What does The Life of a Rule conclude, in numbers, about “Many Rules in Parallel: Sharing Alpha, and How Many Promoted Rules Are Duds”?
Answer: Chapter 6 shows that splitting alpha among 100 rules lengthens verdicts on useless rules by a ratio of only 1.12.
Scope of the numbers: Marked boxes separate published evidence, runnable Python calculations (20 programs), classical sources and the author's hypotheses.
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: 1.12, 100
| rules m | alpha/rule | real alpha | power | wk H0 | wk H1 | fixed wk |
| 1 | 0.05000 | 0.03322 | 0.8714 | 5.83 | 7.71 | 8.86 |
| 5 | 0.01000 | 0.00666 | 0.8709 | 6.29 | 11.69 | 14.19 |
| 10 | 0.00500 | 0.00330 | 0.8747 | 6.45 | 13.53 | 16.46 |
| 20 | 0.00250 | 0.00163 | 0.8745 | 6.49 | 15.30 | 18.70 |
| 40 | 0.00125 | 0.00084 | 0.8744 | 6.51 | 16.96 | 20.94 |
| 100 | 0.00050 | 0.00033 | 0.8744 | 6.52 | 19.31 | 23.88 |
| growth m = 1 to 100 (ratio): H0 1.12, H1 2.51, fixed 2.70 | ||||||
| family false-promotion bound at m = 100: 0.0326 (100 x 0.00033) |
Show the full program
# Chapter 6. p61: splitting alpha across many parallel rules is cheap
# Model: m rules on trial at once; to keep the chance of any false
# promotion near 0.05 the simplest split gives each SPRT alpha/m
# (Bonferroni). We compute exactly, with weekly batches of 600 visitors
# as in p41 (p0 0.03, p1 0.036, beta 0.20), the realised per-rule
# alpha, the power and the mean weeks under H0 and H1, and compare the
# one-sided fixed-sample size at the same alpha and power. Wald's A
# grows like ln(1/alpha) while B barely moves, so null rules, the
# majority of a backlog, are cut almost as fast as before.
import math
from statistics import NormalDist
P0, P1, BETA, M = 0.03, 0.036, 0.20, 600
LA = math.log(P1 / P0)
LB = math.log((1 - P1) / (1 - P0))
N_MAX = 90000
def pmf(p):
hi = min(M, int(M * p + 14 * math.sqrt(M * p * (1 - p))) + 2)
return [math.exp(math.lgamma(M + 1) - math.lgamma(j + 1)
- math.lgamma(M - j + 1) + j * math.log(p)
+ (M - j) * math.log(1 - p)) for j in range(hi + 1)]
def batched(p, alpha):
a = math.log((1 - BETA) / alpha)
b = math.log(BETA / (1 - alpha))
step = pmf(p)
open_k, keep, surv = {0: 1.0}, [], [1.0]
for t in range(1, N_MAX // M + 1):
n = t * M
bins = {}
for k, w in open_k.items():
for j, q in enumerate(step):
bins.setdefault(k + j, []).append(w * q)
open_k = {}
for k in sorted(bins):
mass = math.fsum(bins[k])
llr = k * LA + (n - k) * LB
if llr >= a:
keep.append(mass)
elif llr > b:
open_k[k] = mass
surv.append(math.fsum(open_k.values()))
return math.fsum(keep), math.fsum(surv[:-1])
def n_fixed(alpha):
nd = NormalDist()
za, zb = nd.inv_cdf(1 - alpha), nd.inv_cdf(1 - BETA)
root = math.fsum([za * math.sqrt(P0 * (1 - P0)),
zb * math.sqrt(P1 * (1 - P1))])
return math.ceil((root / (P1 - P0)) ** 2)
print("rules m alpha/rule real alpha power wk H0 wk H1 fixed wk")
base = None
for m in (1, 5, 10, 20, 40, 100):
al = 0.05 / m
a0, w0 = batched(P0, al)
a1, w1 = batched(P1, al)
nf = n_fixed(al) / M
if base is None:
base = (w0, w1, nf)
print("%7d %10.5f %10.5f %6.4f %6.2f %6.2f %8.2f"
% (m, al, a0, a1, w0, w1, nf))
print("growth m = 1 to 100 (ratio): H0 %.2f, H1 %.2f, fixed %.2f"
% (w0 / base[0], w1 / base[1], nf / base[2]))
print("family false-promotion bound at m = 100: %.4f (100 x %.5f)"
% (100 * a0, a0))Single source and citation
Fan, Y. (2026). Empirical Retirement of Live Rules: Wiring the Sequential Probability Ratio Test into Real Conversion Streams to Promote, Demote and Retire Copy Rules (Version 1.0.0), Chapter 6: Many Rules in Parallel: Sharing Alpha, and How Many Promoted Rules Are Duds. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-263 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026263,
author = {Fan, Yafu},
title = {Empirical Retirement of Live Rules: Wiring the Sequential Probability Ratio Test into Real Conversion Streams to Promote, Demote and Retire Copy Rules},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · A Weekly Glance: How a Mediocre Copy Rule Gets Promoted by Mistake
- Chapter 2 · Wald's Two Straight Lines: Boundaries, the OC Function and the Mean Sample Size
- Chapter 3 · Exact Recursions: the Long Tail of the Sample Size and the Cost of a Cap
- Chapter 4 · Connecting Real Conversion Streams: Weekly Batches and Where the Baseline Comes From
- Chapter 5 · The Rule Lifecycle as a State Machine: Promotion, Demotion and Retirement
- Chapter 7 · Classical Sources East and West: Checking by Trial in the Han Feizi, and Wald's Sequential Analysis
- Chapter 8 · Closing the Loop: Wiring the Weekly Radar's Verdicts into the Rule State Machine