Description:
<jats:title>Abstract</jats:title><jats:p>Cluster‐scaled analysis means exploiting the cluster‐based scaling to conventional data analysis to obtain more accurate results or results that we cannot obtain by using ordinary analysis. Our target data is complex and large amounts of data. For this type of data, it is well known that ordinary statistical methods do not always work well, or theoretically, we know that we cannot obtain a correct result. As a tool of this implementation, we utilize fuzzy clustering, which is well known as a robust clustering to a complex and large amount of data. That is, we use the fuzzy clustering result as a scale of data and apply the rescaled data by the cluster‐scale to another target analysis. Our target analysis in this article is principal component analysis, which is a well‐known dimensional reduction method. A numerical example shows a better performance of the cluster‐scaled principal component analysis.</jats:p><jats:p>This article is categorized under:<jats:list list-type="simple">
<jats:list-item><jats:p>Statistical Learning and Exploratory Methods of the Data Sciences > Knowledge Discovery</jats:p></jats:list-item>
<jats:list-item><jats:p>Statistical Learning and Exploratory Methods of the Data Sciences > Modeling Methods</jats:p></jats:list-item>
<jats:list-item><jats:p>Statistical Learning and Exploratory Methods of the Data Sciences > Clustering and Classification</jats:p></jats:list-item>
</jats:list></jats:p>