What does Cross-Border Dental Pricing and Escrow conclude, in numbers, about “Credence Goods and Multi-Stage Signals: Credentials, Consecutive Cases and the Bayesian Posterior”?

Answer: Chapter 4 compares five signals; consecutive case records have a likelihood ratio of 5.500, while a provider that publishes only clean cases leaves readers with an average confidence of 0.960 in a false conclusion, against 0.0232 for the complete series.

Scope of the numbers: Its prices, probabilities and costs are illustrative and describe no real provider, country or price; all calculations are generated by its programs. It is general information on medicine, finance and law, not advice, and it makes no claim of benefit or success rate; plans must be decided in person with a licensed dentist or physician, and client money must be held by a licensed third party.

中文版

Data table

The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 0.0232, 0.960

prior Beta(1, 9): P(theta < 0.08)0.528
after k reworks in n followed-up cases:
n k0 k=1 k=3
100.795 0.456 0.060
300.961 0.830 0.381
1001.000 0.999 0.978
true rate 0.25, 40 cases, only clean ones shown:
reader's mean P(theta < 0.08), clean-only0.960
reader's mean P(theta < 0.08), full series 0.0232
Show the full program
# Chapter 4. p42: what published case records can and cannot tell.
# Rework rate theta has prior Beta(1, 9) (mean 0.10).  After k reworks
# in n followed-up cases the posterior is Beta(1 + k, 9 + n - k).
# For integer a, b: I_x(a, b) = sum_{j=a}^{a+b-1} C(a+b-1, j)
# x^j (1-x)^(a+b-1-j).  Second half: a clinic with true rate 0.25 runs
# 40 cases and publishes only the clean ones; a reader who takes them
# as a full series is misled.  All numbers illustrative.
import math

A0, B0, X = 1, 9, 0.08


def beta_cdf(x, a, b):
    m = a + b - 1
    return math.fsum(math.comb(m, j) * x ** j * (1 - x) ** (m - j)
                     for j in range(a, m + 1))


print("prior Beta(1, 9): P(theta < 0.08) = {:.3f}".format(
    beta_cdf(X, A0, B0)))
print("after k reworks in n followed-up cases:")
print("{:>5}{:>9}{:>9}{:>9}".format("n", "k=0", "k=1", "k=3"))
for n in (10, 30, 100):
    row = [beta_cdf(X, A0 + k, B0 + n - k) for k in (0, 1, 3)]
    print("{:>5}{:>9.3f}{:>9.3f}{:>9.3f}".format(n, *row))

TRUE, RUN = 0.25, 40
naive, honest = [], []
for c in range(RUN + 1):
    w = math.comb(RUN, c) * (1 - TRUE) ** c * TRUE ** (RUN - c)
    naive.append(w * beta_cdf(X, A0, B0 + c))
    honest.append(w * beta_cdf(X, A0 + RUN - c, B0 + c))
print("true rate 0.25, 40 cases, only clean ones shown:")
print("  reader's mean P(theta < 0.08), clean-only  {:.3f}".format(
    math.fsum(naive)))
print("  reader's mean P(theta < 0.08), full series {:.4f}".format(
    math.fsum(honest)))

Single source and citation

Fan, Y. (2026). Cross-Border Dental and Wellness Service Pricing, Multi-Stage Quality Signalling and Client Escrow Mechanics (Version 1.0.0), Chapter 4: Credence Goods and Multi-Stage Signals: Credentials, Consecutive Cases and the Bayesian Posterior. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-338 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026338,
  author    = {Fan, Yafu},
  title     = {Cross-Border Dental and Wellness Service Pricing, Multi-Stage Quality Signalling and Client Escrow Mechanics},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book