Overview

The exploratory graphics are useful for identifying odd-looking values which do not fit in with the rest of the data. In the graphical presentation of data such values appear to be quite separate from the rest of the data, and are called outliers. In many cases outliers are discovered to be misrecorded data values, or represent some special condition that was not in effect when the data were collected.

• Histogram is used to present a sample distribution for numerical data.
• Stem and leaf plot split each value of the numerical data into a ``stem'' and a ``leaf,'' and displays them separately. The advantage of this plot is that we do not lose information on individual observation.
• Boxplot gives a graphical presentation of summary statistics.

Other graphical techniques will be introduced later for different purposes and functionality. Bar graph is used to illustrate data when the variable of interest is categorical. QQ-plot is used to determine whether sample data is approximately normal or not. Scatter plots are needed for studying the relationship between two variables.

---

© TTU Mathematics