Month: June 2020

Meeting 6 (June 25)

VI. (June 25) BONUS MEETING: Power, shpower, severity, positive predictive value (diagnostic model) & a Continuation of The Statistics Wars and Their Casualties

There will also be a guest speaker: Professor David Hand:
      “Trustworthiness of Statistical Analysis”

Reading:

SIST Excursion 5 Tour I (pp. 323-332; 338-344; 346-352),Tour II (pp. 353-6; 361-370), and Farewell Keepsake pp. 436-444

Recommended (if time) What Ever Happened to Bayesian Foundations (Excursion 6 Tour I)


Mayo Memos for Meeting 6:

-Souvenirs Meeting 6: W: The Severity Interpretation of Negative Results (SIN) for Test T+; X: Power and Severity Analysis; Z: Understanding Tribal Warfare

-JSM session I am part of on August 6: P-Values and “Statistical Significance”: Deconstructing the Arguments — Topic Contributed Panel

Nature paper just came out on which I’m a co-author: “Five Ways to Ensure Models Serve Society”

-SEV apps: Richard Morey. Newly updated Richard Morey SEV app.

-Selected blogposts on Power

  • 05/08/17: How to tell what’s true about power if you’re practicing within the error-statistical tribe
  • 12/12/17: How to avoid making mountains out of molehills (using power and severity)

Slides & Video Links for Meeting 6:

Slides: Mayo 2nd Draft slides for 25 June (not beautiful)

Video of Meeting #6: (Viewing Videos in full screen mode helps with buffering issues.)
VIDEO LINK:
https://wp.me/abBgTB-mZ

VIDEO LINK to David Hand’s Presentation: https://wp.me/abBgTB-mS
David Hand’s recorded Powerpoint slides: https://wp.me/abBgTB-n4
AUDIO LINK to David Hand’s Presentation & Discussion: https://wp.me/abBgTB-nm

Another link is here.

 

Meeting 5 (June 18)

.

V. (June 18) The Statistics Wars and Their Casualties

Reading:

SIST: Excursion 4 Tour III: pp. 267-286; Farewell Keepsake pp. 436-444

-Amrhein, V., Greenland, S., & McShane, B., (2019). Comment: Retire Statistical Significance, Nature, 567: 305-308.

-Ioannidis J. (2019). “The Importance of Predefined Rules and Prespecified Statistical Analyses: Do Not Abandon Significance.” JAMA. 321(21): 2067–2068. doi:10.1001/jama.2019.4582

-Mayo, DG. (2019), P‐value thresholds: Forfeit at your peril. Eur J Clin Invest, 49: e13170. doi: 10.1111/eci.13170

Recommended (and fun) P-values on Trial: Selective Reporting of (Best Practice Guides Against) Selective Reporting


Mayo Memos for Meeting 5:

-Souvenirs Meeting 5: S: Preregistration and Error ProbabilitiesT: Even Big Data Calls for Theory and FalsificationZ: Understanding Tribal Warfare

Bonus meeting: 25 June: See General Schedule

-Selected blogposts on Significance Test Wars from March 2019:

  • March 25, 2019: “Diary for Statistical War Correspondents on the Latest Ban on Speech.”
  • June 17, 2019: “The 2019 ASA Guide to P-values and Statistical Significance: Don’t Say What You Don’t Mean” (Some Recommendations)(ii)
  • July 19, 2019: The NEJM Issues New Guidelines on Statistical Reporting: Is the ASA P-Value Project Backfiring? (i)
  • November 4, 2019: On some Self-defeating aspects of the ASA’s 2019 recommendations of statistical significance tests
  • November 14, 2019: The ASA’s P-value Project: Why it’s Doing More Harm than Good (cont from 11/4/19)
  • November 30, 2019: P-Value Statements and Their Unintended(?) Consequences: The June 2019 ASA President’s Corner (b) 
  • December 13, 2019: “Les stats, c’est moi”: We take that step here! (Adopt our fav word of Phil Stat!) iii

-ASA 2016 Guide’s Six Principles (PDF)


Slides & Video Links for Meeting 5:

Slides: Draft Slides for 18 June (not beautiful)

Video Meeting 5: (Viewing in full screen mode helps with buffering issues.)
       VIDEO LINK: https://wp.me/abBgTB-n8

Meeting 4 (June 11)

getting beyond…

IV. (June 11) Rejection Fallacies: Do P-values exaggerate evidence? Jeffreys-Lindley paradox or Bayes/Fisher disagreement:

Reading:

SIST: Excursion 4 Tour II

Recommended (if time): Excursion 4 Tour I: The Myth of “The Myth of Objectivity” 


Mayo Memos for Meeting 4

–Souvenirs  Meeting 4: Q: Have We Drifted From Testing Country? (Notes From an Intermission); R: The Severity Interpretation of Rejection (SIR)

FUN! Take a look at Richard Morey’s newly updated SEV app. It will display P-values, power and SEV (click display options). You can change the default by clicking the tab details and then using that link. Don’t forget to change the range of parameter values. If you change n to 25, you’ll get the answers to the example I gave in meeting #2.

  1. Solutions to problems given in Meeting #2: With X̅ =154 (PDF); with X̅ = 152 (PDF)
  2. Using the app for simple P-values: I wasn’t able to use the board to draw the curves for different P-values in meeting #2. Here’s how you can view them using Morey’s app for simple P-values. 

How do you interpret it? This just came out in NEJM (in defending policies based on antibody tests). “In the world of randomized clinical trials, statisticians test scientific hypotheses by requiring a probability of less than 5% that the observed result could have occurred by chance.” (Waiting for Certainty on Covid-19 Antibody Tests — At What Cost?)  https://www.nejm.org/doi/full/10.1056/NEJMp2017739?source=nejmtwitter&medium=organic-social

-See details on Bonus Meeting: June 25.


Slides & Video Links for Meeting

Slides: (PDF)