Treffer: Developing JMP and VBA Add-Ins for Finite Mixture Modeling of Cotton Fiber Length Distribution.

Highlights: What are the main findings? This research developed custom software add-ins for data processing and statistical analysis of cotton fiber length distributions using the mixed Weibull distribution model. The add-ins were generated for JMP and MS Excel and are available to cotton researchers for use with data from the Advanced Fiber Information System (AFIS). What is the implication of the main finding? Using the tools developed in this research, breeders, geneticists, and processors can effectively parameterize cotton fiber length distribution and extract the intrinsic and process-related factors shaping the distribution patterns. Breeders can use the tools to better discriminate between varieties based on intrinsic length, processors can optimize ginning and spinning to minimize fiber damage and to classify cottons based on length distribution parameters. In this study, software add-ins were developed and presented to allow data processing and statistical analysis of the unique shape of cotton fiber length distribution. The approach uses VBA coding in Excel to process the data, as well as the JMP 14-17 application and add-in builder tools to fit finite mixture models to empirical fiber length distributions. The resulting model derives a parametric expression for the fiber length probability density function. The analysis add-in was applied and validated on a wide range of empirical length distributions and proved to parameterize the complex distribution patterns with an excellent goodness of fit. Both tools were compiled into installable add-ins that extended the capabilities of MS Excel for the processing of AFIS distribution reports and the statistical toolbox of JMP using the Application Builder JSL coding. Installable add-ins, along with a user manual, are available for download by cotton researchers. [ABSTRACT FROM AUTHOR]

Copyright of Fibers is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)