Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 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

Optimal Bias-Correction and Valid Inference in High-Dimensional Ridge Regression: A Closed-Form Solution (2405.00424v2)

Published 1 May 2024 in econ.EM, stat.ME, and stat.ML

Abstract: Ridge regression is an indispensable tool in big data analysis. Yet its inherent bias poses a significant and longstanding challenge, compromising both statistical efficiency and scalability across various applications. To tackle this critical issue, we introduce an iterative strategy to correct bias effectively when the dimension $p$ is less than the sample size $n$. For $p>n$, our method optimally mitigates the bias such that any remaining bias in the proposed de-biased estimator is unattainable through linear transformations of the response data. To address the remaining bias when $p>n$, we employ a Ridge-Screening (RS) method, producing a reduced model suitable for bias correction. Crucially, under certain conditions, the true model is nested within our selected one, highlighting RS as a novel variable selection approach. Through rigorous analysis, we establish the asymptotic properties and valid inferences of our de-biased ridge estimators for both $p<n$ and $p>n$, where, both $p$ and $n$ may increase towards infinity, along with the number of iterations. We further validate these results using simulated and real-world data examples. Our method offers a transformative solution to the bias challenge in ridge regression inferences across various disciplines.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. Abadie, A., and M. Kasy (2019): “Choosing among regularized estimators in empirical economics: The risk of machine learning,” Review of Economics and Statistics, 101(5), 743–762.
  2. Athey, S., and G. W. Imbens (2019): “Machine learning methods that economists should know about,” Annual Review of Economics, 11, 685–725.
  3. Bai, J., and S. Ng (2006): “Confidence intervals for diffusion index forecasts and inference with factor-augmented regressions,” Econometrica, 74(4), 1133–1150.
  4. Bai, Z., and Y. Yin (1993): “Limit of the Smallest Eigenvalue of a Large Dimensional Sample Covariance,” Annals of Probability, 21(3), 1275–1294.
  5. Bühlmann, P. (2013): “Statistical significance in high-dimensional linear models,” Bernoulli, 19(4), 1212–1242.
  6. Cheng, X., and B. E. Hansen (2015): “Forecasting with factor-augmented regression: A frequentist model averaging approach,” Journal of Econometrics, 186(2), 280–293.
  7. Dobriban, E., and S. Wager (2018): “High-dimensional asymptotics of prediction: Ridge regression and classification,” The Annals of Statistics, 46(1), 247–279.
  8. Fan, J., and J. Lv (2008): “Sure independence screening for ultrahigh dimensional feature space,” Journal of the Royal Statistical Society Series B: Statistical Methodology (with discussion), 70(5), 849–911.
  9. Gao, Z., and R. S. Tsay (2022): “Modeling high-dimensional time series: A factor model with dynamically dependent factors and diverging eigenvalues,” Journal of the American Statistical Association, 117(539), 1398–1414.
  10.    (2023): “Supervised Dynamic PCA: Linear Dynamic Forecasting with Many Predictors,” arXiv preprint arXiv:2307.07689.
  11. Giannone, D., M. Lenza, and G. E. Primiceri (2021): “Economic predictions with big data: The illusion of sparsity,” Econometrica, 89(5), 2409–2437.
  12. Hansen, B. E. (2022a): Econometrics. Princeton University Press.
  13.    (2022b): “A modern Gauss–Markov theorem,” Econometrica, 90(3), 1283–1294.
  14. Hastie, T. (2020): “Ridge regularization: An essential concept in data science,” Technometrics, 62(4), 426–433.
  15. Hoerl, A. E. (1959): “Optimum solution of many variables equations,” Chemical Engineering Progress, 55(11), 69–78.
  16. Hoerl, A. E., and R. W. Kennard (1970a): “Ridge regression: applications to nonorthogonal problems,” Technometrics, pp. 69–82.
  17.    (1970b): “Ridge regression: Biased estimation for nonorthogonal problems,” Technometrics, 12, 55–67.
  18. Hoerl, R. W. (1985): “Ridge analysis 25 years later,” The American Statistician, 39(3), 186–192.
  19. Leonard, M. K., L. Gwilliams, K. K. Sellers, J. E. Chung, D. Xu, G. Mischler, N. Mesgarani, M. Welkenhuysen, B. Dutta, and E. F. Chang (2023): “Large-scale single-neuron speech sound encoding across the depth of human cortex,” Nature, pp. 1–10.
  20. McCracken, M. W., and S. Ng (2016): “FRED-MD: A monthly database for macroeconomic research,” Journal of Business & Economic Statistics, 34(4), 574–589.
  21. Otwinowski, J., and J. B. Plotkin (2014): “Inferring fitness landscapes by regression produces biased estimates of epistasis,” Proceedings of the National Academy of Sciences, 111(22), E2301–E2309.
  22. Shao, J., and X. Deng (2012): “Estimation in high-dimensional linear models with deterministic design matrices,” The Annals of Statistics, 40(2), 812–831.
  23. Stock, J. H., and M. Watson (2002a): “Macroeconomic Forecasting Using Diffusion Indexes,” Journal of Business & Economic Statistics, 20, 147–162.
  24. Stock, J. H., and M. W. Watson (2002b): “Forecasting Using Principal Components From a Large Number of Predictors,” Journal of the American Statistical Association, 97(460), 1167–1179.
  25. Theobald, C. M. (1974): “Generalizations of mean square error applied to ridge regression,” Journal of the Royal Statistical Society Series B: Statistical Methodology, 36(1), 103–106.
  26. Tikhonov, A. N. (1943): “On the stability of inverse problems,” Doklady Akademii Nauk SSSR, 39(5), 195–198.
  27. van Wieringen, W. N. (2023): “Lecture notes on ridge regression,” arXiv preprint arXiv:1509.09169, v8.
  28. Vapnik, V. N. (2013): The nature of statistical learning theory. Springer science & business media.
  29. Wang, X., and C. Leng (2016): “High dimensional ordinary least squares projection for screening variables,” Journal of the Royal Statistical Society Series B: Statistical Methodology, 78(3), 589–611.
  30. Zahrt, A. F., J. J. Henle, B. T. Rose, Y. Wang, W. T. Darrow, and S. E. Denmark (2019): “Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning,” Science, 363(6424), eaau5631.
  31. Zhang, Y., and D. N. Politis (2022): “Ridge regression revisited: Debiasing, thresholding and bootstrap,” The Annals of Statistics, 50(3), 1401–1422.

Summary

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