Get Adobe Flash player

327 E. Ridgeville Blvd, #122
Mount Airy, MD 21771-3900

240.744.0000

866.935.STAT (7828)

866.276.STAT (7828)

info@empiristat.com

www.empiristat.com

Privacy Data Shield Policy

News Event and Announcement Detail

March 15, 2016

Urgent P-Value Clarification Statement Issued by the ASA

 

A policy statement issued on March 7, 2016 by the American Statistical Association (ASA) Board of Directors warns statisticians and the research community in general over the misuse of p-values and aims to halt missteps in the quest for certainty.


The p-value is common way for judging the strength of scientific evidence, and its misuse is contributing to a number of research findings that cannot be reproduced.


ASA Executive Director Ron Wasserstein said that this is the first time that his 177-year-old organization has made explicit recommendations on such a foundational matter in statistics, and that the society’s members had become increasingly concerned that the p-value was being misapplied in ways that cast doubt on statistics generally.


With the statement, researchers are advised to avoid drawing scientific conclusions or making policy decisions based on p-values alone; and to describe not only the data that produced statistically significant results, but all statistical tests and choices made in calculations. Otherwise, results may seem inaccurately robust.


The statement provided six principles for using p-values:


  1. P-values can indicate how incompatible the data are with a specified statistical model.

  2. P-values do not measure the probability that the studied hypothesis is true, or the probability that the data were produced by random chance alone.

  3. Scientific conclusions and business or policy decisions should not be based only on whether a p-value passes a specific threshold.

  4. Proper inference requires full reporting and transparency.

  5. A p-value, or statistical significance, does not measure the size of an effect or the importance of a result.

  6. By itself, a p-value does not provide a good measure of evidence regarding a model or hypothesis.


EmpiriStat’s President, Dr. Nicole C. Close stated during an interview “I am very pleased to have our professional organization release this statement.  It is the very basis of our roles in clinical research as biostatisticians to bring the balance between statistical and clinical judgement, and not just a skimming of the p-values produced and displayed in our statistical output.”  Dr. Close went on to say “ I have been teaching these basic principles for many years, and to have this strong statement to further back me up with collaborators, is invaluable.”


The statement is available freely online to all at The American Statistician Latest Articles website. The ASA encourages all statisticians and researchers to review the statement and to share it with colleagues. Feedback is encouraged at ASA Connect.




Back to news...