A Review of Three Discrete Multivariate Analysis Techniques Used in Assessing the Accuracy of Remotely Sensed Data from Error Matrices

Three discrete multivariate analysis techniques were used to assess the accuracy of land use/land cover classifications generated from remotely sensed data. Error matrices or contingency tables were analyzed using these techniques and the results reported. The first technique is a normalization procedure using an "iterative proportional fitting" algorithm that allows for direct comparison of Corresponding cell values in different matrices irregardless of sample size. The second technique provides a method of testing for significant differences between error matrices that vary by only a single variable or factor. The third technique allows for multivariable comparisons to be made between matrices. Each technique is implemented through the use of a computer program.