关于「十项审计与一项以视频为单位的预注册实验」,《完播风险、推荐反馈与获客漏斗》给出的定量结论是什么?

结论:第八章给出十项自动审计与一项以视频为单位随机化的预注册实验(每组 88 条视频)。书中以标注框区分证据、可运行的 Python 程序、原典与假说。

数据口径:书中的威布尔参数、流量池规模、转化率、价格(令吉 RM)与封号概率都是示意模型参数,不是任何平台、账号或企业的数据;本书不描述任何平台的真实算法,也不构成营销或经营建议。 第二章模拟分级流量池:300 人样本下,即使各池观众相同,好视频也有 0.169 在第一关被拦下,观众差异下为 0.308 至 0.478;对冲噪声应重剪而不是重发。

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: 88

viewers per arm if viewers were independent34,999
m viewers/video icc design effect videos per arm
5000.0005 1.25 88
5000.0020 2.00 140
2,0000.0005 2.00 35
2,0000.0020 5.00 88
8,0000.0005 5.00 22
8,0000.0020 17.00 75
null simulation, video-level t test: false alarms 0.0465
Reading: the experiment must count videos, not viewers:
between 22 and 140 videos per arm here, depending on how
much one video's audience differs from another's. Analysed
at the video level, the test keeps its stated error rate.
查看完整验算程序
# Chapter 8. p16: A pre-registered, video-randomised hook experiment.
# Each new video is randomly given a narrow hook (breadth 0.3) or a
# broad one (breadth 1.0). Viewers of one video share its audience
# draw, so the unit of analysis is the video, not the viewer.
# Primary outcome: paid conversion per viewer, assumed 0.010 under the
# narrow hook and 0.008 under the broad one at equal reach. Two-sided
# 0.05, power 0.80. Viewers per arm ignoring clustering:
#   n = (1.96 + 0.8416)^2 (p1 (1 - p1) + p2 (1 - p2)) / (p1 - p2)^2;
# with m viewers per video and intraclass correlation icc, multiply by
# the design effect 1 + (m - 1) icc and divide by m to get videos.
# A simulation of 2,000 null experiments (both arms at 0.010, icc
# 0.002, m = 2,000, 60 videos per arm) checks the type I error of a
# video-level t test.
import math
import random

Z = 1.96 + 0.8416

def viewers(p1, p2):
    return Z ** 2 * (p1 * (1 - p1) + p2 * (1 - p2)) / (p1 - p2) ** 2

if __name__ == "__main__":
    n = viewers(0.010, 0.008)
    print("   viewers per arm if viewers were independent: {:,.0f}".format(
        math.ceil(n)))
    print("   m viewers/video   icc     design effect   videos per arm")
    for m in (500, 2000, 8000):
        for icc in (0.0005, 0.002):
            de = 1 + (m - 1) * icc
            print("   {:15,d} {:7.4f} {:15.2f} {:16d}".format(
                m, icc, de, math.ceil(n * de / m)))
    rng = random.Random(16)
    sd_p = math.sqrt(0.002 * 0.010 * 0.990)
    rej = 0
    for _ in range(2000):
        arms = []
        for _ in range(2):
            rates = []
            for _ in range(60):
                p = min(max(rng.gauss(0.010, sd_p), 0.0), 1.0)
                k = rng.gauss(2000 * p, math.sqrt(2000 * p * (1 - p)))
                rates.append(k / 2000)
            arms.append(rates)
        ma, mb = (sum(a) / 60 for a in arms)
        va = sum((x - ma) ** 2 for x in arms[0]) / 59
        vb = sum((x - mb) ** 2 for x in arms[1]) / 59
        t = (ma - mb) / math.sqrt(va / 60 + vb / 60)
        rej += abs(t) > 1.98
    print("   null simulation, video-level t test: false alarms {:.4f}"
          .format(rej / 2000))
    print("\nReading: the experiment must count videos, not viewers:")
    print("between 22 and 140 videos per arm here, depending on how")
    print("much one video's audience differs from another's. Analysed")
    print("at the video level, the test keeps its stated error rate.")

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《短视频完播率风险函数、推荐反馈环与自动化获客漏斗》第 8 章「十项审计与一项以视频为单位的预注册实验」(版本 1.0.0). 5D Library. https://doi.org/10.5281/zenodo.24090213

DOI: 10.5281/zenodo.24090213 · 阅读本章所在专著 · 5DL-B-081 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026081,
  author    = {Fan, Yafu},
  title     = {Short-Video Completion Hazards, Recommender Exploration Loops and Automated Acquisition Funnels},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  doi       = {10.5281/zenodo.24090213},
  url       = {https://doi.org/10.5281/zenodo.24090213}
}

本书其他章节结论