Latest News

Filter by category

Showing 10 of 29 posts

Bayesian Optimization DoE Python Examples

Why You Should Always Code Your Variables

Say you're running an experiment with concentration ranging from 0.1% to 1.0% and stirring rate from 1000 to 2000 RPM. If you fit a model using these raw values, the stirring rate coefficient might be

The Path of Steepest Ascent

When you're trying to optimize a process, you typically start with a design that gives you a linear model, like a fractional or full factorial design. But most of the time, you're not in the region of

Response Surface Methodology (RSM)

Imagine having a magic button that tells you the perfect combination of temperature, pressure, concentration, and time to maximize your yield. That button doesn't exist, but **Response Surface Methodo

Why Blocking Matters

We've talked about blocking as one of the three fundamental principles of DoE before. In theory, it makes sense: group your experiments by known sources of variability to keep them fro

Understanding Systematic and Random Errors

In Design of Experiments (DoE), we structure our experiments to extract maximum information from minimal trials. However, without proper error management, even the most sophisticated e

How to create a Box-Behnken Design in Python

This guide walks you through creating Box-Behnken designs using Python's pyDOE3 package. I won't dive deep into the theory—if you need background on response surface methodology or why Box-Behnken d

Testing Bayesian Optimization for Lab Experiments

Bayesian Optimization promises to make experimental design smarter and more efficient by iteratively selecting the most promising experiments based on previous results. But how do we know if it's actu

Understanding Bayesian Optimization

Science is about solving problems through experiments. In chemistry, this might mean maximizing the yield of a reaction or improving the hardness of a coating. Traditional methods like full factorial

Central Composite Design vs. Box-Behnken Design

Response surface designs help you capture curvature in your experiments—something that traditional factorial designs can't do on their own. We've already explored how [central composite designs](/blog

A full factorial design in Python from beginning to end

Commercial DoE and statistical software are incredibly powerful, but they also come with a hefty price tag. In addition, such software can be pretty daunting because of their many features of which yo