What does Compliant Referral Commissions conclude, in numbers, about “Estimating the Parameters and a Robust Slope: When Unsure, Err Low”?
Answer: Chapter 6 gives a minimax-regret slope of 0.4705 with a worst regret of 0.1010 under uncertain risk aversion.
Scope of the numbers: Its parameters are illustrative; all calculations are generated by its programs; the book is not individual legal, tax or financial advice, and regulations are given only in gist, subject to human review of the text in force before publication. Marked boxes separate published evidence, runnable Python calculations (17 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. printed values that match the answer: 0.1010, 0.4705
| b* over the interval: 0.3571 (r = 1.0) to 0.6897 (r = 0.25) | ||
| slope | revenue rate | worst regret |
| 0.3571 | 0.1429 | 0.2325 |
| 0.4500 | 0.1800 | 0.1208 |
| 0.5000 | 0.2000 | 0.1600 |
| 0.5263 | 0.2105 | 0.2244 |
| 0.4705 | 0.1882 | 0.1010 |
| 0.6897 | 0.2759 | 0.8668 |
| minimax-regret slope 0.4705, worst regret 0.1010 | ||
| midpoint of the b* range: 0.5234 |
Show the full program
# Chapter 6. p62: a slope that is safe when risk aversion is unknown.
# LEN model of p11 with c = 0.05 and s2 = 36. The operator only knows
# r lies in [0.25, 1.0]. Relative regret of slope b at r:
# (S(b*(r)) - S(b)) / S(b*(r)).
# The minimax-regret slope minimises the worst relative regret over
# r in that interval (grid over r in steps of 0.01, slope in steps of
# 0.0005). Revenue rate = slope * g with gross margin ratio g = 0.4.
# Illustrative values.
C, S2, G = 0.05, 36.0, 0.4
RS = [0.25 + 0.01 * k for k in range(76)]
def surplus(b, r):
e = b / C
return e - C * e * e / 2.0 - r * b * b * S2 / 2.0
def bstar(r):
return 1.0 / (1.0 + r * C * S2)
def worst(b):
return max((surplus(bstar(r), r) - surplus(b, r))
/ surplus(bstar(r), r) for r in RS)
slopes = [0.30 + 0.0005 * k for k in range(1001)]
bmm = min(slopes, key=worst)
print("b* over the interval: {:.4f} (r = 1.0) to {:.4f} (r = 0.25)"
.format(bstar(1.0), bstar(0.25)))
print(" slope revenue rate worst regret")
for b in (bstar(1.0), 0.45, 0.5, bstar(0.5), bmm, bstar(0.25)):
print("{:7.4f} {:13.4f} {:13.4f}".format(b, b * G, worst(b)))
print("minimax-regret slope {:.4f}, worst regret {:.4f}".format(
bmm, worst(bmm)))
print("midpoint of the b* range: {:.4f}".format(
(bstar(1.0) + bstar(0.25)) / 2.0))Single source and citation
Fan, Y. (2026). Incentive-Compatible Compliant Referral Programmes: Commission Slopes in a Principal-Agent Model, a Second-Tier Slope of Zero and Maximal Referrals within Anti-Pyramid Limits (Version 1.0.0), Chapter 6: Estimating the Parameters and a Robust Slope: When Unsure, Err Low. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-279 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026279,
author = {Fan, Yafu},
title = {Incentive-Compatible Compliant Referral Programmes: Commission Slopes in a Principal-Agent Model, a Second-Tier Slope of Zero and Maximal Referrals within Anti-Pyramid Limits},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · Linear Contracts: Cost, Risk and Noise Set the Optimal Commission Slope
- Chapter 2 · Multitasking: a Second-Tier Slope Pushes Effort from Selling to Recruiting
- Chapter 3 · Referral Trees: Expected Size in a Branching Process and Saturation in a Finite Market
- Chapter 4 · Maximising Referrals: a Bonus Paid Once, Only for a Real Purchase
- Chapter 5 · The Compliance Boundary: Constrained Optimisation and a Screen for Commission Plans
- Chapter 7 · Classical Sources: the Two Handles of the Han Feizi and Mackay's Crowds
- Chapter 8 · Closing the Loop: a Compliance Review Sheet, the Commission Slope Calculator and Pre-Registered Tests