关于「实证闭环:季度报价与接单体检、小工具与预注册检验」,《头部艺人稀缺溢价与降格成本》给出的定量结论是什么?

结论:第八章给出季度报价与接单体检流程、蒸馏小工具「艺人接单降格成本计算器」与预注册检验方案,降格检验每组需要 112 位艺人。书中以标注框区分已发表的证据、可运行的 Python 计算(19 段程序)、原典与作者的假说。

数据口径:核对原文后,本书对立项蓝图作了修正:凸性是对能力而非对曝光,且有 Adler 与 Hamlen 的反方证据;已发表的代言事件研究测的是企业股价,不是艺人报价,降格污染因此写成模型与预注册假说;套牢的经典表述来自 Klein、Crawford 与 Alchian,Grossman 与 Hart 讨论的是剩余控制权;「肖像暗投」一律改写为如实披露的肖像拆分授权。 书中参数均为示意,全部计算由书中程序生成;本书不点名评价任何在世人士,不是个人化的法律、财务或投资建议,合同条款只写结构与博弈逻辑,以上架前人工复核为准。

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: 112

H1 dilution: talents per arm112, total = 224
simulated power at that n0.819
if delta0.10: per arm 252
if delta0.20: per arm 63
H2 convexity: talent-fee pairs69
if true k1.25: pairs = 275
model-implied log drop at the p31 trough-0.371
refute H1 if the 95% CI of the gap lies above -0.05
H2 unsupported if the one-sided 95% lower bound of k <1
refute H2 if the one-sided 95% upper bound of k < 1
查看完整验算程序
# Chapter 8. p82: sample sizes for the pre-registered tests.
# H1 dilution: talents who take a down-market deal see their next
# luxury fee fall, in logs, by delta relative to matched controls.
# Planning values: delta 0.15, sd of the log fee change 0.40 (both
# assumed). Two-sided 5%, power 80%; a seeded simulation checks power.
# H2 convexity: the slope k of log fee on a log talent proxy exceeds 1.
# Planning values: true k 1.5, residual sd 0.5, sd of the log proxy 0.3;
# one-sided 5%, power 80%. All planning values are illustrative and
# must be fixed in the registration before any data are seen.
import math
import random

Z2 = 1.959964
Z1 = 1.644854
ZP = 0.841621
SEED = 20261120


def n_two_arm(delta, sd):
    return math.ceil(2 * ((Z2 + ZP) * sd / delta) ** 2)


def n_slope(diff, resid, sdx):
    return math.ceil(((Z1 + ZP) * resid / (sdx * diff)) ** 2)


def sim_two_arm(delta, sd, n, reps, rng):
    hits = 0
    for _ in range(reps):
        a = [rng.gauss(-delta, sd) for _ in range(n)]
        c = [rng.gauss(0.0, sd) for _ in range(n)]
        ma, mc = math.fsum(a) / n, math.fsum(c) / n
        va = math.fsum((x - ma) ** 2 for x in a) / (n - 1)
        vc = math.fsum((x - mc) ** 2 for x in c) / (n - 1)
        if abs(ma - mc) / math.sqrt((va + vc) / n) > Z2:
            hits += 1
    return hits / reps


if __name__ == "__main__":
    rng = random.Random(20261120)
    n1 = n_two_arm(0.15, 0.40)
    print("H1 dilution: talents per arm = {}, total = {}".format(
        n1, 2 * n1))
    print("   simulated power at that n = {:.3f}".format(
        sim_two_arm(0.15, 0.40, n1, 2000, rng)))
    for d in (0.10, 0.20):
        print("   if delta = {:.2f}: per arm {}".format(
            d, n_two_arm(d, 0.40)))
    n2 = n_slope(0.5, 0.5, 0.3)
    print("H2 convexity: talent-fee pairs = {}".format(n2))
    print("   if true k = 1.25: pairs = {}".format(
        n_slope(0.25, 0.5, 0.3)))
    print("model-implied log drop at the p31 trough = {:.3f}".format(
        math.log(452.6 / 656.1)))
    print("refute H1 if the 95% CI of the gap lies above -0.05")
    print("H2 unsupported if the one-sided 95% lower bound of k <= 1")
    print("refute H2 if the one-sided 95% upper bound of k < 1")

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《超模与头部艺人稀缺溢价保护、代言降格污染惩罚与独家经纪博弈母典》第 8 章「实证闭环:季度报价与接单体检、小工具与预注册检验」(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-343 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026343,
  author    = {Fan, Yafu},
  title     = {Flagship Talent Scarcity Pricing, Brand-Dilution Spillover Penalties and Exclusive Representation Game Theory},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论