Empirical Bayes Method for Multiple Testing with Heteroscedastic Errors
Research Paper#Statistics, Machine Learning, Multiple Testing, Empirical Bayes🔬 Research|Analyzed: Jan 3, 2026 08:52•
Published: Dec 31, 2025 04:02
•1 min read
•ArXivAnalysis
This paper introduces a new empirical Bayes method, gg-Mix, for multiple testing problems with heteroscedastic variances. The key contribution is relaxing restrictive assumptions common in existing methods, leading to improved FDR control and power. The method's performance is validated through simulations and real-world data applications, demonstrating its practical advantages.
Key Takeaways
- •Proposes a new empirical Bayes method (gg-Mix) for multiple testing.
- •Addresses the problem of heteroscedastic variances in normal mean inference.
- •Overcomes limitations of existing methods by relaxing restrictive assumptions.
- •Demonstrates superior performance in FDR control and power.
- •Validated through simulations and real-world data applications.
Reference / Citation
View Original"gg-Mix assumes only independence between the normal means and variances, without imposing any structural restrictions on their distributions."