Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Extreme Treatment Effect: Extrapolating Dose-Response Function Into Extreme Treatment Domain (2403.11003v2)

Published 16 Mar 2024 in stat.ME

Abstract: The potential outcomes framework serves as a fundamental tool for quantifying causal effects. The average dose-response function (also called the effect curve), denoted as (\mu(t)), is typically of interest when dealing with a continuous treatment variable (exposure). The focus of this work is to determine the impact of an extreme level of treatment, potentially beyond the range of observed values--that is, estimating (\mu(t)) for very large (t). Our approach is grounded in the field of statistics known as extreme value theory. We outline key assumptions for the identifiability of the extreme treatment effect. Additionally, we present a novel and consistent estimation procedure that can potentially reduce the dimension of the confounders to at most 3. This is a significant result since typically, the estimation of (\mu(t)) is very challenging due to high-dimensional confounders. In practical applications, our framework proves valuable when assessing the effects of scenarios such as drug overdoses, extreme river discharges, or extremely high temperatures on a variable of interest.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (67)
  1. Estimation and inference for the counterfactual distribution and quantile functions in continuous treatment models. Journal of Econometrics, 2021. doi: 10.1016/j.jeconom.2020.12.0090304-4076.
  2. End-to-end balancing for causal continuous treatment-effect estimation. In Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 1313–1326. PMLR, 2022. URL https://proceedings.mlr.press/v162/bahadori22a.html.
  3. Causality in extremes of time series. Extremes, 27:67–121, 2024. doi: 10.1007/s10687-023-00479-5.
  4. L. Breiman. Random forests. Machine learning, 45:5–32, 2001. doi: 10.1023/A:1010933404324.
  5. F. Caeiro and M.I. Gomes. Threshold selection in extreme value analysis. Extreme value modeling and risk analysis: Methods and applications, pages 69–82, 2015. doi: 10.1007/s10687-021-00405-7.
  6. V. Chernozhukov. Extremal quantile regression. The Annals of Statistics, 33(2):806–839, 2005. doi: 10.1214/009053604000001165.
  7. Extremal quantile regression: An overview. Chapman and Hall, 2016.
  8. S. Coles. An Introduction to Statistical Modeling of Extreme Values. Springer Series in Statistics. Springer-Verlag, 2001. ISBN 1-85233-459-2.
  9. V. Courgeau and A. E. D. Veraart. Extreme event propagation using counterfactual theory and vine copulas. Arxiv preprint 2106.13564, 2021.
  10. Dealing with limited overlap in estimation of average treatment effects. Biometrika, 96:187–199, 2009. doi: 10.1093/biomet/asn055.
  11. R. A. Davis. The rate of convergence in distribution of the maxima. Statistica Neerlandica, 36(1):31–35, 1982. doi: 10.1111/j.1467-9574.1982.tb00772.x.
  12. R. A. Davis and T. Mikosch. The extremogram: A correlogram for extreme events. Bernoulli, 15(4):977 – 1009, 2009. doi: 10.3150/09-BEJ213.
  13. A.C. Davison and R. Huser. Statistics of extremes. Annual Review of Statistics and Its Application, pages 203–235, 2015. doi: 10.1146/annurev-statistics-010814-020133.
  14. Models for exceedances over high thresholds. Journal of the Royal Statistical Society: Series B (Methodological), 52(3):3, 1990. doi: jstor.org/stable/2345667.
  15. Estimation and inference of extremal quantile treatment effects for heavy-tailed distributions. JASA, pages 1–11, 2023. doi: 10.1080/01621459.2023.2252141.
  16. D. J. Eck. Bootstrapping for multivariate linear regression models. Statistics and Probability Letters, 134:141–149, 2018. doi: 10.1016/j.spl.2017.11.001.
  17. S. Engelke and A.S. Hitz. Graphical models for extremes. Journal of the Royal Statistical Society Series B, 82(4):871–932, 2020. URL https://EconPapers.repec.org/RePEc:bla:jorssb:v:82:y:2020:i:4:p:871-932.
  18. S. Engelke and J. Ivanovs. Sparse structures for multivariate extremes. Annual Review of Statistics and its Application, 8:241–270, 2021. doi: 10.1146/annurev-statistics-040620-041554.
  19. Limiting forms of the frequency distribution of the largest or smallest member of a sample. Mathematical Proceedings of the Cambridge Philosophical Society, 24(2):180–190, 1928. doi: 10.1017/S0305004100015681.
  20. D. A. Freedman. Bootstrapping regression models. Annals of Statistics, 9(6):1218–1228, November 1981. doi: 10.1214/aos/1176345638.
  21. Causal inference for complex longitudinal data: the continuous case. The Annals of Statistics, 29:1785–1811, 2001. doi: 10.1214/aos/1015345962.
  22. N. Gissibl and C. Klüppelberg. Max-linear models on directed acyclic graphs. Bernoulli, 24:2693–2720, 2018. doi: 10.3150/17-BEJ941.
  23. Causal discovery in heavy-tailed models. The Annals of Statistics, 49, 2020. doi: 10.1214/20-AOS2021.
  24. W. H. Greene. Econometric Analysis. Pearson Education, 2008. ISBN 0-273-75356-8.
  25. J. Hahn. Bootstrapping quantile regression estimators. Econometric Theory, 11(1):105–121, 1995. URL http://www.jstor.org/stable/3532932.
  26. A. Hannart and P. Naveau. Probabilities of causation of climate changes. Journal of Climate, 31:5507–5524, 2018. doi: 10.1175/JCLI-D-17-0304.1.
  27. Returns to education: The causal effects of education on earnings, health, and smoking. Journal of Political Economy, 126(1):197–246, October 2018. doi: 10.1086/698760.
  28. K. Hirano and G. W. Imbens. The Propensity Score with Continuous Treatments, chapter 7, pages 73–84. John Wiley and Sons, Ltd, 2004. ISBN 9780470090459. doi: 10.1002/0470090456.ch7.
  29. P. W. Holland. Statistics and causal inference. Journal of the American Statistical Association, 81(396):945–960, 1986. doi: 10.2307/2289064.
  30. Extreme continuous treatment effects: Measures, estimation and inference. Arxiv preprint 2209.00246, 2022.
  31. Causal inference with general treatment regimes. Journal of the American Statistical Association, 99(467):854–866, 2004. doi: 10.1198/016214504000001187.
  32. Misunderstandings Between Experimentalists and Observationalists about Causal Inference. Journal of the Royal Statistical Society Series A: Statistics in Society, 171(2):481–502, 03 2008. doi: 10.1111/j.1467-985X.2007.00527.x.
  33. Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction. Cambridge University Press, Cambridge, 2015. doi: 10.1017/CBO9781139025751.
  34. E. H. Kennedy. Nonparametric causal effects based on incremental propensity score interventions. JASA, 114(526):645–656, 2019. doi: 10.1080/01621459.2017.1422737.
  35. Non-parametric methods for doubly robust estimation of continuous treatment effects. Journal of the Royal Statistical Society Series B: Statistical Methodology, 79(4):1229–1245, 2017. ISSN 1467-9868. doi: 10.1111/rssb.12212.
  36. G. King and L. Zeng. The dangers of extreme counterfactuals. Political Analysis, 14(2):131–159, 2006. doi: 10.1093/pan/mpj004.
  37. A. Kiriliouk and P. Naveau. Climate extreme event attribution using multivariate peaks-over-thresholds modeling and counterfactual theory. The Annals of Applied Statistics, 2020. doi: 10.1214/20-AOAS1355.
  38. C. Klüppelberg and M. Krali. Estimating an extreme bayesian network via scalings. Journal of Multivariate Analysis, 181:104672, 2021. doi: 10.1016/j.jmva.2020.104672.
  39. R. Koenker. Quantile Regression. Econometric Society Monographs. Cambridge University Press, 2005. doi: 10.1017/CBO9780511754098.
  40. Generalized farlie-gumbel-morgenstern copulas. In Information Processing and Management of Uncertainty in Knowledge-Based Systems. Theory and Foundations, volume 853 of Communications in Computer and Information Science, pages 244–252. Springer International Publishing, 2018. ISBN 978-3-319-91472-5. doi: 10.1007/978-3-319-91473-2_21.
  41. Evaluation of the effect of a continuous treatment: A machine learning approach with an application to treatment for traumatic brain injury. Health economics, 24(9):1213–1228, 2015. doi: 10.1002/hec.3189.
  42. Continuous treatment effect estimation via generative adversarial de-confounding. In Proceedings of the 2020 KDD Workshop on Causal Discovery, volume 127 of Proceedings of Machine Learning Research, pages 4–22. PMLR, 2020. URL https://proceedings.mlr.press/v127/li20a.html.
  43. H. Low and C. Meghir. The use of structural models in econometrics. Journal of Economic Perspectives, 31(2):33–58, 2017. doi: 10.1257/jep.31.2.33.
  44. Statistical methods for extreme event attribution in climate science. Annual Review of Statistics and Its Application, 7(1):89–110, 2020. doi: 10.1146/annurev-statistics-031219-041314.
  45. Nonparametric causal effects based on marginal structural models. Journal of Statistical Planning and Inference, 137(2):419–434, 2007. doi: 10.1016/j.jspi.2005.12.008.
  46. A.M. Neville. Properties of Concrete. Pearson Education Limited, 2011.
  47. Causal modelling of heavy-tailed variables and confounders with application to river flow. Extremes, pages 573–594, 2023. doi: 10.1007/s10687-022-00456-4.
  48. J. Pearl. Direct and indirect effects. In Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence, UAI’01, page 411–420, 2001. doi: 10.5555/2074022.2074073.
  49. J. Pearl. Causality: Models, Reasoning and Inference. Cambridge University Press, 2009. ISBN 978-0521895606.
  50. K. Perlin. An image synthesizer. SIGGRAPH Comput. Graph., 19(0097-8930):287–296, 1985. doi: 10.1145/325165.325247.
  51. J. Pickands. Statistical inference using extreme order statistics. The Annals of Statistics, 3(1), 1975. doi: 10.1214/aos/1176343003.
  52. S. I. Resnick. Extreme Values, Regular Variation and Point Processes. Springer, New York, 2008.
  53. Marginal structural models and causal inference in epidemiology. Epidemiology, 11:550–560, 2000.
  54. The central role of the propensity score in observational studies for causal effects. Biometrika, 70:41–55, 1983. doi: 10.1093/biomet/70.1.41.
  55. Extending marginal structural models through local, penalized, and additive learning. Working Paper 212, Division of Biostatistics, UC Berkeley, California, 2006.
  56. D. B. Rubin. Causal inference using potential outcomes: Design, modeling, decisions. Journal of the American Statistical Association, 100(469):322–331, 2005. doi: 10.2307/2289064.
  57. Threshold selection in univariate extreme value analysis. Extremes, 24(4):881–913, 2021. doi: 10.1007/s10687-021-00405-7.
  58. X. Shen and N. Meinshausen. Engression: Extrapolation for nonlinear regression? arxiv preprint 2307.00835, 2024.
  59. R.L. Smith. Extreme value theory. Handbook of Applicable Mathematics, 1(7):437–447, 1990.
  60. A.N. Soklakov. Occam’s razor as a formal basis for a physical theory. Foundations of Physics Letters, 2002.
  61. A. W. van der Vaart. Bootstrap. Cambridge Series in Statistical and Probabilistic Mathematics. Cambridge University Press, 1998.
  62. Causal isotonic regression. JRSSb, 82(3):719–747, Jul 2020. doi: 10.1111/rssb.12372.
  63. S.N. Wood. Generalized Additive Models: An Introduction with R. Chapman and Hall/CRC, 2 edition, 2017.
  64. I. Yeh. Modeling of strength of high performance concrete using artificial neural networks. Cement and Concrete Research, 28(12):1797–1808, 1998.
  65. B. D. Youngman. evgam: An r package for generalized additive extreme value models. Journal of Statistical Software, 103(3):1–26, 2022. doi: 10.18637/jss.v103.i03.
  66. Y. Zhang. Extremal quantile treatment effects. The Annals of Statistics, 46(6B):3707–3740, 2018. doi: 10.1214/17-AOS1673.
  67. Propensity score-based methods for causal inference in observational studies with non-binary treatments. Statistical Methods in Medical Research, 29(3):709–727, 2020. doi: 10.1177/0962280219888745.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets