Published in:
Open Access
01-12-2005 | Debate
Systems validation: application to statistical programs
Author:
Rickey E Carter
Published in:
BMC Medical Research Methodology
|
Issue 1/2005
Login to get access
Abstract
Background
In 2003, the United States Food and Drug Administration (FDA) released a guidance document on the scope of "Part 11" enforcement. In this guidance document, the FDA indicates an expectation of a risk-based approach to determining which systems should undergo validation. Since statistical programs manage and manipulate raw data, their implementation should be critically reviewed to determine whether or not they should undergo validation. However, the concepts of validation are not often discussed in biostatistics curriculum.
Discussion
This paper summarizes a "Plan, Do, Say" approach to validation that can be incorporated into statistical training so that biostatisticians can understand and implement validation principles in their research.
Summary
Validation is a process that requires dedicated attention. The process of validation can be easily understood in the context of the scientific method.