Mathematics
8 years ago

New test boosts power to detect group effects in scientific studies.

Computational Statistics & Data Analysis
Testing for one-sided group effects in repeated measures study
Dong Wan Shin, Chul Gyu Park, Taesung Park

Paper Summary

Related papers

Theme background image
Mathematics
5 years ago

New method for precise estimation and testing in data analysis

Multicollinearity
Regularization Methods
Missing Data
2 views
Theme background image
Mathematics
5 years ago

Revolutionizing Estimation: Maximum Likelihood Method Unlocks Most Efficient Parameter Estimates

Regularization Methods
Genomic Selection
2 views
Economics, Econometrics and Finance
6 years ago

New Method Improves Accuracy of Small Area Estimation for Human Development

Public Economics
2 views

The article tests for one-sided group effects in repeated measures studies by developing new statistical tests. These tests use a method called likelihood ratio principle and project estimators onto the first quadrant. The results show that the new tests have better power than traditional tests for detecting group effects.