1984
DOI: 10.2307/2425535
|View full text |Cite
|
Sign up to set email alerts
|

Chance-corrected Classification for Use in Discriminant Analysis: Ecological Applications

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
182
0

Year Published

1995
1995
2022
2022

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 295 publications
(183 citation statements)
references
References 12 publications
1
182
0
Order By: Relevance
“…Misclassification rates of DFA were calculated using holdout cross validation procedures proposed by Lachenbruch (1967). The kappa (κ) statistics was used to determine the improvement over chance of the percentcorrect classification rates (Titus et al, 1984). All statistical analyses were performed with SPSS Version 15, MINITAB Version 14, and PAST Version 1.34 software.…”
Section: Resultsmentioning
confidence: 99%
“…Misclassification rates of DFA were calculated using holdout cross validation procedures proposed by Lachenbruch (1967). The kappa (κ) statistics was used to determine the improvement over chance of the percentcorrect classification rates (Titus et al, 1984). All statistical analyses were performed with SPSS Version 15, MINITAB Version 14, and PAST Version 1.34 software.…”
Section: Resultsmentioning
confidence: 99%
“…The bias of the classification was determined with the Cohen's kappa (κ) coefficient, which estimates the improvement over chance of the percent corrected classification rates (Tuset et al 2003b). Values of κ range from 0 to 1, with zero indicating that the discriminant analysis yielded no improvement over chance, while a κ of 1 occurs only with perfect agreement (Titus et al 1984). The κ values were scaled up to a percentage, and the prior probability of classification was equal for all groups.…”
Section: Methodsmentioning
confidence: 99%
“…Cohen's Kappa statistic (Cohen 1960;Titus et al 1984;Congalton 1991) also expresses the proportion of reference pixels correctly classified by the procedure, but in this case after adjusting for (removing) the effect of correct classification by chance.…”
Section: Calculation Of Accuracy Assessment Statisticsmentioning
confidence: 99%
“…P, is calculated from the error matrix by using the row and column proportions &e., P, is the sum of row times column proportions summed over all categories). Further information about this calculation can be found in Titus et al (1984);Campbell (1987);and Congalton (1991). Kappa has its maximum value of 1 when all observations are correctly classified.…”
Section: Kappa Statisticmentioning
confidence: 99%