What does Bunching at Turnover Thresholds conclude, in numbers, about “Three Confounds: Round Numbers, the Limits of Identification and Reporting Responses”?
Answer: The baseline ratio is 0.6007. In world R, the bin from 98 to 100 holds 884 firms and a ratio of 0.5991, no different from the baseline; in world M, the same bin holds 843 firms and the ratio rises to 0.6315, 13.0 standard errors above the baseline. A real response lowers sales and card receipts together and leaves the ratio unchanged; a reporting response lowers only the denominator and pushes the ratio up.
Scope of the numbers: Parameters are illustrative and the threshold is always written T; all calculations are generated by the book's programs. The book does statistical analysis and compliance checking only, teaches no way of staying under a threshold, and is general analysis, not individualised tax, legal or financial 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: 0.5991, 0.6007, 0.6315, 100, 13.0, 843
| baseline traced/declared (60-90): 0.6007 | ||||||
| bin | n(R) | ratio(R) | z(R) | n(M) | ratio(M) | z(M) |
| 92- 94 | 330 | 0.5971 | -1.1 | 321 | 0.5966 | -1.4 |
| 94- 96 | 315 | 0.5911 | -3.1 | 317 | 0.5928 | -2.5 |
| 96- 98 | 303 | 0.5983 | -0.7 | 345 | 0.6016 | 0.3 |
| 98-100 | 884 | 0.5991 | -0.9 | 843 | 0.6315 | 13.0 |
| 100-102 | 180 | 0.6027 | 0.4 | 172 | 0.5939 | -1.6 |
| 102-104 | 207 | 0.5952 | -1.4 | 166 | 0.5987 | -0.5 |
| 104-106 | 193 | 0.5962 | -1.1 | 185 | 0.5974 | -0.8 |
| 106-108 | 191 | 0.6032 | 0.6 | 169 | 0.6028 | 0.5 |
Show the full program
# Chapter 5. p53: real response or reporting response?
# Bunching below T can come from firms that really sell less or from
# turnover that is under-declared. A third-party trace (here the
# card-payment share of sales, phi, drawn between 0.5 and 0.7)
# separates them: a real response keeps traced / declared at phi; an
# under-declaration raises it. World R: a share 0.3 of firms with
# true sales in (T, T + 15] really stop just below T. World M: the
# same firms keep selling but declare just below T. Illustrative.
import math
import random
SEED, N, T, SHARE = 20261113, 20000, 100.0, 0.3
def world(rng, misreport):
rows = []
for _ in range(N):
s = rng.lognormvariate(math.log(80.0), 0.5)
phi = rng.uniform(0.5, 0.7)
moved = T < s <= T + 15 and rng.random() < SHARE
below = T - abs(rng.gauss(0.0, 1.0))
if moved and misreport:
rows.append((below, phi * s))
elif moved:
rows.append((below, phi * below))
else:
rows.append((s, phi * s))
return rows
def by_bin(rows, lo, hi):
vals = [t / d for d, t in rows if lo <= d < hi]
m = math.fsum(vals) / len(vals)
sd = math.sqrt(math.fsum((v - m) ** 2 for v in vals) / (len(vals) - 1))
return len(vals), m, sd / math.sqrt(len(vals))
if __name__ == "__main__":
rng = random.Random(20261113)
wr, wm = world(rng, False), world(rng, True)
base = by_bin(wr, 60.0, 90.0)[1]
print("baseline traced/declared (60-90): {:.4f}".format(base))
print("bin n(R) ratio(R) z(R) n(M) ratio(M) z(M)")
for lo in range(92, 108, 2):
nr, mr, sr = by_bin(wr, lo, lo + 2)
nm, mm, sm = by_bin(wm, lo, lo + 2)
print("{:3d}-{:3d} {:7d} {:9.4f} {:7.1f} {:6d} {:9.4f} {:7.1f}"
.format(lo, lo + 2, nr, mr, (mr - base) / sr, nm, mm,
(mm - base) / sm))Single source and citation
Fan, Y. (2026). Bunching at Tax Thresholds and the Distribution of Turnover: Behavioural Elasticities Revealed by Piling-Up below the Line (Version 1.0.0), Chapter 5: Three Confounds: Round Numbers, the Limits of Identification and Reporting Responses. 5D Library. DOI pending
DOI pending · monograph page goes live after publication · 5DL-B-319 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026319,
author = {Fan, Yafu},
title = {Bunching at Tax Thresholds and the Distribution of Turnover: Behavioural Elasticities Revealed by Piling-Up below the Line},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}Other chapter answers in this book
- Chapter 1 · The Spike at a Kink: Excess Mass, Polynomial Counterfactuals and the Elasticity
- Chapter 2 · Notches and Dominated Ranges: Optimization Frictions and the Marginal Buncher
- Chapter 3 · Three Components of the Counterfactual: Polynomial Degree, Integration Constraint and Bin Width
- Chapter 4 · Is the Spike Noise? Bootstrap Intervals, the Excluded Window and Power
- Chapter 6 · Registration Thresholds: Notches That Vary by Trade and Growth Held Back
- Chapter 7 · Classical Sources East and West: "One Tenth in Substance" and Smith's Four Maxims
- Chapter 8 · Closing the Loop: a Multi-Shop Compliance Self-Check, the Threshold Bunching Estimator and a Pre-Registered Test