DUBLIN–(BUSINESS WIRE)–The “Applied Statistics for Scientists and Engineers” conference has been added to ResearchAndMarkets.com’s offering.
This course provides instruction on how to apply the appropriate statistical approaches: descriptive statistics, data intervals, hypothesis testing, ANOVA, regression, ANCOVA, and model building. Once competence in each of these areas is established, industry-specific applications are presented for the participants.
Throughout 21 CFR and guidance documents for the pharmaceutical, biopharmaceutical, and medical device industries, the application of statistical methods are specified for setting validation criteria and specifications, performing measurement systems analysis (MSA), conducting stability analysis, using design of experiment (DOE) for process development and validation, developing process control charts, and determining process capability indices.
Different statistical methods are required for each of these particular applications. Data and tolerance intervals are common tools used for setting acceptance criteria and specifications. Simple linear regression and analysis-of-covariance (ANCOVA) are used for setting expiries and conducting stability analysis studies. Two-sample hypothesis tests, analysis-of-variance (ANOVA), regression, and ANCOVA are methods used for analyzing designed experiment for process development and validation studies. Descriptive statistics (distribution, summary statistics), run charts, and probability (distributions) are used for developing process control charts and developing process capability indices.
Why should you attend:
21 CFR and guidance documents for the pharmaceutical, biopharmaceutical, and medical device industries specify the application of statistical methods across the product quality lifecycle.
According to the Quality System Regulation (QSR) for medical devices, ‘Where appropriate, each manufacturer shall establish and maintain procedures for identifying valid statistical techniques required for establishing, controlling, verifying the acceptability of process capability and product characteristics.’ Although there are many statistical methods that may be applied to satisfy this portion of the QSR, there are some commonly accepted methods that all companies can and should be used to develop acceptance criteria, to ensure accurate and precise measurement systems, to fully characterize manufacturing processes, to monitor and control process results and to select an appropriate number of samples.
According to both 21 CFR and guidance documents, the need for statistical methods is well established from discovery through product discontinuation. 21 CFR specifies the ‘the application of suitable statistical procedures’ to establish both in-process and final specifications. The guidance documents necessitate the application of statistical methods for the development and validation of measurement systems, process understanding using Quality by Design (QbD) principles, process validation, as well as ensuring the manufacturing process is in control and is capable.
Areas Covered in the Session:
Objectives:
- Describe and analyze the distribution of data
- Develop summary statistics
- Generate and analyze statistical intervals and hypothesis tests to make data-driven decisions
- Describe the relationship between and among two or more factors or responses
- Understand issues related to sampling and calculate appropriate sample sizes
- Use statistical intervals to setting specifications/develop acceptance criteria
- Use Measurement Systems Analysis (MSA) to estimate variance associated with repeatability, intermediate precision, and reproducibility
- Ensure your process is in (statistical) control and capable
Agenda:
Day 1 Schedule
Lecture 1:
Basic Statistics
- Sample versus population
- Descriptive statistics
- Describing a distribution of values
Lecture 2:
Intervals
- Confidence intervals
- Prediction intervals
- Tolerance intervals
Lecture 3:
Hypothesis Testing
- Introducing hypothesis testing
- Performing means tests
- Performing normality tests and making non-normal data normal
Lecture 4:
ANOVA
- Defining analysis of variance and other terminology
- Discussing assumptions and interpretation
- Interpreting hypothesis statements for ANOVA
- Performing one-way ANOVA
- Performing two-way ANOVA
Day 2 Schedule
Lecture 1:
Regression and ANCOVA
- Producing scatterplots and performing correlation
- Performing simple linear regression
- Performing multiple linear regression
- Performing ANCOVA
- Using model diagnostics
Lecture 2:
Applied Statistics
- Setting specifications
- Measurement Systems Analysis (MSA) for assays
- Stability analysis
- Introduction to design of experiments (DOE)
- Process control and capability
- Presenting results
Speakers:
Heath Rushing
Co-founder and Principal
Adsurgo
Heath Rushing is the cofounder of Adsurgo and author of the book Design and Analysis of Experiments by Douglas Montgomery: A Supplement for using JMP. Previously, he was the JMP and Six Sigma training manager at SAS. He led a team of nine technical professionals designing and delivering applied statistics and quality continuing education courses. He created tailored courses, applications, and long-term training plans in quality and statistics across a variety of industries to include biotech, pharmaceutical, medical device, and chemical processing. Mr. Rushing has been an invited speaker on applicability of statistics for national and international conferences. As a Quality Engineer at Amgen, he championed statistical principles in every business unit. He designed and delivered a DOE course that immediately became the company standard required at multiple sites. Additionally, he developed and implemented numerous innovative statistical methods advancing corporate risk management, process capability, and validation acceptance criteria. He won the top teaching award out of 54 instructors in the Air Force Academy math department where he taught several semesters and sections of operations research and statistics. Additionally, he designs and delivers short courses in statistics, data mining, and simulation modeling for SAS.
For more information about this conference visit https://www.researchandmarkets.com/r/718cz9
