The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index; none of the 5 sources its claims cite is checked for support yet.
Comparing Income Distributions Using Atkinson's Measure of Inequality
Open accessAbstract
This article is aimed at undergraduate and graduate economics students, and public sector economists, who are interested in inequality measurement. It examines the use of the Atkinson inequality measure to compare income distributions. A major feature of this measure is that distributional value judgements are made explicit, via the use of a particular form of social welfare function. Emphasis is given to the interpretation of changes in inequality and the role of the relative inequality aversion parameter, which reflects an important feature of those value judgements.
Verifying this paper
8 of 9 steps done · this page updates itself — you can leave and come back
- Registry recordVerified
- Full textRead the full text
- Reference list18 references found
- Reference checkChecking each cited work — 19 of 19
- StatisticsRecomputed
- Claims45 claims anchored to a quote
- Cited sourcesChecked
- Self-checkChecked
- VerificationFindings verified
Overview
CoChat Summary
TL;DR
This paper explains and interprets Atkinson’s inequality measure, emphasizing that it makes distributional value judgements explicit through a social welfare function and a relative inequality aversion parameter. It shows how to interpret values and changes using an abbreviated welfare function, equivalent small distributions, pivotal income, elasticities, and inequality-preserving changes.
Key findings
- Atkinson’s measure is \(A = 1 - y_e/\bar{y}\), where \(y_e\) is the equally distributed equivalent income from an additive, concave welfare function with relative inequality aversion \(\epsilon\); it is the ratio of a power mean of order \(1-\epsilon\) to the arithmetic mean.
- For interpretation, an increase in \(A\) from 0.25 to 0.30—a 20% increase in inequality—would require a 6.67% increase in arithmetic mean income for the judge to be indifferent. In the leaky-bucket example, if the richer income is twice the poorer and \(\epsilon=1\), taking $1 from the richer person requires only 50 cents to the poorer person for constant welfare; if \(\epsilon=0.2\), a leak of 0.13 is tolerated.
- In the equivalent small-distribution approach, for \(\epsilon=0.5\) and \(n=2\), the top income share increases by 3.2% when \(A\) rises by 20%; for \(n=4\), it increases by 6.7%. For \(\epsilon=0.2\) with \(n=6\) and \(n=8\), the top share must increase by 6.7% and 7.0%; for \(\epsilon=0.9\) with \(n=6\) and \(n=8\), by 7.2% and 17.4%. Excess-share changes vary from about 8% to over 20% for \(\epsilon=0.9\) and \(n=8\).
- Pivotal income is \(y^* = \bar{y}(1-A)^{(\epsilon-1)/\epsilon}\); if \(\epsilon=0.5\) and \(A=0.3\), \(y^*=1.43\bar{y}\) and is 2.04 times the equally distributed equivalent income. Elasticities with respect to inequality aversion are derived, and intersections of Atkinson profiles can arise without pathological assumptions; in an 8-person example, increasing 20 to 25 or 50 to 60 reduces inequality for lower aversion but increases it at aversion levels 3.9 and 2.25 respectively, while reducing 5 to 4 and raising 10 to 15 reduces inequality for \(\epsilon<1.55\), after which \(A\) is higher. Inequality-preserving changes exist: distributions [0.2, 2.8, 3.0] and [0.6, 1.0, 4.4] have the same Atkinson measure.
Methods
- Methodological/expository analysis of Atkinson’s measure, deriving formulas for the measure, abbreviated welfare function, equivalent small distribution, pivotal income, elasticities with respect to inequality aversion, and inequality-preserving changes.
- Uses numerical examples and hypothetical distributions—such as 8 individuals with incomes 5, 10, 20, 50, 100, 300, 500, 1000, and a three-person example with sum 6, mean 2, \(\epsilon=0.3\), and \(y_e=1.8\)—rather than an empirical sample.
- Appendix presents asymptotic sampling properties for Atkinson’s measure following Thistle (1990), including formulas for asymptotic variances of \(A\) and \(y_e\).
Limitations
- The paper states that the discussion is in terms of single individuals and avoids complications common to inequality measurement: choice of unit of analysis (households or families), accounting period, and welfare metric; references are kept to a minimum.
- The paper states that no simple conditions or formulae determine intersecting Atkinson profiles; full information about the income distribution is needed, no easily applicable rule establishes re-ranking over a range of \(\epsilon\), and sensitivity analyses are important.
- Evident from the text: there is no empirical application or real survey data; the illustrations are hypothetical/numerical, so empirical performance and standard errors are not demonstrated beyond the appendix formulas. The paper also states that the equivalent-small-distribution approach may not provide information non-specialists can easily digest without discussion.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 1 Not valid · 5 Not checked · 39 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Inequality-reducing changes in one range of the distribution can be matched by inequality-increasing changes in another range.”
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 7 Conclusions
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Many distributional changes, involving higher inequality in the lower-income ranges of the distribution, are generally capable of producing intersections.”
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 7 Conclusions
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Converting to terms involving rather than , it can be seen, for example, that an increase in from 0.25 to 0.30, which represents a 20 per cent increase in inequality, would have to be compensated by an increase in arithmetic mean income of 6.67 per cent, for the judge to be indifferent to the change.”
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 2 The Atkinson Inequality Measure
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Intersections of profiles of the Atkinson measure (plotted against the inequality aversion parameter) can arise without the need for pathological assumptions about the income distribution.”
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 7 Conclusions
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“However, the excess share decreases monotonically as the degree of inequality aversion, , increases, for which more weight is attached to the lower income range.”
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 3 An Equivalent Small Distribution
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
16 more claims
Create a free account to see all 45 claims and to verify the 5 references still open.
- It may state two separate claims as one. 18
- Probably not a substantial claim. 8
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 2 The Atkinson Inequality Measure
“an increase in from 0.25 to 0.30, which represents a 20 per cent increase in inequality, would have to be compensated by an increase in arithmetic mean income of 6.67 per cent, for the judge to be indifferent to the change.”
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 2 The Atkinson Inequality Measure
“ * = (1 - )(8)”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 7 Conclusions
“| 0.9 0.84 | 0.63 | 0.55 | 0.46 | 0.87 | 0.68 | 0.59 | 0.54 |”
§ Comparing Income Distributions Using Atkinson's Measure of Inequality > 3 An Equivalent Small Distribution
“ = 1 - " 1 ( 1- + ( -1) µ 1 - -1 ¶ 1- )# 1(1-) (10”
Citations
Cites
On the measurement of inequality
Atkinson, A. B. (1970) · Journal of Economic Theory · doi:10.1016/0022-0531(70)90039-6 · Cited by 6,550
The analysis of household surveys: A microeconometric approach to development policy
Deaton, A. (1997) · doi:10.1596/0-8018-5254-4 · Cited by 4,877
The Measurement of the Inequality of Incomes
Dalton, H. (1920) · The Economic Journal · doi:10.2307/2223525 · Cited by 1,466
The Distribution and Redistribution of Income
Lambert, P. J. (1992) · doi:10.1007/978-1-349-22409-8_9 · Cited by 699
Measuring Attitudes Towards Inequality
Amiel, Y., Creedy, J., & Hurn, S. (1999) · The Scandinavian Journal of Economics · doi:10.1111/1467-9442.00142 · Cited by 188
Self-citationA SOCIAL WELFARE VIEW OF THE MEASUREMENT OF INCOME EQUALITY
Aigner, D. J., & Heins, A. J. (1967) · Review of Income and Wealth · doi:10.1111/j.1475-4991.1967.tb00732.x · Cited by 116
Large Sample Properties of Two Inequality Indices
Thistle, P. D. (1990) · Econometrica · doi:10.2307/2938198 · Cited by 44
The Palgrave Companion to Cambridge Economics
Cord, R. A. (2017) · Palgrave Macmillan UK eBooks · doi:10.1057/978-1-137-41233-1 · Cited by 33
The effect on inequality of changing one or two incomes
Lambert, P. J., & Lanza, G. (2006) · The Journal of Economic Inequality · doi:10.1007/s10888-006-9020-1 · Cited by 27
An Elementary Interpretation of the Gini Inequality Index
Subramanian, S. (2002) · Theory and Decision · doi:10.1023/a:1020237003687 · Cited by 27
Effect of the rise of a person's income on inequality
Hoffmann, R. (2001) · Brazilian Review of Econometrics · doi:10.12660/bre.v21n22001.2751 · Cited by 20
Interpreting inequality measures and changes in inequality
Creedy, J. (2015) · New Zealand Economic Papers · doi:10.1080/00779954.2015.1045929 · Cited by 12
Self-citationThe Impact of a Marginal Subsidy on G ini Indices
Corvalán, A. (2012) · Review of Income and Wealth · doi:10.1111/roiw.12010 · Cited by 11
The Redistributive Effects of a Minimum Wage Increase in New Zealand: A Microsimulation Analysis
Alinaghi, N., Creedy, J., & Gemmell, N. (2020) · Australian Economic Review · doi:10.1111/1467-8462.12381 · Cited by 11
Self-citationJenkins, S. P. (2017) · Palgrave Macmillan UK eBooks · doi:10.1057/978-1-137-41233-1_52 · Cited by 6
Alternative Distributions for Inequality Comparisons
Creedy, J. (2017) · Australian Economic Review · doi:10.1111/1467-8462.12238 · Cited by 5
Self-citationEarly Gini's contributions to inequality measurement and statistical inference
Forcina, A., & Giorgi, G. M. (2005) · IRIS Research product catalog (Sapienza University of Rome) · Cited by 5
The Atkinson Inequality Measure and Inequality AversionPreprint
Creedy, J. (2019) · RePEc: Research Papers in Economics · Cited by 4
Self-citationA note on inequality-preserving distributional changes
Creedy, J. (2016) · New Zealand Economic Papers · doi:10.1080/00779954.2016.1192215 · Cited by 3
Self-citation
Research works printed but not linked: 2
- Brandolini A., 2018, Anthony Barnes Atkinson, Biographical Memoirs of Fellows of the British Academy, 17, 179
- Gini C., 1914, Sulla misura della concentazione e della variabilità dei cratteri, Atti del Reale Istituto Veneto di Scienze, Lettere ed Arti, 73, 1203
Cited by
Distributional Comparisons Using the Gini Inequality Measure
Creedy, J. (2023) · Australian Economic Review · doi:10.1111/1467-8462.12534
Self-citationRiaz, M., Muhammad, F., & Ahmad, S. (2026) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610918.2026.2674250
Metadata
- Authors
- Creedy, J.
- Affiliations
- Victoria University of Wellington (NZ)
- Corresponding author
- Creedy, John
- ORCID
- Creedy, John
- Venue
- Australian Economic Review
- Publisher
- Wiley
- Published
- 2023-01-09
- Volume
- 56
- Issue
- 1
- Pages
- 141-155
- ISSN
- 0004-9018 (ISSN-L)
- 1467-8462
- OpenAlex
- W3183288060
- Cited by
- 2
- References
- 18
- Citations by year
- 2026: 1 · 2023: 1
- FWCI
- 0.58
- Type
- journal article
- Language
- en
- Open access
- Locations
- Australian Economic Review (publishedVersion)
- ResearchArchive–Te Puna Rangahau (Victoria University of Wellington) (submittedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Funders
- Ministry of Business, Innovation and Employment
- Topics
- Social Sciences › Sociology and Political Science › Income, Poverty, and Inequality
- Social Sciences › Economics, Econometrics and Finance › General Economics, Econometrics and Finance › Economic Theory and Policy
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Labor market dynamics and wage inequality
- Keywords
- Atkinson index, income inequality measurement, income distribution comparison, social welfare function, welfare economics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-11-16, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-16 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.