Monthly Archives: January 2017

3 YEARS AGO (JANUARY 2014): MEMORY LANE

Posted on January 28, 2017 by Mayo
3 years ago...

3 years ago…

MONTHLY MEMORY LANE: 3 years ago: January 2014. I mark in red three posts from each month that seem most apt for general background on key issues in this blog, excluding those reblogged recently[1], and in green up to 3 others I’d recommend[2].  Posts that are part of a “unit” or a group count as one. This month, I’m grouping the 3 posts from my seminar with A. Spanos, counting them as 1.

January 2014

  • (1/2) Winner of the December 2013 Palindrome Book Contest (Rejected Post)
  • (1/3) Error Statistics Philosophy: 2013
  • (1/4) Your 2014 wishing well. …
  • (1/7) “Philosophy of Statistical Inference and Modeling” New Course: Spring 2014: Mayo and Spanos: (Virginia Tech)
  • (1/11) Two Severities? (PhilSci and PhilStat)
  • (1/14) Statistical Science meets Philosophy of Science: blog beginnings
  • (1/16) Objective/subjective, dirty hands and all that: Gelman/Wasserman blogolog (ii)
  • (1/18) Sir Harold Jeffreys’ (tail area) one-liner: Sat night comedy [draft ii]
  • (1/22) Phil6334: “Philosophy of Statistical Inference and Modeling” New Course: Spring 2014: Mayo and Spanos (Virginia Tech) UPDATE: JAN 21
  • (1/24) Phil 6334: Slides from Day #1: Four Waves in Philosophy of Statistics
  • (1/25) U-Phil (Phil 6334) How should “prior information” enter in statistical inference?
  • (1/27) Winner of the January 2014 palindrome contest (rejected post)
  • (1/29) BOSTON COLLOQUIUM FOR PHILOSOPHY OF SCIENCE: Revisiting the Foundations of Statistics

    .

  • (1/31) Phil 6334: Day #2 Slides

 

[1] Monthly memory lanes began at the blog’s 3-year anniversary in Sept, 2014.

[2] New Rule, July 30, 2016-very convenient.

 

Save

Save

Save

Save

Save

Categories: 3-year memory lane, Bayesian/frequentist, Statistics

The “P-values overstate the evidence against the null” fallacy

Posted on January 19, 2017 by Mayo
3077175-lg

.

The allegation that P-values overstate the evidence against the null hypothesis continues to be taken as gospel in discussions of significance tests. All such discussions, however, assume a notion of “evidence” that’s at odds with significance tests–generally Bayesian probabilities of the sort used in Jeffrey’s-Lindley disagreement (default or “I’m selecting from an urn of nulls” variety). Szucs and Ioannidis (in a draft of a 2016 paper) claim “it can be shown formally that the definition of the p value does exaggerate the evidence against H0” (p. 15) and they reference the paper I discuss below: Berger and Sellke (1987). It’s not that a single small P-value provides good evidence of a discrepancy (even assuming the model, and no biasing selection effects); Fisher and others warned against over-interpreting an “isolated” small P-value long ago.  But the formulation of the “P-values overstate the evidence” meme introduces brand new misinterpretations into an already confused literature! The following are snippets from some earlier posts–mostly this one–and also includes some additions from my new book (forthcoming). 

1. What you should ask…

When you hear the familiar refrain, “We all know that P-values overstate the evidence against the null hypothesis”, what you should ask is:

“What do you mean by overstating the evidence against a hypothesis?”

One honest answer is: Continue reading →

Categories: Bayesian/frequentist, fallacy of rejection, highly probable vs highly probed, P-values, Statistics

Winners of December Palindrome: Kyle Griffiths & Eileen Flanagan

Posted on January 14, 2017 by Mayo

Winners of the December 2016 Palindrome contest

Since both November and December had the contest word verifies/reverifies, the judges decided to give two prizes this month. Thank you both for participating!

 

kyle

.

Kyle Griffiths

Palindrome: Sleep, raw Elba, ere verified ire; Sir, rise, ride! If I revere able war peels.

The requirement: A palindrome using “verifies” (reverifies) or “verified” (reverified) and Elba, of course.

Statement: Here’s my December submission, hope you like it, it has a kind of revolutionary war theme. I have no particular history of palindrome-writing or contest-entering.  Instead, I found Mayo’s work via the recommendation of Jeremy Fox of Dynamic Ecology.  I am interested in her take on modern statistical practices in ecology, and generally in understanding what makes scientific methods robust and reliable.  I’m an outsider to philosophy and stats (I have an MS in Biology), so I appreciate the less-formal tone of the blog. I’m really looking forward to Mayo’s next book.

Book choice (out of 12 or more):  Principles of Applied Statistics (D. R. Cox and C. A. Donnelly 2011, Cambridge: Cambridge University Press)

Bio: Part-time Biology Instructor, Scientific Aide for California Dept. of Fish & Wildlife. Interested in aquatic ecology, fish population dynamics.

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

 

.

Eileen Flanagan

Palindrome: Elba man, error reels inanities. I verified art I trade, if I revise it in an isle. Error renamable.

The requirement: A palindrome using “verifies” (reverifies) or “verified” (reverified) and Elba, of course.

Bio: Retired civil servant with a philosophy Ph.D; a bit camera shy so used a stand-in for my photo. 🙂

Statement: I found your blog searching for information on fraud in science a few years ago, and now that I am retired, I am enjoying twisting my mind around palindromes and other word games that I find on-line. 🙂

Book choice (out of 12 or more):  For my book, I would like a copy of Error and the Growth of Experimental Knowledge (D. G. Mayo, 1996, Chicago: Chicago University Press).

 

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

Some of Mayo’s attempts, posted through Nov-Dec:

Elba felt busy, reverifies use. I fire very subtle fable.

To I: disabled racecar ties. I verified or erode, if I revise it. Race card: Elba’s idiot.

Elba, I rave to men: “I felt busy!” Reverified, I hide, I fire very subtle fine mote variable.

I deified able deities. I verified a rap parade. If I revise, I tied. Elba deified I.

Categories: Announcement, Palindrome

BOSTON COLLOQUIUM FOR PHILOSOPHY OF SCIENCE: Understanding Reproducibility & Error Correction in Science

Posted on January 7, 2017 by Mayo

BOSTON COLLOQUIUM FOR PHILOSOPHY OF SCIENCE

2016–2017
57th Annual Program

Download the 57th Annual Program

The Alfred I. Taub forum:

UNDERSTANDING REPRODUCIBILITY & ERROR CORRECTION IN SCIENCE

Cosponsored by GMS and BU’s BEST at Boston University.
Friday, March 17, 2017
1:00 p.m. – 5:00 p.m.
The Terrace Lounge, George Sherman Union
775 Commonwealth Avenue

  • Reputation, Variation, &, Control: Historical Perspectives
    Jutta Schickore History and Philosophy of Science & Medicine, Indiana University, Bloomington.
  • Crisis in Science: Time for Reform?
    Arturo Casadevall Molecular Microbiology & Immunology, Johns Hopkins
  • Severe Testing: The Key to Error Correction
    Deborah Mayo Philosophy, Virginia Tech
  • Replicate That…. Maintaining a Healthy Failure Rate in Science
    Stuart Firestein Biological Sciences, Columbia

 

boston-mayo-2017

Categories: Announcement, philosophy of science, Philosophy of Statistics, Statistical fraudbusting, Statistics

Blog at WordPress.com.