POS 138 Quantitative Reasoning in Political Science

Lab 9: The Boxplot  --

Read: JPDA, pp. 74(bottom)-76:

1. For the Box Charter add-in to work,
   • Download this add-in file to your desktop: BoxCharter.xla
     [note this is a different add-in than you used before]
   • Open the file, leave it open

2. Download this excel file
3. Prepare a boxplot that looks like the image.

Features:

• Select the data range, choose Add-ins | BoxCharter
• Highlight the data range (do not highlight the state names)
• indicate that labels are in the first row.

To add the lines data range:

• You may select a specific state or the two data series shown (at the bottom of the data.
• Click on the Chart
  Copy the row of state or ("execution state") data:

  Execution states

  8.6

  9.4

  9

  7.5

  7.2

  7.2

  8.4

• Illinois

  6.6

  7.4

  8

  35

  4.2

  6.2

  7.4

• paste-special the data series into the chart
• format the data series to produce a line. (select the series from the left hand "Layout option).

Alternatives:

with these data:

or these data:

About Boxplots:

Boxplots, also known as box-and-whisker plots, are a convenient method of displaying the distribution of an interval-level variables. 

Figure xx: Components of a boxplot

The simple boxplot, as shown in figure xx, displays the four quartiles of the data, with the "box" comprising the two middle quartiles, separated by the median.  The upper and lower quartiles are represented by the single lines extending from the box.

A single boxplot box (as in figure xx) rarely reveals much about the data; in most instances stem-and-leaf or histogram charts offer a more detailed graphic representation of the data distribution.  The real advantages of the boxplot graphic comes through, however, in charts that use several boxplot boxes to compare the distribution of a variable across groups or over time.

An especially useful elaboration of the boxplot graph involves plotting an individual case over the boxplot to compare a single cases to the overall  distribution. 

(click to expand thumbnail)

Figure 1: Time series boxplots, with individual cases  (data)

Thus figure 1 displays the percentage Democratic vote for the 50 states over the past seven presidential elections.  We can see that the Democratic vote in Nevada has moved steadily higher relative to the other states while Georgia has become an increasingly Republican state. 

One can easily imagine applying  the same plotting strategy in a variety of other settings, for example, comparing one school district's test scores to the distribution of test scores across other school districts.   Other examples.

Examples of boxplots:

data source:
spreadsheet

data source