What does Likelihood-Ratio Screening of Luxury Goods conclude, in numbers, about “East and West in the Sources: Suspecting the Neighbour of the Axe, and Peirce's Thermometer of Belief”?
Answer: Chapter 7 examines the suspected neighbour of the Liezi and Peirce's log odds of 1878.
Scope of the numbers: Brands are named only generically, the parameters are illustrative, all calculations are generated by the book's programs, and the book is not individual business advice. Chapter 3 gives the effective number of independent features (four features are worth only 2.007 under the illustrative matrix) and a one-number slope of 0.571.
Data table
The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python only
| naive | 4 cues x LR 3 = LR 81 (19.08 deciban), P(guilt) 0.8100 |
| rho n_eff exact LR deciban P(guilt) | |
| 0.0 | 4.00 81.00 19.08 0.8100 |
| 0.3 | 2.11 10.10 10.04 0.3472 |
| 0.6 | 1.43 4.80 6.82 0.2018 |
| 0.9 | 1.08 3.28 5.16 0.1472 |
| 1.0 | 1.00 3.00 4.77 0.1364 |
| axe found in the valley (LR 0.001): P(guilt) from naive 0.0042 | |
| if the cues came only from suspicion they carry no weight: | |
| LR of the cues given the facts | 1.00, P(guilt) stays 0.05 |
| the second look (same son, belief reset): every cue read as LR 1 |
Show the full program
# Chapter 7. p71: the man who lost his axe, as a correlated-evidence
# model. Four cues (gait, face, speech, bearing) each read as a likelihood
# ratio of 3 toward "the neighbour's son took it". If the four readings
# share one source (the observer's own suspicion) with correlation rho,
# the exact combined ratio is 81 ** (1 / (1 + 3 rho)) for equal cues
# (Chapter 2, p23). Prior of guilt 0.05 is illustrative. The found axe is
# modelled as evidence with ratio 0.001 against guilt.
import math
N_CUE, LR_CUE, PRIOR = 4, 3.0, 0.05
DB = 10.0 / math.log(10.0)
def post(prior, lr):
o = prior / (1.0 - prior) * lr
return o / (1.0 + o)
naive = LR_CUE ** N_CUE
print("naive: %d cues x LR %.0f = LR %.0f (%.2f deciban), P(guilt) %.4f"
% (N_CUE, LR_CUE, naive, DB * math.log(naive), post(PRIOR, naive)))
print(" rho n_eff exact LR deciban P(guilt)")
for rho in [0.0, 0.3, 0.6, 0.9, 1.0]:
shrink = 1.0 + (N_CUE - 1) * rho
lr = naive ** (1.0 / shrink)
print("%5.1f %7.2f %9.2f %8.2f %9.4f"
% (rho, N_CUE / shrink, lr, DB * math.log(lr), post(PRIOR, lr)))
found = 0.001
print("axe found in the valley (LR %.3f): P(guilt) from naive %.4f"
% (found, post(post(PRIOR, naive), found)))
print("if the cues came only from suspicion they carry no weight:")
print(" LR of the cues given the facts = 1.00, P(guilt) stays %.2f"
% PRIOR)
print("the second look (same son, belief reset): every cue read as LR 1")Single source and citation
Fan, Y. (2026). Multi-Feature Likelihood-Ratio Screening of Pre-Owned Luxury Goods: Fusing Stitch Pitch, Hardware Spectra and Leather Grain, and the Bayesian Boundary between Lab Referral and Instant Purchase (Version 1.0.0), Chapter 7: East and West in the Sources: Suspecting the Neighbour of the Axe, and Peirce's Thermometer of Belief. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-281 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026281,
author = {Fan, Yafu},
title = {Multi-Feature Likelihood-Ratio Screening of Pre-Owned Luxury Goods: Fusing Stitch Pitch, Hardware Spectra and Leather Grain, and the Bayesian Boundary between Lab Referral and Instant Purchase},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · Weight of Evidence: Single-Feature Likelihood Ratios, Decibans and the Sum of Four Features
- Chapter 2 · Double Counting: How Correlated Features Make Naive Bayes Overconfident
- Chapter 3 · Correcting for Correlation: the Effective Number of Independent Features, Exact Weights and a One-Number Slope
- Chapter 4 · A Loss Matrix and Three Zones: Instant Buy, Referral and Decline
- Chapter 5 · Measuring More or Stopping: Cheap Evidence Is Worth Most at the Boundaries
- Chapter 6 · Channel Priors, Audits and Calibration: What Gets Referred Decides What a Store Can Learn
- Chapter 8 · Closing the Loop: a Three-Zone Intake Procedure, the Refer-or-Buy Screener and a Pre-Registered Test