关于「实践:样盘 A 与样盘 B 的合盘查法,以及一份预先登记的检验」,《钦天双人合盘飞化》给出的定量结论是什么?
结论:第八章用两张不含任何出生资料的样盘示范完整的查法,并给出预先登记的盲选、行为编码与定月检验方案:三选一的盲选、真实命中率 0.40 时需要 318 对伴侣。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;本书不是婚姻、心理、法律或投资建议。 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, 318
| (a) matching, 3 cards, hit rate 0.40 vs 0.3333 | 318 couples |
| (a) matching, 3 cards, hit rate 0.45 vs 0.3333 | 105 couples |
| (b) ji-ji mutual base 0.0823, d | 0.5: 35 exposed of 416 couples |
| (b) ji-ji mutual base 0.0823, d | 0.3: 96 exposed of 1155 couples |
| (b) ji-ji mutual base 0.0823, d | 0.2: 214 exposed of 2599 couples |
| (b) one-way ji base 0.4142, d | 0.5: 54 exposed of 130 couples |
| (b) one-way ji base 0.4142, d | 0.3: 149 exposed of 360 couples |
| (b) one-way ji base 0.4142, d | 0.2: 335 exposed of 809 couples |
| (c) timing, ji-window share 0.1597, rate ratio 1.50 | 146 dated events |
| (c) timing, ji-window share 0.1597, rate ratio 1.25 | 554 dated events |
查看完整验算程序
# Chapter 8. p06: Sample sizes for three pre-registered couple tests.
# Normal approximation, power 0.80. (a) Blind matching: each couple sees its own
# two-person card and two decoys (another real couple's card and a Barnum card);
# chance 1/3, one-sided alpha 0.05. (b) Coded conflict behaviour: couples in a
# pattern against all others, sampled as they come (the pattern's base rate from
# Chapter 1: ji-ji mutual 0.0823, one-way ji 0.4142), effect size d on a coded
# withdrawal score, two-sided alpha 0.05. (c) Timing: dated break-ups (or first
# stonewalling episodes) against the share of months that hold a ji window for
# that couple; the average share over all pairs is 0.1597 (Chapter 1, p04);
# events needed to see a rate ratio r, one-sided alpha 0.05.
from math import sqrt, ceil
ZA1, ZA2, ZB = 1.6449, 1.9600, 0.8416
def n_prop(p0, p1, za):
return ceil((za * sqrt(p0 * (1 - p0)) + ZB * sqrt(p1 * (1 - p1))) ** 2 / (p1 - p0) ** 2)
def n_natural(p, d):
n = (ZA2 + ZB) ** 2 * (1 / p + 1 / (1 - p)) / d ** 2
return ceil(n * p), ceil(n)
if __name__ == "__main__":
for p1 in (0.40, 0.45):
print(" (a) matching, 3 cards, hit rate {:.2f} vs {:.4f}: {} couples".format(
p1, 1 / 3, n_prop(1 / 3, p1, ZA1)))
for name, p in (("ji-ji mutual", 0.0823), ("one-way ji", 0.4142)):
for d in (0.5, 0.3, 0.2):
k, n = n_natural(p, d)
print(" (b) {:<12} base {:.4f}, d = {:.1f}: {} exposed of {} couples".format(
name, p, d, k, n))
p0 = 0.1597
for r in (1.5, 1.25):
print(" (c) timing, ji-window share {:.4f}, rate ratio {:.2f}: {} dated events".format(
p0, r, n_prop(p0, p0 * r, ZA1)))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《钦天双人合盘与宿命情缘飞化母典》第 8 章「实践:样盘 A 与样盘 B 的合盘查法,以及一份预先登记的检验」(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-120 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026120,
author = {Fan, Yafu},
title = {The Qintian Synastry Codex of Cross-Flying Transformations},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}