless of training and occupation or job title—have an obligation to work in a professional, competent, respectful, and ethical manner.”
ASA’s Ethical Guidelines for Statistical Practice

Access to Materials

Once again, the Essential Data Science for Business tutorials provide so many details! Models, methods, software, examples!  If you were not able to attend this live session you can still access a recording of the session along with links to the slides that the presenter used during this session.  Use the Registration Option "Post Session Access" on the event webpage, pay the $35 fee, and NISS will provide you with access to all the materials for this session. Or register for the full series of ten tutorials, and NISS will provide all the links as well.

What’s Up Next?

Here are the topics of the final tutorial sessions that will presented in 2021:
•    March 10, 2021: Jie Chen (Wells Fargo), Tim Hesterberg (Google) and Juan Li (Google) "Domain Knowledge and Application Areas" (see event page!)
•    March 24, 2021: Sam Woolford (Bentley University) "Non-Analytic Skills for Analytic Consulting Success" (see event page!)
•    April/May (TBA), 2021: Victor Lo & Dessislava Pachamanova, "Prescriptive Analytics and Optimization" Information for registering and attending these sessions will be posted on the NISS website soon!

Friday, February 26, 2021 by Glenn Johnson