The influences of data precision on the calculation of temperature percentile indices.

Percentile-based temperature indices are part of the suite of indices developed by the WMO CCl/CLIVAR/JCOMM Expert Team on Climate Change Detection and Indices. They have been used to analyse changes in temperature extremes for various parts of the world. We identify a bias in percentile-based indices which consist of annual counts of threshold exceedance. This bias occurs when there is insufficient precision in temperature data, and affects the estimation of the means and trends of percentile-based indices. Such imprecision occurs when temperature observations are truncated or rounded prior to being recorded and archived. The impacts on the indices depend upon the type of relation (i.e. temperature greater than or greater than or equal to) used to determine the exceedance rate. This problem can be solved when the loss of precision is not overly severe by adding a small random number to artificially restore data precision. While these adjustments do not improve the accuracy of individual observations, the exceedance rates that are computed from data adjusted in this way have properties, such as long-term mean and trend, which are similar to those directly estimated from data that are originally of the same precision as the adjusted data. Copyright © 2008 Royal Meteorological Society