关于「怀疑者的三把刀:回归均值、报告偏倚与「安慰剂无力」」,《开放标签与价格标签》给出的定量结论是什么?
结论:p61 说明,回归均值在示意参数下只解释不服药组改善的一部分,单凭它产生 52.3 分的回落需要 115.6 分的测量误差。p62 说明,若客观指标完全可信,报告偏倚可以解释自评效应的 0.769,扣除后伦博试验的开放标签效应只剩 0.134。p63 说明,2001 年的「安慰剂无力」分析与 2025 年的开放标签元分析指向同一个边界:主观连续量表上有小到中等的作用,客观硬结局上几乎没有。下一章转向两部古典文献:它们分别在一千八百多年前与两百多年前,已经触碰到了同一个边界。
数据口径:书中参数为示意;全部计算由书中程序生成;本书不是医疗建议,不宣称任何产品或做法对身体或健康有任何作用,书中流程与工具为非个人化经营建议。 书中以标注框区分已发表证据、可运行的 Python 计算(21 段程序)、原典与作者假说。
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。 与结论吻合的打印值: 0.134, 0.769, 2025
| objective reliability r true change bias b bias share | |
| 1.0 | 0.090 0.300 0.769 |
| 0.8 | 0.112 0.278 0.712 |
| 0.6 | 0.150 0.240 0.615 |
| 0.4 | 0.225 0.165 0.423 |
| 0.3 | 0.300 0.090 0.231 |
| trial-level effects after removing a bias of 0.30: | |
| Kaptchuk 2010, day 21 | 0.790 -> 0.490 |
| Lembo 2021, OLP vs no pill | 0.434 -> 0.134 |
| Fendel 2025, clinical | 0.470 -> 0.170 |
| bias that would erase the clinical pooled effect | 0.47 |
查看完整验算程序
# Chapter 6. p62: How much of an unblinded self-report effect could be
# reporting bias? A sensitivity scan.
# Published anchors: Fendel et al. (2025): self-report SMD 0.39,
# objective SMD 0.09. Kaptchuk et al. (2010): day-21 d 0.79. Lembo et
# al. (2021): open label vs no pill d 0.434 (from p12).
# Model (ours): observed self-report SMD = true change + bias b, where
# the objective SMD measures the true change up to a reliability factor
# r (an objective measure with r < 1 shrinks the true change by r).
# 自评偏倚的敏感度扫描:客观指标信度不同,偏倚能解释多少。
SELF, OBJ = 0.39, 0.09
print("objective reliability r true change bias b bias share")
for r in (1.0, 0.8, 0.6, 0.4, 0.3):
true = min(OBJ / r, SELF)
b = SELF - true
print(" {:.1f} {:.3f} {:.3f} {:.3f}"
.format(r, true, b, b / SELF))
print("trial-level effects after removing a bias of 0.30:")
for name, d in (("Kaptchuk 2010, day 21", 0.79),
("Lembo 2021, OLP vs no pill", 0.434),
("Fendel 2025, clinical", 0.47)):
print(" {:<27} {:.3f} -> {:.3f}".format(name, d, d - 0.30))
print("bias that would erase the clinical pooled effect: 0.47")唯一数据源与引用
范雅福(Fan, Y.). (2026). 《开放标签安慰剂预测编码、价格标签期望增益与杯弓蛇影反安慰剂母典》第 6 章「怀疑者的三把刀:回归均值、报告偏倚与「安慰剂无力」」(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-201 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026201,
author = {Fan, Yafu},
title = {Open-Label Placebos and Predictive Coding, Price-Tag Expectancy Gains and the Nocebo of the Bow in the Cup},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}