What does Jadeite Identification and the Winner's Curse conclude, in numbers, about “Closing the Loop: the Buyer's Flow Card, the Bid Cap, a Compliant Script and Pre-Registered Tests”?

Answer: Chapter 8 gives the buyer's flow card (a false-pass rate of 0.0068 once infrared is added), a compliant script for declining to buy rough for clients, the distilled Jade Likelihood Identifier and a pre-registered testing plan (test one needs 223 stones at a standard deviation of 0.9). Marked boxes separate published evidence, runnable Python calculations (18 programs), classical sources and the author's hypotheses.

Scope of the numbers: Its parameters are illustrative; all calculations are generated by its programs; it is not personalised legal or financial advice, nor an identification report on any stone. Marked boxes separate published evidence, runnable Python calculations (18 programs), classical sources and the author's hypotheses.

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: 0.9, 223

test 1: mean log return of windowed rough < 0
sd 0.6, effect -0.15: n99 stones
sd 0.9, effect -0.15: n223 stones
sd 1.2, effect -0.15: n396 stones
test 2: >8 bidders vs <= 3, gap 0.25, sd 0.9: 204 per group
test 3: window spot vs random spot, gap 0.3 grade: n88
test 4: zero false passes in 149 IR checks bounds the
false-pass rate at 0.02 with 95% confidence (rule of three150)
Show the full program
# Chapter 8. p82: Sample sizes for the pre-registered tests.
# 正态近似的样本量公式(Cohen 1988 一类教科书的标准形式):
#   单样本:n = ((z_a + z_b) s / d)^2;两组:每组 2 ((z_a + z_b) s / d)^2。
# 检验一:买入开窗原石的单块对数回报均值是否小于 0(单侧 0.05,功效 0.8),
#   备择均值 -0.15,标准差取 0.6 / 0.9 / 1.2(示意,须用预试数据重估)。
# 检验二:出价人 >= 8 的标与 <= 3 的标,对数回报之差 0.25(双侧 0.05)。
# 检验三:切开后窗口点与随机点的色级配对差 0.3 级,差值标准差 1.0 级。
# 检验四:流程卡放行件红外复核,零误放时要以 95% 把握说误放率 <= 0.02,
#   需 n >= ln(0.05) / ln(0.98)。
import math
from statistics import NormalDist

Z = NormalDist().inv_cdf


def n_one(d, s, alpha, power, sides):
    za = Z(1 - alpha / sides)
    return math.ceil(((za + Z(power)) * s / d) ** 2)


def main():
    print("test 1: mean log return of windowed rough < 0")
    for s in (0.6, 0.9, 1.2):
        print("  sd %.1f, effect -0.15: n = %d stones"
              % (s, n_one(0.15, s, 0.05, 0.8, 1)))
    per = 2 * n_one(0.25, 0.9, 0.05, 0.8, 2)
    print("test 2: >= 8 bidders vs <= 3, gap 0.25, sd 0.9: %d per group"
          % per)
    print("test 3: window spot vs random spot, gap 0.3 grade: n = %d"
          % n_one(0.3, 1.0, 0.05, 0.8, 2))
    n4 = math.ceil(math.log(0.05) / math.log(0.98))
    print("test 4: zero false passes in %d IR checks bounds the" % n4)
    print("  false-pass rate at 0.02 with 95%% confidence (rule of"
          " three: %d)" % math.ceil(3 / 0.02))


if __name__ == "__main__":
    main()

Single source and citation

Fan, Y. (2026). Hydrostatic Specific Gravity and Bayesian Jadeite Identification, Window-Cut Signalling Games and the Winner's Curse in Rough-Jade Tenders (Version 1.0.0), Chapter 8: Closing the Loop: the Buyer's Flow Card, the Bid Cap, a Compliant Script and Pre-Registered Tests. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-206 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026206,
  author    = {Fan, Yafu},
  title     = {Hydrostatic Specific Gravity and Bayesian Jadeite Identification, Window-Cut Signalling Games and the Winner's Curse in Rough-Jade Tenders},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book