Map level accuracy
Map level accuracy describes the accuracy of the map as a total.
Error matrix terms: Overall, Kappa & Tau
- Overall Accuracy = sum of diagonal entries/ total no. of samples Note that this does not take into account errors due to chance agreement.
- Adjusted Accuracy = calculation of Kappa coefficient

Test hypotheses that image classification accuracy is significantly different to a randomly drawn map.
- Tau accuracy = Improved Adjusted Accuracy = calculation of Tau coefficient (Ma & Redmond 1995)

Reference:
Ma, Z.K. and R.L. Redmond (1995). Tau-Coefficients for Accuracy Assessment of Classification of Remote-Sensing Data. Photogrammetric Engineering and Remote Sensing, 61(4): p435-439.