Improving the design of the letter contrast sensitivity test

Abstract

Purpose: To develop a small-format letter contrast sensitivity test with improved accuracy, suitable for portable use and near testing, and having a simple and unambiguous scoring system that can be used with reference to existing norms.

Methods: A near test, printed on resin-coated paper and mounted on plastic was developed by using Sloan letters, with 0.04 log unit contrast decrements between each letter and a simple scoring procedure. Monte Carlo methods and a Weibull function model of visual performance were used to assess test accuracy.

Results: The new test has 28% lower score standard deviations than the Pelli-Robson Contrast Sensitivity Chart, over a wide range of low misreporting rates, while maintaining test scores that differ from the Pelli-Robson by 0.01 log unit, permitting use of norms collected with the Pelli-Robson test.

Conclusions: While maintaining comparability with Pelli-Robson norms, the new test has improved accuracy in comparison with the Pelli-Robson chart and several other advantages that result from its smaller size.