Goldman School of Public Policy - University of California, Berkeley

Working Paper Series

Visually-Weighted Regression

Authors

  • Solomon Hsiang, Goldman School of Public Policy, University of California, Berkeley

History

  • Goldman School of Public Policy Working Paper (May 2013)

Abstract

Uncertainty in regression can be eciently and e ectively communicated using the visual properties of statistical objects in a regression display. Altering the visual weight" of lines and shapes to depict the quality of information represented clearly communicates statistical con dence even when readers are unfamiliar with the formal and abstract de nitions of statistical uncertainty. Here we present examples where the color-saturation and contrast of regression lines and con dence intervals are parametrized by local measures of an estimate's variance. The results are simple, visually intuitive and graphically compact displays of statistical uncertainty. This approach is generalizable to almost all forms of regression

Download File

Download a PDF (2MB)