Special k: The Science of Finding the Optimal k in Clustering w/ Jason Bryer- nyhackr Mar Meetup

Visit https://www.nyhackr.org to learn more and follow https://x.com/nyhackr Talk Title- Special k: The Science (or Art) of Determining the Optimal k in Cluster Analysis Talk Description- Cluster analysis is a statistical procedure for grouping observations using an observation-centered approach as compared to variable-centered approaches (e.g. PCA, factor analysis). As an unsupervised method true cluster membership is usually not known. Hence, determining the optimal number of clusters, or k, poses unique challenges. A review of six common metrics for determining k with several clustering methods using two data sets will be explored. An introduction to two bootstrapping fit statistics will be provided along with validation techniques for evaluating the validity and stability of the cluster results across bootstrap samples. Bio- Dr. Jason Bryer is currently an Assistant Professor and Associate Director in the Data Science and Information Systems department at the City University of New York. He is currently the Principal Investigator of the FIPSE ($3 million #P116F150077) and IES funded ($3.8 million R305A210269) Diagnostic Assessment and Achievement of College Skills (DAACS), which is a suite of technological and social supports designed to optimize student learning. Dr. Bryer’s other research interests include quasi-experimental designs with an emphasis on propensity score analysis, data systems to support formative assessment, and the use of open source software for conducting reproducible research. He is the author of over a dozen R packages, including three related to conducting propensity score analyses.