In Novonesis’ pursuit to understand the performance of industrial yeast products in specific customer conditions, our application research and development groups excel in generating insightful data sets for screening top yeast candidates at customer scale. Scientists regularly employ statistics to address complex questions related to both broad and specific customer scenarios.
The introduction of Bayesian methods into Python libraries has significantly enhanced our ability to compute models and facilitate data-based decisions based on probabilities, even when traditional statistically significant results are not available. Additionally, the new capabilities in JMP 18 enable seamless integration with Python, empowering our scientists to generate large data sets and address customer-specific inquiries without leaving JMP. By leveraging application research data, customer trial data, and prior information, we are embarking on a journey to characterize our decisions based on informed data and Bayesian statistics, rather than relying on statistically insignificant trends. This approach aims to provide a more comprehensive understanding and quantification of performance, ultimately leading to more informed decision making.
