|
Activity Number:
|
76
- To Open Source, or Not
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, July 28, 2019 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section for Statistical Programmers and Analysts
|
|
Abstract #304449
|
Presentation
|
|
Title:
|
Histogram Principal Component Analysis in R Shiny
|
|
Author(s):
|
Sun Makosso-kallyth* and Brahim Brahim
|
|
Companies:
|
SM Analytics and InfoVisuCA
|
|
Keywords:
|
R-shiny;
principal component analysis;
Histogram-valued variables;
symbolic data;
segmentation
|
|
Abstract:
|
In this era of massive and big data, new Technics and tools for transforming complex data into information are needed. For example, data where for each observation and variable, a distribution is given are more and more common and called distributional data. Unsupervised learning methods like Histogram Principal Component Analysis has proven to be extremely efficient to explain those data. The goal of this paper is to introduce to the audience a friendly shiny-R app that implements two-histogram principal component analysis. We first introduce those two methods based respectively on first order moment and the quantiles of distributional data and then we show to the R users how they can use a friendly shiny app to explore their data.
|
Authors who are presenting talks have a * after their name.
