High-Dimensional Data Analysis
Atanu Bhattacharjee · 2020
Currently, the proliferation of knowledge of cancer promotes cancer management by gene therapy. High-dimensional data measure genomic information of cancer patients. Motivated by these essential applications in cancer research, there has been a dramatic growth in the development of statistical methodology in the analysis of high-dimensional data, mainly related to regression model selection, estimation and prediction. The high-dimensional data is useful to explore the cancer progression, especially for disease management. However, the analyst faces difficulties to deal with high-dimensional data where the feature dimension p grows exponentially. This chapter is dedicated to shows the Bayesian approach in high-dimensional data. Variable selection in high-dimensional data is one of the challenges. Bayesian variable selection strategy is presented in this work. Different R packages for variable selection steps are illustrated. This chapter will help to consider Bayesian in high-dimensional variable selection.