What does Drift and Noise on Long Pages conclude, in numbers, about “Speed, Accuracy and the Opposing Evidence: Compressed Barriers, Mixed Audiences and the Cue of Argument Quantity”?

Answer: Chapter 6 shows that compressing the barriers raises unsuited buyers per hundred decided visitors from 13.89 to 25.53, that noise cuts kept sales to 0.7767, and writes the opposing evidence on argument quantity as a cue into the model.

Scope of the numbers: Chapter 4 pushes a page forward section by section: deleting the feature table of an illustrative page gains 0.0081, and the best and worst orders of sections differ by 0.1764. Marked boxes separate published evidence, runnable Python calculations (20 programs), classical sources and the author's hypotheses.

中文版

Data table

The numbers below are printed verbatim by the chapter's Python program and can be reproduced by running it. standard-library Python onlyprinted values that match the answer: 13.89, 25.53

aP(fit buys)P(poor fit buys)buyers/100fit shareE[T]
4.00.76850.231544.630.68883.5803
3.00.71090.289145.780.62122.1095
2.00.64570.354347.090.54850.9710
1.50.61060.389447.790.51110.5532
1.00.57440.425648.510.47370.2481
0.50.53740.462649.250.43650.0624
poor-fit buyers per 100 visitors at a = 4.0: 13.89, at a = 1.0: 25.53
Show the full program
# Chapter 6. p61: pressure that narrows the barriers. Visitors are a mix
# of good fits (drift +0.3) and poor fits (drift -0.3); pushing them to
# decide sooner is modelled as a smaller barrier separation a.
# 起点居中 z = a/2,s = 1。适配者占 0.4(示意)。壁距缩小时:
# 适配者付款概率下降,不适配者付款概率上升,买家中适配者的比例下降。
# 这些不适配者的付款就是「误撞」,日后最可能变成退款与差评。
# 本书只讨论真实截止;虚构倒计时等于人为压缩壁距,书中不采用。
import math

FIT, VF, VN, S = 0.4, 0.3, -0.3, 1.0


def p_pay(v, a):
    return 1.0 / (1.0 + math.exp(-v * a / (S * S)))


def mean_time(v, a):
    return (a / (2 * v)) * math.tanh(v * a / (2 * S * S))


print("a     P(fit buys)  P(poor fit buys)  buyers/100  fit share  E[T]")
for a in (4.0, 3.0, 2.0, 1.5, 1.0, 0.5):
    pf, pn = p_pay(VF, a), p_pay(VN, a)
    buy = FIT * pf + (1 - FIT) * pn
    share = FIT * pf / buy
    et = FIT * mean_time(VF, a) + (1 - FIT) * mean_time(VN, a)
    print("%.1f   %.4f       %.4f            %.2f       %.4f     %.4f"
          % (a, pf, pn, 100 * buy, share, et))
print("poor-fit buyers per 100 visitors at a = 4.0: %.2f, at a = 1.0: %.2f"
      % (100 * (1 - FIT) * p_pay(VN, 4.0), 100 * (1 - FIT) * p_pay(VN, 1.0)))

Single source and citation

Fan, Y. (2026). Fokker-Planck Drift-Diffusion on Long Sales Pages: Belief-Drift Rates and First-Passage Times to the Payment Barrier (Version 1.0.0), Chapter 6: Speed, Accuracy and the Opposing Evidence: Compressed Barriers, Mixed Audiences and the Cue of Argument Quantity. 5D Library. DOI pending

DOI pending · monograph page goes live after publication · 5DL-B-240 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026240,
  author    = {Fan, Yafu},
  title     = {Fokker-Planck Drift-Diffusion on Long Sales Pages: Belief-Drift Rates and First-Passage Times to the Payment Barrier},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

Other chapter answers in this book