Customer Testimonials
|
|
Subscribe NewsletterUsing Statistical Methods for Effective Outlier Detection
Product Id
:
600190
Overview: Statistical outlier detection has become a popular topic as a result of the US Food and Drug Administration's out of specification (OOS) guidance and increasing emphasis on the OOS procedures of pharmaceutical companies.
When a test fails to meet its specifications, the initial response is to conduct a laboratory investigation to seek an assignable cause. As part of that investigation, an analyst looks for an observation in the data that could be classified as an outlier.
When a test fails to meet its specifications, the initial response is to conduct a laboratory investigation to seek an assignable cause. As part of that investigation, an analyst looks for an observation in the data that could be classified as an outlier.
Areas Covered in the Session:
- What is an outlier?
- How to label an outlier
- Extreme Studentized Deviate Test
- Dixon Test
- Graphical methods to determine outliers
Who Will Benefit:
- Management
- Research and Development
- Regulatory Affairs personnel
- Quality assurance/quality control personnel
- Auditors and inspectors