Title: Testing the equality of two object parameters in two populations of symbolic data
Authors: Anuradha Roy - The University of Texas at San Antonio (United States) [presenting]
Daniel Klein - P.J. Safarik University (Slovakia)
Abstract: Advances in computing power in the past few decades greatly encouraged the collection of hundreds of thousands of data (big data) in our everyday lives. Big data in an object format such as histograms or intervals provide a more complete picture and the dynamics of the data. Big data can be explored by symbolic data analysis in which the object of the analysis is not a single-valued variable, but an object variable including histogram-valued and interval-valued variables. We will consider a method of testing the equality of two mean intervals for interval-valued data, and consider a Mushroom data set to illustrate our proposed method. The key point we want to emphasize is that we do not treat the Mushroom data as the classical single-valued data, nor as a very large collection of individual observations (also known as `Big Data'), but rather some type of structured aggregated data such as interval-valued data.