The following article is the fourth draft of the revised ASA Ethics Guidelines.  You are invited to read it and join the
discussion on it.
 

Post-JSM Draft for General Comments, October 8, 1998

 

 *****************************************************************************

The revisions contained (and bolded) in this draft result from comments and committee discussions since the August 27^th draft. This is the last draft that can be made available for public comment. The next revision will be sent to the ASA Board of Directors for final approval and publication.
 

Statisticians and other professionals are urged to give the following draft the widest possible distribution. While the finished product will represent the professional ethics policy of the American Statistical Association, the contents should reflect principles that will be effective as well for professional users of statistical methods in other disciplines and locations. Because of that goal, we invite comments from all statistical practitioners regardless of their discipline or location and from others who may have interests in this material, such as journal editors. Please reproduce and forward this material freely, but only with complete text. Please respond as soon as possible, but not later than October 15, 1998:
 

Direct post to the statistical ethics web site: http://tcnj.edu/~asaethic

Email to Ethics Committee Chair, Dr. John Gardenier at: drgarden@erols.com

Fax to Dr. Gardenier at: (301) 436-3705

Postal Mail to:

Ethics, American Statistical Association, 1429 Duke St., Alexandria, VA 22314-3415 USA
 
  Note: Bold text identifies the latest changes; bolding will be removed in the final version.
***************************************************************************************************************

 
 I. PREAMBLE

 A. Purpose
 

The ASA Ethical Guidelines for Statistical Practice are intended to help statistical practitioners make and communicate ethical decisions. All professional users of statistical methods should urge clients, employers, researchers, policy makers, journalists, and the public to expect statistical practice to be in accordance with these guidelines and to object when that is not the case. Students learning how to apply statistical theory to problems should be encouraged to follow these guidelines whether or not their target professional specialty will be "statistician." Employers, attorneys, and other clients of statistical practitioners have a responsibility to provide a moral environment that fosters use of the ethical guidelines.
 
 
 

B. Statistics and Society
 

The professional conduct of statistical analyses is essential to many aspects of society. The use of statistics in medical diagnoses and biomedical research may affect whether individuals live or die, whether their health is protected or jeopardized, and whether medical science advances or gets sidetracked. Life, death, and health, as well as efficiency, may be at stake in statistical analyses of transportation, occupational, or environmental safety. Early detection and control of new or recurrent infectious diseases depends on sound epidemiological statistics. Mental and social health may be at stake in psychological and sociological applications of statistical analysis.
 

Effective functioning of the economy depends on the availability of reliable, timely, and properly interpreted economic data. The profitability of individual firms depends in part on their quality control and their market research, both of which should rely on statistical methods. Agricultural productivity benefits greatly from statistically sound applications to research and to output reporting. Governmental policy decisions regarding public health, criminal justice, social equity, education, the environment, siting critical facilities, and other matters depend in part on sound statistics.
 

Scientific and engineering research in all disciplines require careful design and analysis of experiments and observations. To the extent that uncertainty and measurement error are involved -- that is, in most research -- research design, data quality management, analysis, and interpretation are all crucially dependent on statistical concepts and methods. Even in theory, much of science and engineering inherently involves statistical variability. Variability needs to be carefully examined both for random error and for possible researcher bias or wishful thinking.
 

C. Shared Values
 

Because of the dependence of society on sound statistical practice, all practitioners of statistics, whatever their training and occupation, have social obligations to perform their work in a professional, competent, and ethical manner. This document is directed to those whose primary occupation is statistics. Still, the principles expressed here should also guide the statistical work of professionals in all other disciplines that use statistical methods. All statistical practitioners are obliged to conduct their professional activities with responsible attention to:
 

1. The social value of one's work and the consequences of how well or poorly it is performed.

2. The need to avoid slanting statistical work toward predetermined outcomes. (It is acceptable to advocate a position; it is not acceptable to misapply statistical methods in doing so.)

3. Statistics as a science. (As in all science, understanding evolves. Statisticians have a body of established knowledge, but also many open issues that deserve frank discussion.)

4. Maintaining and upgrading competence in one's work.
 

In addition, good professional citizenship encourages:
 

5. Collegiality and civility with fellow professionals.

6. Support for improved public understanding of and respect for statistics.

7. Support for sound statistical practice, especially when it is unfairly criticized.

8. Exposure of dishonest or incompetent uses of statistics.

9. Service to the profession as a statistical editor, reviewer, or association official.

10. Preservation of data archives.
 

 A. Professionalism
 

1. Strive for practical significance, not just statistical significance. Typically, combine normative understanding of the subject matter issues, statistical protocols that are clearly defined before looking at the data, and power analyses or similar justification of both the practical significance of the study and the sample sizes needed for valid results.
 

2. Use data selection processes that will be consistent with clear, unambiguous, "transparent" treatment of the issues during the research and with accurate understanding of that treatment by readers of the resulting publication(s). Consider possible researcher or data provider bias as well as random variation.
 

3. Assure that adequate statistical expertise and adequate subject matter expertise both are applied to any planned study. If this criterion is not met initially, it is important to add the missing expertise before completing the study design.
 

4. Use only statistical methodologies suitable to the data and to valid results.
 

5. Do not join a research project unless you can expect to achieve valid results and unless you feel assured that your name will not be in any way associated with the project or resulting publications without your explicit consent.
 

6. Recognize that automated statistical computation alone does not constitute adequate statistical analysis; it is also necessary to understand the theory, the data, and the methods used in each statistical study. This goal is served best when a competent statistical practitioner is included early in the research design, preferably in the planning stage.
 

7. Respect and acknowledge the contributions and the intellectual property of others.
 

8. Disclose conflicts of interest, financial and otherwise, and resolve them. This may sometimes require divestiture of the conflicting personal interest or recusal or withdrawal from the professional activity. Examples where conflict of interest may be problematic include grant reviews, other peer reviews, and tensions between scholarship and personal or family financial interests.
 

9. Provide only such expert testimony as you would be proud to have peer reviewed.
 
 

B. Responsibilities to Funders, Clients, Employers
 

1. Where appropriate, allow a client or employer a choice between valid alternative statistical approaches that may vary in scope, cost, or precision.
 

2. Clearly state one's statistical qualifications and experience relevant to one's work.
 

3. Clarify the respective roles of different participants in studies to be undertaken.
 

4. Explain any expected adverse consequences of failure to follow through on an agreed sampling or analytic plan.
 

5. Apply statistical sampling and analysis procedures objectively, without regard for outcome.
 

6. Keep all statistical methods publicly available; they are not proprietary, although

specific implementations of them may be proprietary. (Not applicable where employment law or contract dictates that new methods derived by employees are the intellectual property of the employer.)
 

7. Guard privileged information of the employer/client/funder.
 

8. Fulfill all commitments.
 

9. Accept full responsibility for one's professional performance.
 
 

C. Responsibilities in Publications and Testimony
 

1. Maintain personal responsibility for all work bearing one's name; avoid undertaking

work or coauthoring publications for which one would not want to acknowledge responsibility. Conversely, accept (or insist upon) appropriate authorship or acknowledgment for professional statistical contributions to research and the resulting publications or testimony.
 

2. Report statistical and substantive assumptions made in the study.
 

3. In co-authored publications, clearly identify the responsibility(ies) for statistical work that may affect interpretation of the results and conclusions.
 

4. The ethically preferred rule for authorship order in statistical publications is by degree of intellectual contribution to the study and to the material to be published, to the extent such ordering can feasiblely be determined. When some other rule of authorship order is used in a statistical publication, the rule used should be disclosed in a footnote or endnote. (Where authorship order by contribution is assumed by those making decisions about hiring, promotion, or tenure, for example, failure to disclose an alternative rule may improperly damage or advance careers.)
 

5. Account for all data considered in a study and explain the sample(s) actually used.
 

6. Report the sources and assessed adequacy of the data.
 

7. Report the data cleaning and screening procedures used, including any imputation.
 

8. Report the statistical methods used and their relation to the assumptions, clearly and fully so as to support statistical peer review.
 

9. In publications or testimony, identify the ultimate paying sponsor of the study, the stated purpose, and the intended use of the study results.
 

10. When reporting analyses of volunteer data or other data not representative of a defined population, include appropriate disclaimers.
 

11. Report the limits of statistical inference of the study and possible sources of error, both random and systematic. For example, disclose any significant failure to follow through fully on an agreed sampling or analytic plan and explain any resulting adverse consequences.
 

12. Share (non-proprietary) data used in published studies to aid peer review and replication.
 

13. As appropriate, promptly and publicly correct any errors discovered after publication.
 

14. Write with consideration of the intended audience. (For the general public, convey the scope, relevance, and conclusions of a study without technical distractions. For the professional literature, strive to answer the questions likely to occur to your peers.)

D. Responsibilities to Research Subjects
 

1. Know and adhere to applicable rules for protection of human subjects, including protection of special populations who may not be fully able to protect their own interests. Assure adequate planning to support the practical value of the research, the validity of expected results, and consideration of all ethical issues involved. [U. S. federal guidelines are administered by the Office for Protection from Research Risks (OPRR) at the National Institutes of Health (NIH.) The regulations are defined in Title 45 of the Code of Federal Regulations, Chapter 46 (45CFR46). State and local rules, private organization guidelines, and regulations or guidelines in other countries may differ.]
 

2. Avoid use of excessive numbers of research subjects by making informed recommendations for study size. These may be based on prospective power analysis or the planned precision of the study endpoint(s), also considering the feasibility of obtaining research subjects and the value of the data elements to be collected.
 

3. Avoid excessive risk to research subjects and excessive imposition on their time and privacy.
 

4. Protect the privacy and confidentiality of research subjects and the data they provide.
 

5. Prior to participating in a study involving human beings, analyzing data from such a study, or accepting resulting manuscripts for review, ensure that appropriate subject approvals were obtained. (This will lower your risk of learning only after the fact that you had collaborated on an unethical study.)
 

6. Avoid or minimize the use of deception. Where it is necessary, as in some psychological and sociological research, encourage independent ethical review and monitoring of the research.
 

7. Where full disclosure of study parameters to subjects or to other investigators is not advisable, as in some randomized clinical trials, at least inform them of the nature of the information withheld and the purpose of withholding it.
 

8. Know and adhere to appropriate guidelines for protecting special populations, such as prisoners and mentally impaired individuals, in research involving such people. The applicable categories and appropriate guidelines may be defined by regulations or by ethical review boards.
 

9. Know and adhere to appropriate animal welfare guidelines in research involving animals. Assure that normative understanding of the subject matter combines with power analysis or similar justification to support the practical value of the research and the sample sizes to be used.
 

E. Responsibilities to Research Team Colleagues
 

1. Inform colleagues of other disciplines about relevant aspects of statistical ethics.
 

2. Promote effective and efficient use of statistics by the research team.
 

3. Respect the ethical obligations of members of other disciplines as well as one's own.
 

4. Assure professional quality reporting of the statistical design and analysis.
 

5. Avoid compromising statistical validity for expediency.
 

F. Responsibilities to Other Statisticians or Statistical Practitioners
 

1. Promote review of one's work by sharing data and methods adequately.
 

2. Be willing to help strengthen the work of others through appropriate peer review. When doing so, complete the review promptly and well.
 

3. Assess methods, not individuals.
 

4. Respect differences of opinion.
 

5. Make decisions regarding statistical practitioners' hiring, firing, promotion, work assignments, publications and presentations, candidacy for offices and awards, and other professional matters on the basis of the professional qualifications and contributions of the individual. It is the policy of the American Statistical Association to deplore harassment of or discrimination against statistical practitioners on professionally irrelevant bases such as: Race, Color, Ethnicity, Sex, Sexual Orientation, National Origin, Age, Religion, or any Disability.
 

G. Responsibilities Regarding Allegations of Misconduct:
 

1. Avoid condoning or appearing to condone careless, incompetent, or unethical conduct of

statistical studies in one's working environment or elsewhere.
 

2. It is not sufficient to deplore plagiarism and data fabrication or falsification. Misconduct more broadly includes all professional dishonesty, by commission or omission, and, within the realm of professional activities and expression, all harmful disrespect for people, their intellectual and physical property, and their reputations.
 

3. Recognize that differences of opinion and honest error do not constitute misconduct; they warrant discussion but not accusation. Questionable scientific practices may or may not constitute misconduct, depending on their nature and the definition of misconduct used.
 

4. If involved in a misconduct investigation, know and follow prescribed procedures. Maintain confidentiality during an investigation, but disclose the results honestly after the investigation has been completed.
 

5. Following a misconduct investigation, support efforts of the accused, the witnesses, and

those reporting the possible scientific error or misconduct to resume their careers in as normal a manner as possible.
 

6. Do not condone retaliation against, or blackballing of, those who responsibly call attention to possible scientific error or misconduct.
 

H. Responsibilities of Organizations or Individuals Employing Statistical Practitioners, such as Employers, Attorneys, or other Clients.
 

1. Recognize that results of valid statistical studies cannot be guaranteed to conform to what those commissioning the study, or the statistical practitioner(s), may have expected or desired. Any measures taken to assure a particular outcome will lessen the validity of the analysis.
 

2. Valid results can only result from competent work in a moral environment. Pressure on a statistical practitioner to deviate from the Guidelines above is likely to damage both the validity of study results and the professional credibility of the practitioner.
 

3. Statistical practitioners have ethical obligations to keep methodology publicly available for the benefit of society at large; proprietary reservation of statistical methodology for private profit, if justified at all, should be as limited as possible in time and scope.
 

4. Statistical practitioners and others have a social responsibility to support sound statistical analysis and to expose incompetent or corrupt statistical practice. In cases of conflict, statistical practitioners and those employing them are encouraged to resolve issues of ethical practice privately if possible. If private resolution is not possible, recognize that statistical practitioners have an ethical obligation to expose incompetent or corrupt practice before it can cause avoidable harm to research subjects or to society at large.
 

5. Within organizations and within professions using statistical methods generally, statistical practitioners who have greater prestige, power, or status have a responsibility to protect the professional freedom and responsibility of more subordinate statistical practitioners to comply with these Guidelines.
 

6. Statistical practitioners should not be included in authorship or in acknowledgment regarding projects or publications without their explicit permission.

*****************************************************************************

Sources:
 

1989 Ethical Guidelines for Statistical Practice, American Statistical Association

1985 Declaration on Professional Ethics of the International Statistics Institute

W. E. Deming's personal ethics code (1972)

Formal resolutions of the ASA Board of Directors

1993 Code of Ethics of the Association for Computing Machinery (ACM)

RESPONSIBLE SCIENCE: Ensuring the Integrity of the Research Process, National Academy of Science, 1992

Integrity and Misconduct in Research, the1995 report of the DHHS Commission on Research Integrity.

Comments attached to survey responses regarding a 1994 ASA Workshop on Ethical Issues in Statistical Expert Testimony

Comments and discussions on earlier drafts of these guidelines.

American Statistical Association Committee on Professional Ethics members (1998):
 

John C. Bailar, Paula H. Diehr, Susan S. Ellenberg, John S. Gardenier (Chair),

Lilliam Kingsbury, David M. Levy, Richard E. Potthoff, Jerome Sacks, Chamont W. Wang
 

ASA Executive Director, Ray A. Waller; ASA Staff Liaison, Derek Lawlor

******************************************************************************
 Final DRAFT for General Comment - October 8, 1998