What does Thumb Zones and the First Screen conclude, in numbers, about “Practice: The Nightamber Product Page from Diagnosis and Redesign to a Pre-Registered A/B Test”?
Answer: Chapter 8 takes Nightamber through the whole method: after the redesign the viewport tax falls to 0.258 and 0.267, product facts on the first screen grow to 164 pixels, the price and the button are always visible, and the actions of the purchase path fall in the comfortable zone for both the right-hand and the left-hand model; the pre-registered four-week test, with 19,200 sessions per arm, can detect relative lifts of 0.149 and above, while a lift of 0.10 has only a 0.477 chance of being seen. Marked boxes separate evidence, calculations, sources and hypotheses, each hypothesis stating what would refute it; the source studied is the Kaogongji and its four conditions of good work: "heaven has its seasons, earth has its qi, materials have their beauty, craftsmen have their skill".
Scope of the numbers: All brands and figures are invented samples computed by the book's programs; laws on privacy consent and accessibility are described only in general terms and are not legal advice.
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: 0.10, 0.149, 0.477, 19200
| sessions per arm 19,200 over 4 weeks; minimum detectable lift at power 0.80 | 0.149 |
| analytic power at lift 0.10 | 0.477 |
| analytic power at lift 0.15 | 0.806 |
| analytic power at lift 0.20 | 0.961 |
| sample-ratio check: stop and debug if one arm differs from 19,200 by more than 322 sessions | |
| simulated A/A (no true change) share declared a win 0.021 | |
| simulated true lift 0.10 share declared a win 0.466 | |
| simulated true lift 0.20 share declared a win 0.957 |
Show the full program
# Chapter 8. p83: The pre-registered A/B test of the redesigned Nightamber product template.
# Traffic and baseline are the Chapter 1 p12 sample assumptions. Simulated tests draw each arm's count from a
# normal approximation to the binomial (seeded); they check the design, they are not results of any test.
import math
import random
from statistics import NormalDist
WEEKLY, WEEKS = 9600, 4
BASE = 0.038 # add-to-bag per session, control arm (assumed)
ALPHA, POWER = 0.05, 0.80
N = WEEKLY * WEEKS // 2 # sessions per arm
nd = NormalDist()
za, zb = nd.inv_cdf(1 - ALPHA / 2), nd.inv_cdf(POWER)
def ztest(k1, k2, n):
p = (k1 + k2) / (2 * n)
se = math.sqrt(p * (1 - p) * 2 / n)
return (k2 - k1) / n / se if se > 0 else 0.0
def power_at(lift):
p2 = BASE * (1 + lift)
se = math.sqrt((BASE * (1 - BASE) + p2 * (1 - p2)) / N)
return nd.cdf((p2 - BASE) / se - za)
lo, hi = 0.0, 1.0
for _ in range(60):
mid = (lo + hi) / 2
lo, hi = (mid, hi) if power_at(mid) < POWER else (lo, mid)
print("sessions per arm {:,} over {} weeks; minimum detectable lift at power 0.80: {:.3f}".format(
N, WEEKS, hi))
for lift in (0.10, 0.15, 0.20):
print(" analytic power at lift {:.2f}: {:.3f}".format(lift, power_at(lift)))
srm = nd.inv_cdf(1 - 0.001 / 2) * math.sqrt(2 * N * 0.25)
print("sample-ratio check: stop and debug if one arm differs from {:,} by more than {:.0f} sessions".format(
N, srm))
rng = random.Random(8137)
def draw(p):
return max(0, round(rng.gauss(N * p, math.sqrt(N * p * (1 - p)))))
SIMS = 4000 # a win = z above the two-sided critical value: nominal A/A rate 0.025
for label, lift in (("A/A (no true change)", 0.0), ("true lift 0.10", 0.10), ("true lift 0.20", 0.20)):
hits = sum(1 for _ in range(SIMS) if ztest(draw(BASE), draw(BASE * (1 + lift)), N) > za)
print("simulated {:<22} share declared a win {:.3f}".format(label, hits / SIMS))Single source and citation
Fan, Y. (2026). Mobile Thumb-Zone Kinetics, Dark-Luxury Micro-Interactions and Above-the-Fold Visual Retention Engineering (Version 0.1.0), Chapter 8: Practice: The Nightamber Product Page from Diagnosis and Redesign to a Pre-Registered A/B Test. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-137 · v0.1.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026137,
author = {Fan, Yafu},
title = {Mobile Thumb-Zone Kinetics, Dark-Luxury Micro-Interactions and Above-the-Fold Visual Retention Engineering},
year = {2026},
publisher = {5D Library},
edition = {0.1.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · Method: Four Measurable Losses, the Book's Sample, Evidence Grades and A/B Design
- Chapter 2 · The Thumb Zone: the Geometry of What a Finger Can Reach
- Chapter 3 · The Sticky-Header Tax: Browser Bars, Safe Areas, Stacked Banners and Floating Widgets
- Chapter 4 · The Arithmetic of Gold on Black: Display Polarity, Halation, Contrast Floors and Ceilings, and Price Numerals
- Chapter 6 · Above the Fold: Pixel Allocation, the Arithmetic of Three Web Metrics, the Evidence on Skeleton Screens and a Hero Byte Budget
- Chapter 7 · The Boutique Playbook: Product Page, Checkout, Private-Message Entry, Membership Page and the Distillation Spec