Dr Raluca Ilinca Schmitt
Bayer AG
Referent:innen
Dr Christian Palmes
Bayer AG
Zielsetzung
Our DoE course offers a clear, hands-on introduction to planning and analyzing experiments using Minitab. The course features four case studies presented in a completely click-through manner. All examples are set in a pharmaceutical context.
DoE theory is covered at a practical level to ensure participants understand the concepts and can accurately interpret software outputs, ultimately leading to correct conclusions.
• Day 1: Focuses on the planning stage of DoE
• Day 2: Focuses on the analysis of DoE results
The course covers a broad range of classical and modern DoE designs, including full and fractional factorial, Plackett-Burman, central composite (RSM), D-optimal and mixture designs.
Hintergrund
Design of Experiments (DoE) is a powerful statistical method used in Quality by Design (QbD) to gain insights into the characteristics of processes and products. It provides a scientific basis for selecting process parameter ranges in regulatory submissions and helps identify key parameters affecting product quality, while minimizing the number of experiments and associated costs.
In the planning step, a minimal number of experiments is selected to representatively cover the experimental space. In the analysis step, a multivariate empirical model is fitted to the measurements to describe the relationship between process parameters and quality attributes of interest. This model is then used to predict product quality with the desired level of certainty and to establish operational ranges that ensure compliance with specification limits.
The importance of the DoE methodology in the pharmaceutical development is further emphasized by various regulatory guidelines, including the Quality ICH Guidelines (Q8, Q11, and the newer Q14) and, more recently, the European Pharmacopoeia (Supplement 11.7).
In the planning step, a minimal number of experiments is selected to representatively cover the experimental space. In the analysis step, a multivariate empirical model is fitted to the measurements to describe the relationship between process parameters and quality attributes of interest. This model is then used to predict product quality with the desired level of certainty and to establish operational ranges that ensure compliance with specification limits.
The importance of the DoE methodology in the pharmaceutical development is further emphasized by various regulatory guidelines, including the Quality ICH Guidelines (Q8, Q11, and the newer Q14) and, more recently, the European Pharmacopoeia (Supplement 11.7).
Zielgruppe
This course is ideal for employees in development, quality control labs, process engineering, and quality assurance departments who are currently using DoE or plan to use it in the future. It is also suitable for GMP auditors, inspectors, and validation personnel involved in DoE review or other submission processes. Requirements: Basic math skills/understanding and strong intrinsic Motivation.
Date & Venue
Date
Tuesday, 23 September 2025, 09.00 – 17.30 h
(Registration and coffee 08.30 – 09.00 h)
Wednesday, 24 September 2025, 08.30 – 17.00 h
Venue
HYPERION Hotel Berlin
Prager Straße 12
10779 Berlin
Germany
Programm
Gesamtes Programm als PDF herunterladen
Day 1
Welcome and Setting Up the Scene
Welcome and Setting Up the Scene
- A short introduction round
- Objectives of the training
Basics of DoE Planning: Part A
- Why DoE?
- One-Factor-at-a Time (OFAT) vs. DoE
- The DoE workflow
- Experimental goals
- Main, interaction and quadratic effects
First Optimization Example
- Get familiar with DoE in Minitab
- Plan and evaluate a factorial experiment in Minitab
- Calculate main and interaction effects in Excel
Basics of DoE Planning: Part B
- Randomization, blocking and replication
- Power and sample size
- Orthogonality
- Fractional factorial designs: resolution III, IV and V
- Plackett-Burman and central composite designs
- Special designs: D-optimal and mixture designs
A Pharmaceutical Optimization Problem: Planning
- Plan a full-factorial design in Minitab
- Assess signal to noise, correlation and effect-sizes
- Employ Minitab’s DoE planning tool
Exercise: Hands-On DoE Planning
- Plan a DoE on your own
- Case Study 1: Optimization of a granulation process
- Case Study 2: HPLC robustness assessment
Day 2
Statistical Modeling and Prediction
Statistical Modeling and Prediction
- Effect selection
- Analysis of variance (ANOVA)
- Model building
- F-test, t-test, p-value
- Confidence, prediction and tolerance intervals
- Data and model visualizations with Minitab
Interpreting Model Diagnostics
- Goodness of fit and prediction
- Curvature
- Predicted values and residuals
- Transformations (Box-Cox)
A Pharmaceutical Optimization Problem: Analysis
- Effect selection for model building
- Interpretation of model diagnostics
- Derivation and Assessment of Sweet Spot and Proven Acceptable Ranges (PARs)
Supplementary Material: Design Augmentation
- Questions with answers (elaborated sample solutions)
- Simultaneous optimization of 3 responses with 2 factors
- Design augmentation to incorporate quadratic effects
- Circumscribed central composite designs in Minitab
- Design Space and Sweet Spot derivation using overlay plots
| ECA-Member*: | € 1990,- |
| Non ECA Member*: | € 2190,- |
| EU/GMP Inspectorates*: | € 1095,- |
| APIC Member Discount*: | € 2090,- |
Alle Preise zzgl. MwSt. Wichtige Hinweise zur Umsatzsteuer.
* auch unkompliziert per Kreditkarte bezahlbar
Weitere Termine vor Ort
Weitere Termine vor Ort nicht verfügbar
Weitere Termine online
Weitere Termine online nicht verfügbar
Aufzeichnung nicht verfügbar
This course is part of the GMP Certification Programme "ECA Certified Validation Manager"
Haben Sie noch Fragen?
Wir stehen Ihnen für weitere Auskünfte gerne zur Verfügung.
E-Mail: info@concept-heidelberg.de
Für Lieferanten: Ausstellungs- und Sponsoringmöglichkeiten
Seminarprogramm als PDF
Sonderkonditionen DB BahnTeilnehmerstimmen - das sagen andere über unsere Seminare:
