ABSTRACT
The basic scatterplot and smooth scatterplot are the current data mining methods for assessing the relationship between predictor and dependent variables, an essential task in the model-building process. This chapter focuses on a new dataset to keep an edge on refocusing another illustration of the scatterplot and smoothed scatterplot. It presents a primer on chi-squared automatic interaction detection (CHAID), after which bring the proposed subject to the attention of data miners, who are buried deep in data, to help exhume themselves along with the patterns and relationships within the data. The chapter aims to view an exemplary scatterplot filled with too many data and reviews the corresponding smooth scatterplot, a rough-free, smooth-full scatterplot, which reveals the sunny-side up of the inherent character of a paired-variable assessment. The smooth scatterplot uses averages of raw data, and the smoother scatterplot uses averages of fitted values of CHAID end nodes.
