关于「蓝图修正二:「不可预测与高张力」的证据为何薄弱」,《亲密决策阈值不对称》给出的定量结论是什么?

结论:真实效应为 0.2、每组 16 人时,功效只有 0.079,发表结果的平均效应是 0.852,高估 4.26 倍。每组 50 人时,功效 0.165,平均 0.496,高估 2.48 倍;每组 200 人时,功效 0.513,高估降到 1.39 倍。真实效应为零时,每组 16 人仍有 0.024 的研究会「显著」,平均报告效应 0.828。真实效应为 0.5、每组 16 人时,功效 0.291,高估 1.84 倍;每组 64 人时,功效 0.804,高估只剩 1.12 倍。

数据口径:书中参数均为示意或合成;全部计算由书中程序生成;本书不是心理咨询、婚恋咨询或临床判断,也不是个人化经营建议。 第三章在合成拆解里,感知安全、体验与污名承担原始差距的 0.842,并说明零接受率会把优势比放大到失真。

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: 0.024, 0.079, 0.165, 0.2, 0.291, 0.496

A. 20,000 simulated studies per row
d_truen/cellpowermean published dinflation
0.2160.0790.8524.26
0.2500.1650.4962.48
0.22000.5130.2781.39
0.0160.0240.828n/a
0.5160.2910.9191.84
0.5640.8040.5591.12
B. a lone significant small study overstates by about 2x or more
查看完整验算程序
# Chapter 5. p52: small studies and the winner's curse
# Two-cell experiments with n per cell; true standardized effect d_true.
# Keep only results with |z| > 1.96 and the predicted sign ("published").
# Report power and the mean published effect. Normal sampling of the
# estimate: d_hat ~ N(d_true, sqrt(2 / n)). Fixed seed; illustrative.
import math
import random

rng = random.Random(42452)
REPS = 20000

print("A. {:,} simulated studies per row".format(REPS))
print("  d_true  n/cell  power   mean published d  inflation")
for d_true, n in ((0.2, 16), (0.2, 50), (0.2, 200), (0.0, 16),
                  (0.5, 16), (0.5, 64)):
    se = math.sqrt(2.0 / n)
    kept = []
    for _ in range(REPS):
        dh = rng.gauss(d_true, se)
        if dh / se > 1.96:
            kept.append(dh)
    power = len(kept) / REPS
    mp = math.fsum(kept) / len(kept) if kept else float("nan")
    infl = mp / d_true if d_true > 0 else float("nan")
    tag = "{:9.2f}".format(infl) if d_true > 0 else "      n/a"
    print("   {:.1f}     {:4d}   {:.3f}       {:.3f}        {}".format(
        d_true, n, power, mp, tag))
print("B. a lone significant small study overstates by about 2x or more")

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《亲密决策阈值不对称:男性边际成本核算与女性情境张力唤醒的演化经济学母典》第 5 章「蓝图修正二:「不可预测与高张力」的证据为何薄弱」(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-424 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026424,
  author    = {Fan, Yafu},
  title     = {Asymmetric Intimacy Thresholds: Male Marginal-Cost Accounting versus Female Contextual-Tension Arousal in Mating Economics},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论