Cover/Itinerary of Statistical Inference as Severe Testing: How to Get Beyond the Statistics Wars

SNEAK PREVIEW: Here’s the cover of Statistical Inference as Severe Testing: How to Get Beyond the Statistics Wars:

It should be out in July 2018. The “Itinerary”, generally known as the Table of Contents, is below. I forgot to mention that this is not the actual pagination, I don’t have the page proofs yet. These are the pages of the draft I submitted. It should be around 50 pages shorter in the actual page proofs, maybe 380 pages.




Excursion 1: How to Tell What’s True about Statistical Inference    

         Tour I: Beyond Probabilism and Performance 1
1.1   Severity Requirement: Bad Evidence, No Test (BENT) 3
1.2   Probabilism, Performance and Probativeness 11
1.3   The Current State of Play in Statistical Foundations: A view from a hot air balloon 22
         Tour II: Error Probing Tools vs. Logics of Evidence          29
1.4   The Law of Likelihood and the Likelihood Principle 29
1.5 Trying and Trying Again: The Likelihood Principle 41
Excursion 2: Taboos of Induction and Falsification 56
           Tour I: Induction and Confirmation                        56
2.1   The Traditional Problem of Induction 56
2.2    Is Probability a Good Measure of Confirmation? 63
         Tour II: Falsification, Pseudoscience, Induction    72
2.3   Popper, Severity and Methodological Probability 72
2.4   Novelty and Severity 87
2.5   Fallacies of Rejection and an Animal Called NHST 90
2.6   The Reproducibility Revolution (Crisis) in Psychology 94
2.7   How to Solve the Problem of Induction Now 105
Excursion 3: Statistical Tests and Scientific Inference 113
           Tour I: Ingenious and Severe Tests 113
3.1   Statistical Inference and Sexy Science: The 1919 Eclipse Test 115
3.2.   N-P Tests: an Episode in Anglo-Polish Collaboration 125
3.3   How to Do All N-P Tests Do (and more) While a Member of the Fisherian Tribe 139
         Tour II: It’s The Methods, Stupid 156
3.4   Some Howlers and Chestnuts of Statistical Tests 157
3.5  P-Values Aren’t Error Probabilities Because Fisher Rejected Neyman’s Performance Philosophy 166
3.6   Hocus-pocus: P-values Are Not Error Probabilities, Are Not Even Frequentist! 175
         Tour III: Capability and Severity: Deeper Concepts 181
3.7   Severity, Capability and Confidence Intervals (CIs) 181
3.8   The Probability our Results are Statistical Fluctuations: Higg’s Discovery 194
Excursion 4: Objectivity and Auditing 211
         Tour I: The Myth of “The Myth of Objectivity 211
4.1   Dirty hands: Statistical Inference is Sullied with Discretionary Choices 212
4.2   Embrace Your Subjectivity 218
         Tour II: Rejection Fallacies: Who’s Exaggerating What? 230
4.3   Significant Results with Overly Sensitive Tests: Large n problem 231
4.4   Do P-Values Exaggerate the Evidence? 237
4.5   Who’s Exaggerating? How to Evaluate Reforms Based on Bayes Factor Standards 251
         Tour III: Auditing: Biasing Selection Effects & Randomization 258
4.6 Error Control is Necessary for Severity Control 260
4.7 Randomization 278
         Tour IV: More Auditing: Objectivity and Model Checking 288
4.8   All Models are False 288
4.9   For Model Checking, They Come Back to Significance Tests 293
4.10 Bootstrap Resampling: My sample is a mirror of the universe 298
4.11 Misspecification (M-S) Testing in the Error Statistical Account 300
Excursion 5: Power and Severity 313
           Tour I: Power: Pre-data and Post-data 313
  5.1   Power Howlers, Trade-offs and Benchmarks 315
  5.2   Cruise Severity Drill: How Tail Areas (appear to) Exaggerate the Evidence 322
  5.3   Insignificant Results: Power Analysis and Severity 328
  5.4   Severity Interpretation of Tests: Severity Curves 336
           Tour II: How Not to Corrupt Power 342
  5.5   Power Taboos, Retrospective Power, and Shpower 342
  5.6   Positive Predictive Value: Fine for Luggage 351
         Tour III: Deconstructing the N-P vs. Fisher Debates 361
5.7   Statistical Theatre: “Les Miserables Citations” 361
5.8   Neyman’s Performance and Fisher’s Fiducial Probability 372
Excursion 6: (Probabilist) Foundations Lost, (Probative) Foundations Found 384
         Tour I: What Ever Happened to Bayesian Foundations? 384
6.1   Bayesian Ways: From Classical to Default 386
6.2   What are Bayesian Priors? A Gallimaufry 391
6.3   Unification or Schizophrenia: Bayesian Family Feuds 399
6.4   Is Bayes’ Rule Irrational? 406
6.5   Can You Change Your Bayesian Prior? 408
         Tour II: Pragmatic and Error Statistical Bayesians 415
6.6   Pragmatic Bayesians 415
6.7   Error Statistical Bayesians: Falsificationist Bayesians 423
           Souvenir (Z) Farewell 428



Categories: Announcement

Post navigation

10 thoughts on “Cover/Itinerary of Statistical Inference as Severe Testing: How to Get Beyond the Statistics Wars

  1. hadn’t been planning a cover like this, there was to be a picture, but when an idea of a wallpaper of words was included in samples from Cambridge University Press, I wondered if it could work as a way to convey the contents to readers. I wanted the red title to go right over the background words, but CUP thought this would be easier to read. I was prepared to forgo a picture in order to communicate the kinds of topics considered.
    Aside from conveying the contents, there are some possible metaphors. Here’s one: Once the concepts and problems in the background are seen through the perspective of one who holds a view of statistical inference as severe testing, they are seen in a different way.
    Share your impressions/metaphors.

  2. Mike Jacovides

    Good. There’s a chance that in the title of Excursion 4, Tour 2, you want “who’s” (as in 4.5) but maybe you don’t

  3. James T. Lee

    Exciting news! Cover clever too. Can hardly wait to buy my copy of this new book.

    • James: Very kind of you, I feel it’s a bit strange, but I was asked for a cover idea way earlier than I expected and somehow this took shape (it was initially Diana Gillooly’s idea–from CUP)

  4. By the way, this hasn’t been proofed yet, so please send typos. I already found a few. I’m working on all that now.

  5. Jose Perezgonzalez

    Looking forward to reading the book! The cover is perfect as it is! I don’t have any metaphor of my own, really, although I cannot help but going back to Taleb’s (borrowed from Popper?) black swan metaphor and perceiving error statistics as a tool which could help tame that bird (among other things). Haven’t found typos in the table of contents (unless switching title to lower cases, and ‘shpower’, were not intentional, of course.)

  6. Christian Hennig

    Good to see this… I’m particularly curious about Excursion 4 of course!

  7. khicks6

    Amazing! Thank you for all your brilliance, but more importantly – that you’ve shared it with us.

  8. Pingback: We're gonna have a discussion of Deborah Mayo's new book! - Statistical Modeling, Causal Inference, and Social Science

Blog at