Beyond the Count

Crime Location Quotient vs. Raw Aggregates in Public Security

Jesus L. Monroy

Mar 6, 2026

The Volume illusion

In public security, Raw State Counts often lead to a “Population Trap.”

The Problem: Large states (like Estado de México) always appear as “hotspots” simply due to density.
The Noise: National trends (e.g., a 10% drop in crime) hide whether local interventions are actually working.
The Result: “Peanut-buttering” resources across high-volume areas without addressing structural issues.

Defining the quotient

The CLQ Formula

The Crime Location Quotient (CLQ) measures the “specialization” of a crime in a specific area relative to a reference region.

\[CLQ_i = \frac{C_{i} / T_{i}}{C_{ref} / T_{ref}}\]

where:

\(C_i\) = Crimes of type X in municipality i.
\(T_i\) = Total crimes in municipality i.
\(C_{ref}\) = Total crimes of type X in the State/Country.

Why CLQ Wins

3 Strategic Pillars

Relative Concentration: It identifies where a specific crime is disproportionately high, regardless of population.
Structural Diagnosis: It distinguishes between “General Disorder” and “Organized Specialization.”
The Trend Filter: In a cohort analysis, CLQ only improves if the municipality recovers faster than the national average.

Comparative Matrix

Feature	State Counts	CLQ Analysis
SuSensivity	Biased by population	Normalized/Structural
Trend tracking	Absolute change	Relative/Performance
Strategy	Reactive/General	Proactive/Targeted
Cohort suitability	Poor (low granularity)	High (dynamic tracking)

Table 1: Comparison of Public Security Metrics

The Data Mirage

Why Stats \(\neq\) Reality

92% Invisible: The Cifra Negra means we only see the tip of the iceberg.
The Reporting Bias: Higher education and higher trust = Higher “apparent” crime.
CLQ as the Filter: By focusing on the Quotient, we strip away the noise of absolute volume and reveal the underlying structure of violence.

“Official statistics tell us more about the behavior of the police than the behavior of criminals.”

Contact

Jesus L. Monroy

Economist & Data Scientist

Passionate about creating tools that make data accessible and impactful using SQL, Python, Streamlit, Shiny and Tableau in diverse sectors like Public Security, e-commerce, and Healthcare.
BA in Economics, MA in Information Technology, and Data Science/Machine Learning certification.

Portfolio | Linkedin | Twitter | Tableau