An arrangement of data containing the joint distribution of two or more categorical variables, usually in a database, a series of tables, or a special visualization
A statistical table that shows the observed frequencies of data elements classified according to two variables, with the rows indicating one variable and the columns indicating the other variable
a cross-classification of variables that are discrete (or categorical) The entries in a cell of the table correspond to the number of observations that share the characteristics defined by the given row and column
A table that compares mapped data with ground data to determine accuracy The "known" classes derived from accuracy assessment plots are compared to the classes derived from photo interpretation The results are then tabulated in the form of a contingency table to determine the degree of misclassification that has occurred between classes Also referred to as error matrix, confusion matrix, or misclassification matrix For an example of a contingency table see http: //biology usgs gov/npsveg/scbl/matrixf html
The "A" table entry is the number of event forecasts that correspond to event observations, or the number of hits; entry "B" is the number of event forecasts that do not correspond to observed events, or the number of false alarms; entry "C" is the number of no-event forecasts corresponding to observed events, or the number of misses; and entry "D" is the number of no-event forecasts corresponding to no events observed, or the number of correct rejections This 2x2 table will be referenced in the definitions of a number of performance measures formulated for the 2x2 verification problem These measures include percent correct (PC), probability of detection (POD), false alarm ratio (FAR), success ratio (SR), threat score (TS) or critical success index (CSI), Gilbert skill score (GS), Heidke skill score (HSS), and a categorical measure of bias