a method of determining whether a graphical representation of a data set demonstrates symmetry about its x-axis, y-axis, or origin, so that knowing the arrangement of values for one portion of the graph (e.g., values above the mean) enables one to determine the values for the opposite, mirror-image portion of the graph (i.e., values below the mean). If the data do possess such symmetry, they can be analyzed using statistical techniques that assume a normal distribution.