Mapping Health Statistics: Representing Data Reliability

Data reliability is a major concern for both science and policy analysis. Methods of specifying the reliability of sample data, the variance around measures of central tendency, the confidence we should put in statistical summaries, etc. are well developed. When data are geo referenced, however, reliability estimates have not traditionally been mapped. For the same reasons that we map spatial data rather than limiting ourselves to tables or to numerical results of statistical analysis, we should portray data reliability in map form. This paper reports on the first stage of an effort to develop and assess reliability representation methods in the context of the U. S. National Center for Health Statistics Mortality Atlas.