关于「实证闭环:门店排程日志、预注册检验与真伪判据」,《沉香挥发与嗅觉适应》给出的定量结论是什么?

结论:第八章给出门店闭环、蒸馏小工具「香氛排程器」、预注册方案(以成交率为结局需 459 个营业日)与真伪判据(入水下沉似然比仅 1.75)。书中以标注框区分已发表的证据、可运行的 Python 计算(21 段程序)、原典与作者的假说。

数据口径:书中的房间、香材、香炉与适应参数均为示意;全部计算由书中程序生成;本书是非个人化经营建议,不讨论健康影响,不是医疗建议。 第五章把嗅觉适应写成带时间常数的过程:示意参数下,点香后第 15 分钟主人只剩新鲜鼻子 0.250 的灵敏度,用加量追赶需要 12.4 倍浓度;「主人几乎闻不到」依赖适应深度,须实测。

English version

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: 459

z_alpha 1.960, z_beta 0.842
baseliftn per armvisits totaldays at 6/day (ICC 0.02)
0.150.0324024804881
0.150.059061812333
0.150.08377754139
0.250.03339767941246
0.250.0512512502459
0.250.085041008185
0.350.03404280841483
0.350.0514712942540
0.350.085831166214
design effect for day-level randomisation: 1.10
查看完整验算程序
# Chapter 8. p81: how many visits a pre-registered shop test needs.
# Design: each appointment is randomised to schedule A (chip on the
# heater all day) or schedule B (chip lit 15 minutes before arrival,
# p61). Outcome: purchase within the visit (yes / no). Two-sided test
# of two proportions, alpha 0.05, power 0.80, normal approximation:
#   n per arm = (z_a sqrt(2 pbar qbar) + z_b sqrt(p1 q1 + p2 q2))^2
#               / (p1 - p2)^2.
# If whole days are randomised instead, inflate by the design effect
# 1 + (m - 1) ICC with m = 6 visits a day. Baselines, lifts and the
# ICC of 0.02 are illustrative (示意).
import math
from statistics import NormalDist

Z = NormalDist()
ZA, ZB = Z.inv_cdf(1 - 0.05 / 2), Z.inv_cdf(0.80)


def n_arm(p1, p2):
    pb = (p1 + p2) / 2
    num = ZA * math.sqrt(2 * pb * (1 - pb)) + \
        ZB * math.sqrt(p1 * (1 - p1) + p2 * (1 - p2))
    return math.ceil(num * num / (p1 - p2) ** 2)


print("z_alpha {:.3f}, z_beta {:.3f}".format(ZA, ZB))
print("base   lift   n per arm  visits total  days at 6/day (ICC 0.02)")
de = 1 + (6 - 1) * 0.02
for p1 in (0.15, 0.25, 0.35):
    for lift in (0.03, 0.05, 0.08):
        n = n_arm(p1, p1 + lift)
        days = math.ceil(2 * n * de / 6)
        print("{:4.2f}  {:5.2f}  {:9d}  {:12d}  {:9d}".format(
            p1, lift, n, 2 * n, days))
print("design effect for day-level randomisation: {:.2f}".format(de))

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《沉香倍半萜挥发动力学、嗅觉受体组合编码与嗅觉适应时间常数母典》第 8 章「实证闭环:门店排程日志、预注册检验与真伪判据」(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-205 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026205,
  author    = {Fan, Yafu},
  title     = {Agarwood Sesquiterpene Volatilisation, Combinatorial Olfactory-Receptor Coding and the Time Constant of Olfactory Adaptation},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论