Store | Contact Us | Careers
 
  • Home
  • Industries
  • Products
  • Training
  • Support
  • Services
  • Events
  • News
  • About
    • About Esri
    • Careers
    • Esri Video
    • Partners

Support

Search Support
You are here: > ArcScripts > Search Results > Script Details Login | Feedback | Help

Cohen's Kappa and Classification Table Metrics 2.1a



contact author | download help | report inappropriate content
Author Jeff Jenness
File Name kappa_stats.zip
Language Avenue
Last Modified Dec 10 2007
Status of work Public Domain
Software ArcView GIS
File Size 132.9 kb
Downloads 1458

ArcScripts is intended for the free exchange of scripts and tools related to ESRI software products. Please alert the moderator if this script is a demo, trial-version, or an advertisement for a retail product.

Summary
DESCRIPTION: The Kappa statistic is used to measure the agreement between predicted and observed categorizations of a dataset while correcting for agreement that occurs by chance. This statistic is especially useful in landscape ecology and wildlife habitat relationship (WHR) modeling for measuring the predictive accuracy of classification grids.

The Kappa Analysis extension will provide end users with a packaged approach for accuracy assessment, using the Kappa statistic as well as several additional metrics, which can be used for gauging model performance. Additional metrics include overall accuracy, overall misclassification rate, model specificity and sensitivity, omission and commission errors, and positive and negative predictive power. When multiple competing models are available, these metrics can be used to quantitatively compare and identify the “better” model within a multi-criteria model selection process.

In addition to generating Kappa statistics, this extension also does the following:

** Compare Kappa Analyses: This tool allows you to compare the kappa statistics between different analyses, perhaps comparing different observers, predictive algorithms or dates of remote sensing imagery.

** Calculate Sample Size: This tool provides a means to estimate the sample size required to achieve a confidence level and precision for statistical analysis.

** Calculate Summary Statistics: From any numeric field in a table, this function will calculate the Mean, Standard Error of the Mean, Confidence Intervals, Minimum, 1st Quartile, Median, 3rd Quartile, Maximum, Variance, Standard Deviation, Average Absolute Deviation, Skewness (normal and Fisher’s G1), Kurtosis (normal and Fisher’s G2), Number of Records, Number of Null Values, and Total Sum.

** Probability Calculators: This function will allow you to calculate the probability, cumulative probability and inverse probability (i.e. given a cumulative probability, calculate the corresponding critical value) of a wide range of statistical distributions, including the Beta, Binomial, Cauchy, Chi-Square, Exponential, F, Logistic, LogNormal, Normal, Poisson, Student’s T and Weibull distributions. This function is available as a general calculator that remains open until you are finished with it, or as a Table tool that performs the calculations on all selected records in a table.

REQUIRES: Spatial Analyst

An on-line version of the documentation may be viewed at:

http://www.jennessent.com/arcview/kappa_stats.htm

Please visit Jenness Enterprises ArcView Extensions site for more ArcView Extensions and other software by the author.

http://www.jennessent.com/arcview/arcview_extensions.htm

Enjoy! Please contact the authors (jeffj@jennessent.com or james.wynne@nau.edu) if you have problems with this extension.

Jeff Jenness and J. Judson Wynne
Contact Us | Privacy | Legal | Site Map