1r.kappa(1)                    Grass User's Manual                   r.kappa(1)
2
3
4

NAME

6       r.kappa   -  Calculate  error  matrix  and kappa parameter for accuracy
7       assessment of classification result.
8

KEYWORDS

10       raster
11

SYNOPSIS

13       r.kappa
14       r.kappa help
15       r.kappa  [-wqh]   classification=name   reference=name    [output=name]
16       [title=string]   [--verbose]  [--quiet]
17
18   Flags:
19       -w
20           Wide report
21           132 columns (default: 80)
22
23       -q
24           Quiet
25
26       -h
27           No header in the report
28
29       --verbose
30           Verbose module output
31
32       --quiet
33           Quiet module output
34
35   Parameters:
36       classification=name
37           Name of raster map containing classification result
38
39       reference=name
40           Name of raster map containing reference classes
41
42       output=name
43           Name for output file containing error matrix and kappa
44
45       title=string
46           Title for error matrix and kappa
47           Default: ACCURACY ASSESSMENT
48

DESCRIPTION

50       r.kappa tabulates the error matrix of classification result by crossing
51       classified map layer with respect to reference map layer.  Both overall
52       kappa  (accompanied  by  its variance) and conditional kappa values are
53       calculated.  This analysis  program  respects  the  current  geographic
54       region and mask settings.
55
56       r.kappa  calculates the error matrix of the two map layers and prepares
57       the table from which the report is to be  created.   kappa  values  for
58       overall  and each classes are computed along with their variances. Also
59       percent of commission and ommission  error,  total  correct  classified
60       result  by  pixel  counts, total area in pixel counts and percentage of
61       overall correctly classified pixels are tabulated.
62
63       The report will be write to an output file which is in plain text  for‐
64       mat and named by user at prompt of running the program.
65
66       The  body  of  the report is arranged in panels.  The classified result
67       map layer categories is arranged along the vertical axis of the  table,
68       while  the  reference  map  layer categories along the horizontal axis.
69       Each panel has a maximum of 5 categories (9 if wide format) across  the
70       top.   In  addition, the last column of the last panel reflects a cross
71       total of each column for each row.  All of the categories  of  the  map
72       layer  arranged along the vertical axis, i.e., the reference map layer,
73       are included in each panel.  There is a total at  the  bottom  of  each
74       column representing the sum of all the rows in that column.
75

NOTES

77       It  is  recommended  to  reclassify categories of classified result map
78       layer into a more manageable number before running r.kappa on the clas‐
79       sified  raster  map  layer. Because r.kappa calculates and then reports
80       information for each and every category.
81
82       NA's in output file mean non-applicable in case MASK exists.
83

SEE ALSO

85       g.region, r.category, r.mask, r.reclass, r.report, r.stats
86

AUTHOR

88       Tao Wen, University of Illinois at Urbana-Champaign, Illinois
89
90       Last changed: $Date: 2007-10-10 10:01:00 +0200 (Wed, 10 Oct 2007) $
91
92       Full index
93
94       © 2003-2008 GRASS Development Team
95
96
97
98GRASS 6.3.0                                                         r.kappa(1)