Accuracy, precision, and uncertainty are important concepts in GIS. The data we we use in GIS represents information about and related to Earth. As you have learned in earlier chapters Earth is complicated, large, and dynamic. Accuracy is the proximity of a representation of something to the things actual value. In GIS spatial accuracy is distinct from attribute accuracy: both are important. Precision is related to the repeatability of a measurement’s accuracy as well as the extent to which a measure is capable of representing the actual value. There are slightly different definitions and assessment routines of Accuracy and Precision for different levels of data vary (nominal, ordinal, interval, and ratio). For instance, with nominal data, we can assess the extent to which a feature that exists is a specific category is assigned to that category using a certain instrument or classification routine. If we do this for all of the categories in a nominal classification system we can establish the overall utility of the system as well as the extent to which the system is capable of classify the categories in the scheme. This is done using a tool called a Confusion Matrix. A confusion matrix takes the categories in the scheme and compares the assignment of each observation to a category by the scheme to the actual category of the item being assigned. This provides an assessment of the scheme and can justify its application in new settings.