Latent Variables Conference 2016

University Of South Carolina At Columbia, Columbia SC

Investigators

Abstract

This award supports participation of junior researchers in the research conference "Latent Variables 2016" held at the University of South Carolina, October 12-14, 2016. The statistical concept of a latent variable (a quantity whose values are inferred rather than directly measured) is important for statistical analysis in a wide variety of fields, from medicine to social science to machine processing of natural language. The purpose of the Latent Variables conference is to encourage the exchange of research ideas in latent variables, and to motivate and direct future research in this and related areas. The conference provides an excellent opportunity for young researchers to present their work, to learn about recent developments in the field, and to initiate new research collaborations. The conference features four plenary talks by leaders in the field, as well as six pairs of concurrent sessions, each with three speakers, that will include address research progress in several areas related to latent variables theory and analysis, including multiple testing, frailty models, objective Bayes analysis, factor models, diagnostic screening, model misspecification, group testing and biomarker pooling, item response theory, model-based clustering, generalized linear latent variable models, and measurement error models. Poster sessions will provide additional opportunities for exchange of ideas, and one of the poster sessions is designated specifically for graduate students to present their research. Additional information can be found at the conference web site: http://www.stat.sc.edu/latent-variables-2016