Fundamentals

Gini Coefficient: What It Measures and How to Interpret It

By Daniel Sardá · Published on October 22, 2026

6 min read1,187 words

The Gini coefficient summarizes the inequality of a distribution in a single number. Understanding its scale, assumptions, and limits helps prevent it from becoming a verdict it cannot deliver.

Imagine two communities with the same total income and the same number of residents. In the first, income is distributed relatively evenly. In the second, a small part of the population receives almost all of it. The average can be identical in both communities, but the distribution is not. The Gini coefficient summarizes that difference in a single number.

It is a measure of inequality applied to a particular variable and population. It is commonly used to study income or consumption among people or households, although it can also be calculated for wealth. That is why saying that “the Gini is high” leaves out essential information: Gini of what, among whom, over what period, and according to which source?

Key idea: The Gini coefficient describes how concentrated a variable is. It does not explain why that distribution exists or determine whether it is fair.

How to read the Gini scale

The indicator is usually reported on one of two equivalent scales:

• From 0 to 1.
• From 0 to 100, by multiplying the first value by one hundred.

In either case, the lower end represents perfect equality: every observed unit receives exactly the same amount of the variable being measured. The upper end represents perfect inequality: one unit receives everything and all the others receive nothing.

Thus, 0.35 and 35 express the same result on different scales. Before comparing two figures, check which convention each source uses.

A higher value indicates more inequality, provided the same variable, population, and methodology are being compared. But the endpoints are mathematical reference points, not political instructions. The fact that zero represents perfect equality does not mean the indicator declares it to be the social ideal. The Gini coefficient does not incorporate judgments about rights, merit, needs, liberty, or well-being.

The intuition behind the Lorenz curve

The Gini coefficient is linked to the Lorenz curve, a visual representation of a distribution. To construct it, the population is ordered from lowest to highest by income or consumption. The cumulative share of the population is then compared with the cumulative share of the variable it receives.

In a perfectly equal distribution, 20 percent of the population would receive 20 percent of income, 50 percent would receive 50 percent, and so on. This relationship forms a diagonal known as the line of equality.

In real distributions, the Lorenz curve usually falls below that diagonal. The farther away it is, the greater the concentration. The Gini coefficient summarizes this distance through the area between the observed curve and the line of equality. You do not need to master the formula to grasp the idea: the number compresses the visual distance from a uniform distribution into one measure.

That summary comes at a cost. Two different distributions can produce the same Gini coefficient: one may show disparities among lower-income groups, while another may show concentration at the top. Where possible, it is therefore useful to pair the measure with the full curve, percentiles, or group shares.

An example with two communities

Suppose five people in community A receive 18, 19, 20, 21, and 22 units of income. In community B, they receive 2, 8, 15, 25, and 50. Both add up to 100 units and have an average income of 20 per person.

Yet the second distribution is much more concentrated. Its Gini coefficient would be higher because there is a greater distance between what each person receives, even though average income is the same.

The example shows why the average and the Gini coefficient answer different questions. Knowing the degree of inequality is not enough to know a standard of living: if every income rose in the same proportion, the Gini could remain unchanged even though everyone had more resources.

Key idea: The average tells us about the average level; the Gini coefficient tells us about relative distribution. Understanding a society requires both perspectives and often others as well.

What it measures—and what it does not

The Gini coefficient is useful because it can summarize a complex distribution and track its evolution. But it should not be confused with related indicators.

Income is not wealth. Income is a flow received over a period. Wealth is a stock of assets minus liabilities. A society may show one level of income inequality and a very different level of wealth inequality.

Inequality is not poverty. Inequality compares positions within a distribution; poverty identifies deprivation relative to a threshold. Absolute poverty can decline while the Gini rises, or a distribution can be highly equal at a generally low income level.

Inequality is not mobility. The coefficient offers a distributive snapshot for a moment or period, but it does not by itself show whether people change position over time.

Description is not explanation. The Gini coefficient does not identify the causes of a distribution. Without further research, it cannot attribute a change to education, technology, barriers to entry, demographics, taxes, or transfers.

Nor does it establish a universal threshold above which a society is “good” or “bad.” Such labels require normative criteria and additional evidence that the indicator does not contain.

How to compare figures without getting it wrong

Two values are comparable only when their underlying bases are sufficiently consistent. Before drawing conclusions, check the following:

• Variable: income, consumption, or wealth.
• Unit: people or households, including whether household size and composition are adjusted for.
• Income concept: market, gross, or disposable income after taxes and transfers.
• Coverage and period: the population included, the territory, and the measurement year.
• Source and method: survey design, data treatment, and the scale used.

These differences matter. The OECD distinguishes among several income concepts. In some statistics, it uses equivalised disposable income: income after taxes and cash transfers, adjusted for household size. That result is not equivalent to a Gini coefficient for unadjusted market income.

The World Bank likewise notes that data may be based on income or consumption and that surveys and methodologies vary across countries. A small difference between two figures may reflect changes in measurement rather than a substantive social transformation.

Caution: An isolated ranking hides methodological choices. The year, coverage, variable, and source should always travel with the number.

A tool for asking better questions

Read carefully, the Gini coefficient can help identify distributive changes and frame more precise questions. Read as a verdict, it can conceal as much as it reveals.

From an institutional perspective, a distribution may invite examination of whether the rules protect property, competition, and equality before the law; whether privileges, barriers, or the capture of political power exist; and how taxes and transfers operate. But the coefficient cannot answer those questions on its own. Nor can it automatically select a policy without considering causes, incentives, effects, and respect for liberty.

Its best use is modest and concrete: identify the variable being measured, confirm that figures are comparable, and combine the result with information on poverty, mobility, income levels, and institutional conditions. The Gini coefficient is a starting point for understanding a distribution, not the end of the analysis.