关于「实践:样盘 A 过一遍工作站,三张牌,以及带巴纳姆对照的盲选检验」,《人类图、卓尔金历与塔罗投射》给出的定量结论是什么?
结论:第八章把一张不含任何出生资料的样盘送进测算站,得到单一定义的生产者、人生角色 5/1、五条导通通道与 Dreamspell kin 30,按写明的种子抽出恋人逆位、倒吊人逆位与星币国王,把它们落成一条先写退出条款、再谈租期的合约规则,并给出一份带巴纳姆对照的预先登记盲选检验:三选一、真实命中率 0.40 时需要 447 人。书中以标注框区分已发表的证据、可运行的 Python 计算、原典与作者的假说。
数据口径:全部计算由书中程序生成;本书不是投资、法律、医疗或心理建议。 书中以标注框区分已发表的证据、可运行的 Python 计算、原典与作者的假说。
对照数据表
下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 0.40, 447
| (A) hit rate 0.40 vs 1/3 | 447 people, at least 166 hits, exact size 0.0498 |
| (A) hit rate 0.45 vs 1/3 | 152 people, at least 61 hits, exact size 0.0468 |
| (A) hit rate 0.50 vs 1/3 | 79 people, at least 34 hits, exact size 0.0455 |
| (B) own vs Barnum, paired d | 0.3: 96 people |
| (B) own vs Barnum, paired d | 0.2: 215 people |
| (C) card swap, d | 0.3: 234 per arm |
| (C) card swap, d | 0.2: 526 per arm |
查看完整验算程序
# Chapter 8. p07: Sample sizes for the pre-registered tests.
# (A) Blind matching against a Barnum control: each participant sees three
# unlabelled profiles in the same format - one written from their own
# chart (type, profile, channels, centres, seal and tone), one from a
# stranger's chart chosen to differ in type and seal, and one assembled
# from generic statements - and picks the one most like them. Chance
# 1/3. Exact one-sided binomial test, alpha 0.05, power 0.90.
# (B) Own profile versus the Barnum profile, accuracy rated 0-10 by the
# same person: paired test, one-sided alpha 0.05, power 0.90, effect d.
# (C) Card swap: half the participants get the reading of their real
# three-card draw, half the reading of another person's draw (blind);
# usefulness rated on a 1-7 scale. Two-sided alpha 0.05, power 0.90,
# n per arm = 2 (z_a + z_b)^2 / d^2.
from math import ceil, comb
ZA1, ZA2, ZB = 1.6449, 1.9600, 1.2816
def tail(n, k, p):
return sum(comb(n, i) * p ** i * (1 - p) ** (n - i)
for i in range(k, n + 1))
def plan(p0, p1, alpha=0.05, power=0.90):
k = 0
for n in range(10, 3000):
while tail(n, k, p0) > alpha:
k += 1
while k > 0 and tail(n, k - 1, p0) <= alpha:
k -= 1
if tail(n, k, p1) >= power:
return n, k, tail(n, k, p0)
if __name__ == "__main__":
for p1 in (0.40, 0.45, 0.50):
n, k, a = plan(1 / 3, p1)
print(" (A) hit rate {:.2f} vs 1/3: {} people, at least {} hits,"
" exact size {:.4f}".format(p1, n, k, a))
for d in (0.3, 0.2):
print(" (B) own vs Barnum, paired d = {:.1f}: {} people".format(
d, ceil(((ZA1 + ZB) / d) ** 2)))
for d in (0.3, 0.2):
print(" (C) card swap, d = {:.1f}: {} per arm".format(
d, ceil(2 * ((ZA2 + ZB) / d) ** 2)))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《人类图通道、玛雅卓尔金历与七十八塔罗投射母典》第 8 章「实践:样盘 A 过一遍工作站,三张牌,以及带巴纳姆对照的盲选检验」(版本 1.0.0). 5D Library. DOI 待发布
DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-126 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026126,
author = {Fan, Yafu},
title = {The Human Design, Tzolkin and Seventy-Eight Tarot Projection Codex},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}