For the graph to represent your data most effectively, consider the following guidelines.
- The data must include at least three columns of numeric or date/time data
- The columns must have the same number of rows. The data may also include up to three columns of categorical data for grouping and up to two columns of categorical data for paneling.
- The sample size should be medium
- Although there are no formal guidelines for the amount of data needed for a bubble plot, medium-sized samples may work the best. Larger samples more clearly indicate patterns in the data; however, too many data points may cause the bubbles to overlap, making the graph hard to understand.
- The sample data should be selected randomly
- In statistics, random samples are used to make generalizations, or inferences, about a population. If your data were not collected randomly, your results may not represent the population.