Statistical Justification for Sample Size and the Use of Only 3 Lots

Overview:

This webinar explains how to choose and justify a sample-size for Lots that are included in Process Validation studies.

The statistical methods discussed during the webinar include the following:

• Confidence intervals
• Confidence / Reliability Calculations (for variables & attributes)

It then explains how to analyze those samples in such a way that they provide statistically valid final %Reliability for the production Process itself. One example is worked through completely.

Why should you Attend: Almost all manufacturing and development companies perform at least some process validation studies, but it is difficult to decide how many Lots to include in the study and how large the Sample per Lot should be.

This webinar provides a "statistical" justification and method for determining Sample Sizes, and a statistical justification for using only 3 Lots (which is the typical number, especially in industries regulated by the FDA).

Those justifications can then be documented in Protocols or regulatory submissions, or can be given to regulatory auditors who may ask for them during onsite audits at your company. Thus, this webinar is designed to help you avoid regulatory delays in product approvals and to prevent an auditor from issuing you a nonconformity.

This webinar does not address clinical trials, nor bulk-solution processes. It applies to unitized products such as pills, drug-filled syringes, medical devices, and components.

Areas Covered in the Session:

• Introduction:
  • Regulatory requirements
  • Basic concepts and vocabulary
• Calculation of Sample Size to be taken from each Lot in the Validation study
• Calculation of % Confidence and %Reliability ( = %-in-specification) for each Lot
• Calculation of % confidence and %Reliability for the Production Process
• Worked example (with all calculations)
• Example summary "justification" statement
• Access to instructor's website, for downloading free relevant statistical software

Who Will Benefit:

• QA/QC Supervisor
• Process Engineer
• Manufacturing Engineer
• R&D Engineer