1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
|
@article{Landis1977,
doi = {10.2307/2529310},
url = {https://doi.org/10.2307/2529310},
year = {1977},
month = {mar},
publisher = {{JSTOR}},
volume = {33},
number = {1},
pages = {159},
author = {J. Richard Landis and Gary G. Koch},
title = {The Measurement of Observer Agreement for Categorical Data},
journal = {Biometrics}
}
@article{Powers2011,
doi = {10.9735/2229-3981},
url = {https://doi.org/10.9735/2229-3981},
title={Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation},
author={Powers, David Martin},
year={2011},
publisher={Bioinfo Publications}
}
@book{Sammut2010,
doi = {10.1007/978-0-387-30164-8},
url = {https://doi.org/10.1007/978-0-387-30164-8},
year = {2010},
publisher = {Springer {US}},
editor = {Claude Sammut and Geoffrey I. Webb},
title = {Encyclopedia of Machine Learning}
}
@article{Fleiss1971,
doi = {10.1037/h0031619},
url = {https://doi.org/10.1037/h0031619},
year = {1971},
publisher = {American Psychological Association ({APA})},
volume = {76},
number = {5},
pages = {378--382},
author = {Joseph L. Fleiss},
title = {Measuring nominal scale agreement among many raters.},
journal = {Psychological Bulletin}
}
@book{Altman1990,
title={Practical statistics for medical research},
author={Altman, Douglas G},
year={1990},
publisher={CRC press}
}
@article{Gwet2008,
doi = {10.1348/000711006x126600},
url = {https://doi.org/10.1348/000711006x126600},
year = {2008},
month = {may},
publisher = {Wiley-Blackwell},
volume = {61},
number = {1},
pages = {29--48},
author = {Kilem Li Gwet},
title = {Computing inter-rater reliability and its variance in the presence of high agreement},
journal = {British Journal of Mathematical and Statistical Psychology}
}
@article{Scott1955,
doi = {10.1086/266577},
url = {https://doi.org/10.1086/266577},
year = {1955},
publisher = {Oxford University Press ({OUP})},
volume = {19},
number = {3},
pages = {321},
author = {William A. Scott},
title = {Reliability of Content Analysis: The Case of Nominal Scale Coding},
journal = {Public Opinion Quarterly}
}
@article{Bennett1954,
doi = {10.1086/266520},
url = {https://doi.org/10.1086/266520},
year = {1954},
publisher = {Oxford University Press ({OUP})},
volume = {18},
number = {3},
pages = {303},
author = {E. M. Bennett and R. Alpert and A. C. Goldstein},
title = {Communications Through Limited Response Questioning},
journal = {Public Opinion Quarterly}
}
@article{Cicchetti1994,
doi = {10.1037/1040-3590.6.4.284},
url = {https://doi.org/10.1037/1040-3590.6.4.284},
year = {1994},
publisher = {American Psychological Association ({APA})},
volume = {6},
number = {4},
pages = {284--290},
author = {Domenic V. Cicchetti},
title = {Guidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychology.},
journal = {Psychological Assessment}
}
@article{Davies1980,
doi = {10.2307/2346911},
url = {https://doi.org/10.2307/2346911},
year = {1980},
publisher = {{JSTOR}},
volume = {29},
number = {3},
pages = {323},
author = {Robert B. Davies},
title = {Algorithm {AS} 155: The Distribution of a Linear Combination of chi-squared Random Variables},
journal = {Applied Statistics}
}
@article{Kullback1951,
doi = {10.1214/aoms/1177729694},
url = {https://doi.org/10.1214/aoms/1177729694},
year = {1951},
month = {mar},
publisher = {Institute of Mathematical Statistics},
volume = {22},
number = {1},
pages = {79--86},
author = {S. Kullback and R. A. Leibler},
title = {On Information and Sufficiency},
journal = {The Annals of Mathematical Statistics}
}
@article{Goodman1972,
doi = {10.1080/01621459.1972.10482401},
url = {https://doi.org/10.1080/01621459.1972.10482401},
year = {1972},
month = {jun},
publisher = {Informa {UK} Limited},
volume = {67},
number = {338},
pages = {415--421},
author = {Leo A. Goodman and William H. Kruskal},
title = {Measures of Association for Cross Classifications, {IV}: Simplification of Asymptotic Variances},
journal = {Journal of the American Statistical Association}
}
@article{Goodman1963,
doi = {10.1080/01621459.1963.10500850},
url = {https://doi.org/10.1080/01621459.1963.10500850},
year = {1963},
month = {jun},
publisher = {Informa {UK} Limited},
volume = {58},
number = {302},
pages = {310--364},
author = {Leo A. Goodman and William H. Kruskal},
title = {Measures of Association for Cross Classifications {III}: Approximate Sampling Theory},
journal = {Journal of the American Statistical Association}
}
@article{Byrt1993,
doi = {10.1016/0895-4356(93)90018-v},
url = {https://doi.org/10.1016/0895-4356(93)90018-v},
year = {1993},
month = {may},
publisher = {Elsevier {BV}},
volume = {46},
number = {5},
pages = {423--429},
author = {Ted Byrt and Janet Bishop and John B. Carlin},
title = {Bias, prevalence and kappa},
journal = {Journal of Clinical Epidemiology}
}
@article{Shepperd2014,
doi = {10.1109/tse.2014.2322358},
url = {https://doi.org/10.1109/tse.2014.2322358},
year = {2014},
month = {jun},
publisher = {Institute of Electrical and Electronics Engineers ({IEEE})},
volume = {40},
number = {6},
pages = {603--616},
author = {Martin Shepperd and David Bowes and Tracy Hall},
title = {Researcher Bias: The Use of Machine Learning in Software Defect Prediction},
journal = {{IEEE} Transactions on Software Engineering}
}
@article{Deng2016,
doi = {10.1016/j.ins.2016.01.033},
url = {https://doi.org/10.1016/j.ins.2016.01.033},
year = {2016},
month = {may},
publisher = {Elsevier {BV}},
volume = {340-341},
pages = {250--261},
author = {Xinyang Deng and Qi Liu and Yong Deng and Sankaran Mahadevan},
title = {An improved method to construct basic probability assignment based on the confusion matrix for classification problem},
journal = {Information Sciences}
}
@misc{Haghighi2018,
doi = {10.5281/zenodo.1157173},
author = {Sepand Haghighi and Masoomeh Jasemi and Shaahin Hessabi},
keywords = {Machine Learning, statistics, confusion-matrix, statistical-analysis, matrices, matrix},
title = {Pycm : Multi Class Confusion Matrix Library In Python},
pages = {--},
publisher = {Zenodo},
year = {2018}
}
|
