Table of Contents#### Download Safari Books Online apps: Apple iOS | Android | BlackBerry

### 3.6 Summary

Entire Site

Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

Data can be described graphically and numerically.

Continuous and nominal data require different graphs and numerical summaries.

JMP uses appropriate tools depending on whether a column is either continuous or nominal.

Continuous data can be graphed by histograms, box plots, time plots, and CDF plots.

Continuous data histograms show the distribution of values by tabulating the frequency of occurrence per class (or bar) width.

Box plots summarize the median, the lower and upper quartile, as well as minimum and maximum values.

Box plots of few data values can distort the data distribution.

Box plots of data where a large portion of values is concentrated in a narrow band may give undue focus on values outside the concentrated data range.

Time plots graph data over time. They can be used to discover temporal patterns.

CDF plots show the cumulative frequency of occurrence.

Continuous data can be summarized by measures of location (mean, median, and quantiles) and measures of spread (standard deviation, variance, and range).

The mean is a simple average of the data values.

The median is the value with at least 50% as large as and at least 50% as small as it.

The upper and lower quartile split the data into the lower 25%, the middle 50%) and the upper 25% respectively.

JMP uses interpolated quantile values. The median, quartiles, or other quantiles, except the maximum or minimum, need not be data values.

Nominal data can be graphed in frequency histograms, mosaic plots, and pie charts.

Nominal data can be numerically summarized by frequency counts and relative frequencies per nominal category. In a nominal frequency histogram, the horizontal axis represents outcome categories.

Relative frequencies stress the proportional occurrence of each nominal category.

Relative frequency can be graphed in a mosaic plot or a pie chart.

A good graph has all axes labeled and does not contain unnecessary information.

A good graph has easily distinguishable marker symbols.

A good graph has properly spaced axes.