Tornado Plot Page

The Tornado Plot allows visualizing how much the design variables influence a particular response. Values range between -1 and 1, with values farther away from 0 indicating a stronger correlation. Correlation values greater than 0 indicate a positive correlation, e.g., "Rain is positively correlated to wet sidewalks." Correlation values less than 0 indicate an inverse correlation, e.g., "Sunny days are inversely correlated to wet sidewalks."

Settings

To configure the Tornado Plot page, select the Basic Settings option from the Chart menu:

The first option is for which analytical method to use in calculation correlation:

  • Pearson - Pearson is a standard parametric method for calculating correlation.
  • Spearman - Spearman's is a correlation method based on rank ordering of the samples.

For more information on these methods please refer here.

The second option determines how the variable names are shown in the graph:

  • Full Names - Shows the full name of the variable, e.g., Model.pad.padCost
  • Abbreviated Groups - Shows the first letter of each group before the final, e.g., M.p.padCost
  • Name Only - Shows only the last portion of the variable name, e.g., padCost

See Also: Data Explorer