|
Abstract:
|
In statistics, usually data are formatted as single values. However, what if the data are rather represented by lists, intervals, histograms or even distributions? Symbolic data analysis was introduced to deal with these kinds of data. Among symbolic data, interval-valued data are the most commonly seen in application. Recently, different approaches have been introduced to analyze interval-valued data, including linear regression, principal component analysis and clustering, etc. My research focuses on interval-valued data regression. The study begins with the concept of symbolic data, definition of symbolic interval-valued data, its descriptive statistics and current linear regression approaches. It then seeks to introduce a symbolic covariance method. By utilizing a symbolic covariance function, outlier identification, model diagnosis and confidence interval methods are also discussed.
|
