关于「实证闭环:摄影棚档期价格表与预注册检验」,《空间租赁收益管理与档期装箱》给出的定量结论是什么?
结论:第八章给出摄影棚档期价格表的周度流程、档期保护水平计算器与预注册交替周检验方案:单间棚需要 196 周,八间棚并行需要 25 周。书中以标注框区分已发表的证据、可运行的 Python 计算(18 段程序)、原典与作者的假说。
数据口径:书中的棚日、价格、需求与到达概率均为示意;全部计算由书中程序生成;本书是非个人化经营建议,所有价格明码标价,稀缺提示只来自真实档期,小工具给出的价格表须经营者人工复核后发布。 第一章在一个 20 个棚日的示意月份里,用精确期望算出保护 10 个棚日可使月收入从 47323.9 元升到 57432.1 元,多 21.36 %,但模拟显示保护在 0.1900 的月份里少收钱。
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: 196, 25
| weekly Littlewood level y* | 3 of 5 days |
| FCFS: mean 11066.8 sd 3517.9 | |
| protect: mean 12817.8 sd 5057.2 | |
| modelled effect 1751.1 yuan/week | 98 weeks per arm, 196 in all |
| 1 studio(s) in parallel | 196 calendar weeks |
| 4 studio(s) in parallel | 49 calendar weeks |
| 8 studio(s) in parallel | 25 calendar weeks |
| half the effect 875.5 yuan/week | 389 weeks per arm, 778 in all |
| 1 studio(s) in parallel | 778 calendar weeks |
| 4 studio(s) in parallel | 195 calendar weeks |
| 8 studio(s) in parallel | 98 calendar weeks |
查看完整验算程序
# Chapter 8. p82: pre-registered switchback test, weeks needed.
# Unit: one studio-week of C = 5 days (p11 scaled to a week: full-day
# Poisson mean 2.25 at 4800, short-blocks-a-day Poisson mean 4 at 1800).
# Weeks alternate between FCFS and Littlewood protection. The exact mean
# and variance of weekly revenue under each rule come from enumerating
# both Poisson demands. Two-sided alpha 0.05, power 0.8:
# n per arm = (z_.975 + z_.8)^2 (var_a + var_b) / delta^2
# for the modelled effect and for half of it (the falsification line).
import math
from statistics import NormalDist
C, F_H, F_L, M_H, M_L, N = 5, 4800, 1800, 2.25, 4.0, 60
def pois(mean):
p = [math.exp(-mean)]
for k in range(1, N + 1):
p.append(p[-1] * mean / k)
return p
PH, PL = pois(M_H), pois(M_L)
def moments(y):
vals = []
for dh, ph in enumerate(PH):
for dl, pl in enumerate(PL):
sl = min(dl, C - y)
sh = min(dh, C - sl)
vals.append((ph * pl, F_H * sh + F_L * sl))
m = math.fsum(p * v for p, v in vals)
var = math.fsum(p * (v - m) ** 2 for p, v in vals)
return m, var
tail = [math.fsum(PH[k:]) for k in range(N + 1)]
ystar = max(y for y in range(C + 1) if F_H * tail[y] >= F_L)
m0, v0 = moments(0)
m1, v1 = moments(ystar)
z = NormalDist().inv_cdf(0.975) + NormalDist().inv_cdf(0.8)
print("weekly Littlewood level y* = %d of %d days" % (ystar, C))
print("FCFS: mean %.1f sd %.1f" % (m0, math.sqrt(v0)))
print("protect: mean %.1f sd %.1f" % (m1, math.sqrt(v1)))
for label, delta in (("modelled effect", m1 - m0),
("half the effect", (m1 - m0) / 2)):
n = math.ceil(z * z * (v0 + v1) / delta ** 2)
print("%s %.1f yuan/week: %d weeks per arm, %d in all"
% (label, delta, n, 2 * n))
for studios in (1, 4, 8):
print(" %d studio(s) in parallel: %d calendar weeks"
% (studios, math.ceil(2 * n / studios)))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《空间租赁动态收益管理与档期装箱、舱位控制嵌套保护水平与碎片空置消除母典》第 8 章「实证闭环:摄影棚档期价格表与预注册检验」(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-282 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026282,
author = {Fan, Yafu},
title = {Dynamic Revenue Management and Slot Packing for Space Rentals: Nested Protection Levels and the Elimination of Fragmented Idle Time},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}