---
title: Extreme Value Inference for General Heterogeneous Data
url: https://www.ml-quant.com/papers/ssrn/4816397/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4816397
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4816397
featured: 2024-05-08
citations: 3
topic: Other
---


# Extreme Value Inference for General Heterogeneous Data

A new study applies extreme value statistics to independent data with varying distributions, introducing a new asymptotic theory and its applications to the lifespan of identical twins and global earthquake energies.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4816397
- Identifier: SSRN 4816397
- Released: 2024-04-29
- First featured: Quant Letter No. 48 (2024-05-08): https://www.ml-quant.com/issues/2024-05-08/
- Citations (Semantic Scholar): 3
- Published in: not yet
- Topic: Other

## Related

- [Elicitability and Identifiability of Tail Risk Measures](https://www.ml-quant.com/papers/arxiv/2404.14136/): The article proves the joint identifiability and elicitability of tail risk measures and the corresponding quantile, making it easier to fit, compare, and validate models for tail risk measures.
- [The Efficient Tail Hypothesis: An Extreme Value Perspective on Market Efficiency](https://www.ml-quant.com/papers/arxiv/2408.06661/): The Efficient Tail Hypothesis (ETH), a theory about the extreme behavior of the market, is rejected in a study of China's futures market, revealing potential profitable investment opportunities.
- [Depth Anything V2](https://www.ml-quant.com/papers/arxiv/2406.09414/): Depth Anything V2 is a new model for monocular depth estimation, using synthetic and large-scale pseudo-labeled real images for faster, more accurate results and setting a new evaluation benchmark.
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://www.ml-quant.com/papers/arxiv/2406.01574/): MMLU-Pro, an improved dataset, expands the Massive Multitask Language Understanding benchmark by adding tougher questions and more choices, serving as a better benchmark to monitor progress in the field.
- [Qwen2.5-Coder Technical Report](https://www.ml-quant.com/papers/arxiv/2409.12186/): The report unveils the Qwen2.5-Coder series, an improvement from its predecessor, showcasing remarkable code generation abilities and achieving top-tier performance in various code-related tasks.
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://www.ml-quant.com/papers/arxiv/2311.18259/): Understanding Human Activity: The paper presents Ego-Exo4D, a large-scale video dataset and benchmark challenge featuring human activities from various perspectives, aimed at improving first-person video understanding.