# When does poor governance presage biosecurity risk?

## TL;DR

This paper explores how statistical modeling of detailed consignment data can improve biosecurity inspection decisions, moving beyond traditional reliance on historical interception records.

## Contribution

It introduces a statistical modeling approach using generalized linear mixed models to better inform biosecurity inspection strategies based on detailed consignment information.

## Key findings

- Statistical profiles improve inspection decision accuracy.
- Graphical summaries offer insights into pathway governance.
- Models outperform historical record-based methods.

## Abstract

Border inspection, and the challenge of deciding which of the tens of millions of consignments that arrive should be inspected, is a perennial problem for regulatory authorities. The objective of these inspections is to minimise the risk of contraband entering the country. As an example, for regulatory authorities in charge of biosecurity material, consignments of goods are classified before arrival according to their economic tariff number (Department of Immigration and Border Protection, 2016). This classification, perhaps along with other information, is used as a screening step to determine whether further biosecurity intervention, such as inspection, is necessary. Other information associated with consignments includes details such as the country of origin, supplier, and importer, for example. The choice of which consignments to inspect has typically been informed by historical records of intercepted material. Fortunately for regulators, interception is a rare event, however this sparsity undermines the utility of historical records for deciding which containers to inspect. In this paper we report on an analysis that uses more detailed information to inform inspection. Using quarantine biosecurity as a case study, we create statistical profiles using generalised linear mixed models and compare different model specifications with historical information alone, demonstrating the utility of a statistical modelling approach. We also demonstrate some graphical model summaries that provide managers with insight into pathway governance.