Crime Concentration Index
Also known as: Crime Concentration at Place, Hot-Spot Concentration Measure, Cumulative Crime Concentration, Law of Crime Concentration
The crime concentration index quantifies how unevenly crime is distributed across micro-geographic places such as street segments or addresses. Building on Sherman, Gartin, and Buerger's 1989 discovery that a small fraction of addresses produces most calls for police service, and formalized in Weisburd's 2015 'law of crime concentration', it expresses the share of all crime accounted for by the most crime-prone places.
Key highlights
- Reduces a complex spatial crime distribution to an intuitive, comparable summary — the share of crime at the worst places.
- Provides the empirical foundation for place-based and hot-spot policing by pinpointing the small set of places that drive most crime.
- Bandwidth and Gini-type indices allow comparison across cities, crime types, and years on a common scale.
- Reveals the striking temporal stability of high-crime places, supporting the criminology of place as a unit of analysis.
- Requires only geocoded counts, data routinely available from police records systems.
Intuition
This section is available to Pro members. Upgrade to Pro
How it works
This section is available to Pro members. Upgrade to Pro
When to use it
Use a crime concentration measure when you have geocoded incident data and want to describe and compare how spatially concentrated crime is — across cities, crime types, or over time — and to target hot spots for place-based policing. It is the natural descriptive companion to hot-spot statistics and supports testing whether concentration is stable, the empirical core of the criminology of place. It is descriptive, not inferential: it tells you where and how concentrated crime is, not why. It is sensitive to the spatial unit and to low base rates, so it should not be over-interpreted when counts are sparse, and it does not establish that high-crime places are causally distinct without further modeling.
Strengths & limitations
- Reduces a complex spatial crime distribution to an intuitive, comparable summary — the share of crime at the worst places.
- Provides the empirical foundation for place-based and hot-spot policing by pinpointing the small set of places that drive most crime.
- Bandwidth and Gini-type indices allow comparison across cities, crime types, and years on a common scale.
- Reveals the striking temporal stability of high-crime places, supporting the criminology of place as a unit of analysis.
- Requires only geocoded counts, data routinely available from police records systems.
- Purely descriptive: it quantifies concentration but does not explain its causes or guarantee that interventions will reduce crime.
- Highly sensitive to the spatial unit of analysis; concentration appears stronger at finer units, complicating cross-study comparison.
- Many micro-places have zero crime, which inflates apparent concentration and can make the index unstable for rare crime types.
- Cumulative-share figures depend on how the denominator (the universe of places) is defined, which is not always standardized.
- Stability findings can be confounded by changes in reporting, geocoding quality, or boundary definitions over time.
Common pitfalls
This section is available to Pro members. Upgrade to Pro
Applications
This section is available to Pro members. Upgrade to Pro
Frequently asked
What does the 'law of crime concentration' actually claim?
Weisburd's law holds that for a defined cumulative proportion of crime, a narrow and predictable bandwidth of the smallest spatial units (such as street segments) will account for it. Empirically, roughly 25% of crime concentrates at about 0.4–1.6% of segments and 50% at about 2–6%, with similar figures recurring across cities. The law also asserts that these high-crime places are temporally stable.
Why does the spatial unit matter so much?
Concentration is partly mechanical: the finer the unit, the more zero-crime units exist and the more concentrated crime appears. Measuring at the address level yields higher concentration than at the segment level, which is higher than at the neighborhood level. For valid comparison, studies must hold the unit constant, and the criminology of place generally favors street segments as a meaningful, stable micro-unit.
How is the crime concentration index related to hot-spot analysis?
They are complementary. The concentration index is a global descriptive summary of how unequally crime is distributed across all places. Hot-spot analysis (e.g., Getis-Ord Gi*, kernel density) is a local, inferential method that identifies which specific places are statistically significant clusters. Concentration tells you that crime is concentrated; hot-spot analysis tells you where the significant clusters are.
Sources
- 1.Sherman, L. W., Gartin, P. R., & Buerger, M. E. (1989). Hot spots of predatory crime: Routine activities and the criminology of place. Criminology, 27(1), 27–56.
- 2.Weisburd, D. (2015). The law of crime concentration and the criminology of place. Criminology, 53(2), 133–157.
You have read it. What now?
Cite this page
ScholarGate. (2026, June 22). Crime Concentration Index. ScholarGate. https://scholargate.app/criminology/crime-concentration-index