Skip to content

Negative Binomial Regression

Definition

A count regression model that adds a dispersion parameter to absorb overdispersion, the pattern where a crime count's variance exceeds its mean, producing more honest standard errors than Poisson regression on the same data.

Related terms

Crime Rate
The number of recorded offences of a given type divided by the population at risk, usually per 100,000 people, which allows comparison...
Ecological Fallacy
The error of applying a statistical association observed at the population or group level to an individual, without verifying that the individual...
Interrupted Time-Series Design
A design that compares the trend in a crime series before and after an identified intervention date, testing for a change in...
Poisson Regression
A regression model for count outcomes, such as burglaries per ward per month, that assumes the variance of the counts equals their...
Trend Index
A rate rebased to 100 in a chosen base year so that later years can be read directly as a percentage change...

Explained in

Your journey to becoming a forensic professional starts here.

Practice with mock tests, learn from structured notes, and get your questions answered by a global forensic community, all in one place.