The Box-Whisker Type dialog box is displayed after you select the desired variables for the box and whisker plot. Select one of the box-whisker types (described below) and click the OK button to display a box and whisker plot based on your selections.

Median/Quart./Range. This box plot describes the central tendency of the variable in terms of the median of the values (represented by the smallest box in the plot). The spread (variability) in the variable values is represented in this plot by the quartiles (the 25th and 75th percentiles, larger box in the plot) and the minimum and maximum values of the variable (the "whiskers" in the plot).

Mean/SE/SD. Here, the smallest box in the plot represents the mean (central tendency) of the variable, while the dispersion (variability) is represented by ± 1 times the standard error (large box) and ± 1 times the standard deviation about the mean ("whiskers").

Mean/SD/1.96*SD. This plot will show the mean (small box in the plot) of the variable surrounded by a larger box (± 1 times the standard deviation). If the distribution is normal, then the "whiskers" in this plot represent a "95% confidence interval" defined as the variable mean ± 1.96 times the variable standard deviation.

Mean/SE/1.96*SE. Once again, this plot will show the mean (small box in the plot) of the variable surrounded by a larger box. However, in this plot, the larger box represents ± 1 times the standard error. If the distribution is normal, then the "whiskers" in this plot represent a "95% confidence interval" defined as the variable mean ± 1.96 times the variable standard deviation.

Many other graphic options (such as graph customizations or variable selections) or types of graphs are available in the Graphs menu. In order to produce box plots representing the distribution of the values in cases (and not variables), use the Graphs of Block Data - Custom Graph from Block by Row - Box Plots option from the Select Graph dialog box (instead of transposing your data file).