This Statistical training presents techniques that are accepted in industry while maintaining statistical rigor.
Statistical outlier detection has become popular due to out of specification (OOS) procedures. When a test fails to meet its specifications, the initial response is to look for an observation in the data that could be classified as an outlier.
Areas Covered in the Seminar:
- What is an Outlier, and Why are they Important?
Boxplots, Trimmed Means, Confidence Intervals
- Outlier Identification
Extreme Studentized Deviate Test, Dixon Test
- Regression
Influential Observations, Effect on parameters, residual analysis
- Comparing the Methods
- Case Study
Who Will Benefit:
This web seminar will provide valuable assistance to all regulated companies that need to validate their systems, including companies in the Medical Device, Diagnostic, Pharmaceutical, and Biologics fields. The employees who will benefit include:
- QA managers and personnel
- Validation specialists
- Quality system auditors
- Consultants
Instructor Profile
Mr. Steven Walfish is the founder and President of Statistical Outsourcing Services. He brings over 17 years of industrial experience providing statistical solutions to complex business problems. Mr. Walfish was Senior Manager Biostatistics, Nonclinical at Human Genome Sciences in Rockville MD. Mr. Walfish has held positions with PricewaterhouseCoopers, Chiron Diagnostics and Johnson & Johnson. Mr. Walfish holds a Bachelors of Arts in Statistics from the University of Buffalo, Masters of Science in Statistics from Rutgers University and an Executive MBA from Boston University.
