Mathematics
8 years ago

New statistical tests offer more powerful tools for data analysis.

IEEE Transactions on Reliability
Goodness-of-Fit Tests Based on Kullback-Leibler Information
Birdal Şenoǧlu, Barış Sürücü

Paper Summary

Related papers

Theme background image
Mathematics
3 years ago

New method accurately tests distribution fit for real-world data applications.

Skew Distributions
Missing Data
Model-Based Clustering
3 views
Theme background image
Mathematics
3 years ago

New method outperforms traditional tests in judging data distribution fit.

Skew Distributions
Clinical Trials
Missing Data
2 views
Theme background image
Agricultural and Biological Sciences
8 years ago

New EDF test improves extreme event prediction accuracy for climate change.

Meta-analysis
Skew Distributions
Drought Monitoring

The article evaluates different tests for checking if data fits certain distributions. Tests based on sample entropy were compared with traditional tests like the W, Z, and R tests. The traditional tests were found to be more powerful overall, especially the Z test. These traditional tests can also be used with censored data and multiple samples.