关于「Bailey-Muth-Nourse 回归:从成交配对到价格指数」,《收藏品回报去偏》给出的定量结论是什么?

结论:当单件波动只有 0.10 时,两种口径只差 0.0053,十年后中位数作品的价值是买入价的 1.84 倍,平均作品是 1.94 倍,单件亏损的概率只有 0.027。单件波动升到 0.30,算术年率是 0.1119,比几何年率高出 0.0489;十年后平均作品是 2.89 倍,但中位数作品仍然只有 1.84 倍,而单件作品低于买入价的概率是 0.260。波动到 0.50 时,算术年率是 0.2045,几何年率仍是 0.0630,单件亏损的概率是 0.350。

数据口径:书中参数为示意;全部计算由书中程序生成;本书非个人化法律或理财建议,费率与法规以上架前人工复核为准。 书中以标注框区分已发表的证据、可运行的 Python 计算(20 段程序)、原典与作者的假说。

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: 0.0053, 0.027, 0.0489, 0.0630, 0.10, 0.1119

log drift m = 0.0611; horizon 10 years
smedian/ymean/ygapmed x10mean x10P(loss)
0.100.06300.06830.00531.841.940.027
0.200.06300.08450.02151.842.250.167
0.300.06300.11190.04891.842.890.260
0.400.06300.15150.08851.844.100.315
0.500.06300.20450.14151.846.430.350
half the variance, s 0.25 / 0.30 / 0.35: 0.0312 / 0.0450 / 0.0612
s that turns a 0.063 median into a 0.087 mean: 0.211
查看完整验算程序
# Chapter 2. p23: arithmetic index, geometric index and the typical piece
# Model: one piece's log price change over h years is normal with mean
# m*h and variance s*s*h. A log (geometric) repeat-sales index estimates
# m; the median piece grows at exp(m) - 1 a year, while the mean piece
# grows at exp(m + s*s/2) - 1. The drift m = log(1.063) takes the corrected
# Korteweg et al. figure as a log rate for illustration; the idiosyncratic
# volatilities s are illustrative. Closed form, no randomness.
import math

M = math.log(1.063)
H = 10


def phi(x):
    return 0.5 * math.erfc(-x / math.sqrt(2.0))


def main():
    print("log drift m = {:.4f}; horizon {} years".format(M, H))
    print("{:>6}{:>10}{:>10}{:>8}{:>10}{:>10}{:>9}".format(
        "s", "median/y", "mean/y", "gap", "med x10", "mean x10", "P(loss)"))
    for s in (0.10, 0.20, 0.30, 0.40, 0.50):
        med = math.expm1(M)
        mean = math.expm1(M + 0.5 * s * s)
        mx_med = math.exp(M * H)
        mx_mean = math.exp(M * H + 0.5 * s * s * H)
        ploss = phi(-M * H / (s * math.sqrt(H)))
        print("{:>6.2f}{:>10.4f}{:>10.4f}{:>8.4f}{:>10.2f}{:>10.2f}"
              "{:>9.3f}".format(s, med, mean, mean - med, mx_med, mx_mean,
                                ploss))
    print("half the variance, s 0.25 / 0.30 / 0.35: {:.4f} / {:.4f} / "
          "{:.4f}".format(0.5 * 0.25 ** 2, 0.5 * 0.30 ** 2, 0.5 * 0.35 ** 2))
    s_needed = math.sqrt(2.0 * (math.log(1.087) - M))
    print("s that turns a 0.063 median into a 0.087 mean: {:.3f}".format(
        s_needed))


if __name__ == "__main__":
    main()

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《收藏品重复成交指数选择偏差、赝品先验与另类资产流动性折价母典》第 2 章「Bailey-Muth-Nourse 回归:从成交配对到价格指数」(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-208 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026208,
  author    = {Fan, Yafu},
  title     = {Repeat-Sales Selection Bias in Collectibles, Forgery Priors and the Illiquidity Discount of Alternative Assets},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论