Statistical Analysis of Large Administrative Health Databases: Emerging Challenges and Strategies

Why Study Administrative Health Data?

This data offers us a valuable opportunity to deal with practical situations where studies or experiments are infeasible, unethical or too costly to perform. 

While administrative data offer researchers a rich source of information, they posit many statistical challenges. These have to be adequately addressed to ensure a positive trade-off between quantity versus quality of the data. 

Typically, health administrative data databases are large in scale and may be of variable quality. Some may only record variables that are:

• are easily available,
• only relevant to billing and finances, such as in the case of claims data.

Records are often kept without consideration of the use of this data in research or clinical practice.

Areas of Exploration

Challenges in Big Health Data

Includes addressing statistical challenges in the analysis of large-scale administrative health data, such as the Clinical Practice Research Datalink (CPRD) and Childhood, Adolescent and Young Adult Cancer Survivors Program (CAYACS) databases.

New Methods of Analysis

Includes developing original and innovative methods of analyzing large-scale databases, to advance foundational work and facilitate genuine applications.

Public Health Value

Includes exploring use-cases and how to best capitalize on the information carried by large-scale administrative health databases. For example, in gaining a better understanding of health care demand. 

Solving Global Challenges

Research Team’s Goal

1. To develop methods of advancing foundational work and facilitate genuine application.
2. To develop methods of advancing foundational work and facilitate genuine application.