Robust bootstrap regression testing in the presence of outliers
dc.citation.epage | 35 | |
dc.citation.issue | 1 | |
dc.citation.spage | 26 | |
dc.contributor.affiliation | Університет Аль-Кадисія | |
dc.contributor.affiliation | University of Al-Qadisiyah | |
dc.contributor.author | Хассан, С. У. | |
dc.contributor.author | Алі, К. Х. | |
dc.contributor.author | Hassan, S. U. | |
dc.contributor.author | Ali, K. H. | |
dc.coverage.placename | Львів | |
dc.coverage.placename | Lviv | |
dc.date.accessioned | 2023-12-13T09:11:07Z | |
dc.date.available | 2023-12-13T09:11:07Z | |
dc.date.created | 2021-03-01 | |
dc.date.issued | 2021-03-01 | |
dc.description.abstract | Бутстрап — це один із методів вибору випадкової вибірки із заміною, який був запропонований для вирішення проблеми малих вибірок, розподіли яких важко отримати. Розподіл бутстрап-вибірок є емпіричним або вільним, і завдяки його випадковому відбору із заміною ймовірність вибору конкретного спостереження може дорівнювати одиниці. На жаль, коли вихідні дані вибірки містять викиди, виникає серйозна проблема, яка призводить до некоректності оцінки за допомогою звичайних найменших квадратів, тому слід рекомендувати робастні методи регресії. Добре відомо, що найкраща робастна регресійна модель має високу точку пробою не більше ніж 0.50, тому робастний регресійний метод не буде працювати, якщо відсоток викидів у вибірці перевищує 0.50. Добре відомо, що бутстрап-процес з фіксованим x робить перевибірку залишків, які, ймовірно, мають викиди. Більше того, точка(и) важеля є викидом, який виникає в X-напрямку, тому буде існувати його вплив на бутстрапвибірки з фіксованим x. Тому прийняття рішення щодо нульової гіпотези коефіцієнтів бутстрап-регресії не може бути надійним. У цій статті пропонується використовувати зважений бутстрап із фіксованим x із ймовірнісним підходом, щоб гарантувати, що відсоток викидів у бутстрап-вибірках буде дуже низьким. А потім зважена M-оцінка повинна бути спрямована на розв’язання проблеми викидів і важливих точок та прийняття більш надійного рішення щодо перевірки гіпотези про коефіцієнти бутстрапрегресії. Ефективність запропонованого методу була порівняна з іншими методами на реальних та змодельованих даних. Результати показують, що запропонований нами метод є ефективнішим та надійнішим за інші. | |
dc.description.abstract | Bootstrap is one of the random sampling methods with replacement, that was proposed to address the problem of small samples whose distributions are difficult to derive. The distribution of bootstrap samples is empirical or free and due to its random sampling with replacement, the probability of choosing a specific observation may be equal to one. Unfortunately, when the original sample data contains an outlier, there is a serious problem that leads to a breakdown OLS (Ordinary Least Squares) estimator, and robust regression methods should be recommended. It is well known that the best robust regression method has a high breakdown point is not more than 0.50, so the robust regression method would break down when the percentage of outliers in the bootstrap sample exceeds 0.50. It is well known that fixed-x bootstrap is resampled the residuals which probably are having outliers. Moreover, the leverage point(s) is an outlier that occurs in X-direction, so the effects of it on fixed-x bootstrap samples would be existence. However, the decision-making about the null hypothesis of bootstrap regression coefficients could not be reliable. In this paper, we propose using weighted fixed-x bootstrap with a probability approach to guarantee the percentage of outliers in the bootstrap samples will be very low. And then weighted M-estimate should be to tackle the problem of outliers and leverage points and taking a more reliable decision about bootstrap regression coefficients hypothesis test. The performance of the suggested method has been tested with others by using real data and simulation. The results show our proposed method is more efficient and reliable than the others. | |
dc.format.extent | 26-35 | |
dc.format.pages | 10 | |
dc.identifier.citation | Hassan S. U. Robust bootstrap regression testing in the presence of outliers / S. U. Hassan, K. H. Ali // Mathematical Modeling and Computing. — Lviv : Lviv Politechnic Publishing House, 2022. — Vol 9. — No 1. — P. 26–35. | |
dc.identifier.citationen | Hassan S. U. Robust bootstrap regression testing in the presence of outliers / S. U. Hassan, K. H. Ali // Mathematical Modeling and Computing. — Lviv : Lviv Politechnic Publishing House, 2022. — Vol 9. — No 1. — P. 26–35. | |
dc.identifier.doi | 10.23939/mmc2022.01.026 | |
dc.identifier.uri | https://ena.lpnu.ua/handle/ntb/60552 | |
dc.language.iso | en | |
dc.publisher | Видавництво Львівської політехніки | |
dc.publisher | Lviv Politechnic Publishing House | |
dc.relation.ispartof | Mathematical Modeling and Computing, 1 (9), 2022 | |
dc.relation.references | [1] Amado C., Pires A. M. Robust bootstrap with non random weights based on the influence function. Communications in Statistics – Simulation and Computation. 33 (2), 377–396 (2004). | |
dc.relation.references | [2] Athreya K., Hinkley D. V. Bootstrap of the mean in the infinite variance case. Annals of Statistics. 15 (2), 724–731 (1987). | |
dc.relation.references | [3] Croux C., Filzmoser P., Pison G., Rousseeuw P. J. Fitting multiplicative models by robust alternating regressions. Statistics and Computing volume. 13, 23–36 (2003). | |
dc.relation.references | [4] Efron B. Bootstrap methods: another look at the jackknife. In Breakthroughs in Statistics. 569–593 (1992). | |
dc.relation.references | [5] Giloni A., Simonoff J. S., Sengupta B. Robust weighted LAD regression. Computational Statistics & Data Analysis. 50 (11), 3124–3140 (2006). | |
dc.relation.references | [6] Huber P. J. The place of the L1-norm in robust estimation. Computational Statistics & Data Analysis. 5 (4), 255–262 (1987). | |
dc.relation.references | [7] Huber P. J., Ronchetti E. M. Robust statistics. Wiley Series in Probability and Mathematical Statistics. John Wiley & Sons, Inc. (1981). | |
dc.relation.references | [8] Yohai J. V., Maronna A. R. Location estimators based on linear combinations of modified order statistics. Communications in Statistics – Theory and Methods. 5 (5), 481–486 (1976). | |
dc.relation.references | [9] Koenker R. Quantile regression. Cambridge University Press (2005). | |
dc.relation.references | [10] Midi H., Uraibi H. S., Talib B. A. Dynamic robust bootstrap method based on LTS estimators. European Journal of Scientific Research. 32 (3), 277–287 (2009). | |
dc.relation.references | [11] Habshah M., Norazan M. R., Rahmatullah Imon A. H. M. The performance of diagnostic-robust generaliozed potential approach for the identification of multiple high leverage points in linear regression. Journal of Applied Statistics. 36 (5), 507–520 (2009). | |
dc.relation.references | [12] Rousseeuw P. J. Least median of squares regression. Journal of the American Statistical Association. 79 (388), 871–880 (1984). | |
dc.relation.references | [13] Rousseeuw P. J., Leroy A. M. Robust Regression and Outlier Detection. Wiley Series in Probability and Mathematical Statistics. John Wiley & Sons, Inc. (1987). | |
dc.relation.references | [14] Shao J. Bootstrap estimation of the asymptotic variances of statistical functionals. Annals of the Institute of Statistical Mathematics. 42, 737–752 (1990). | |
dc.relation.references | [15] Shao J. Bootstrap variance estimators with truncation. Statistics & Probability Letters. 15 (2), 95–101 (1992). | |
dc.relation.references | [16] Singh K. Breakdown theory for bootstrap quantiles. Annals of Statistics. 26 (5), 1719–1732 (1998). | |
dc.relation.references | [17] Stromberg A. J. Robust covariance estimates based on resampling. Journal of Statistical Planning and Inference. 57 (2), 321–334 (1997). | |
dc.relation.references | [18] Uraibi H. S. Weighted Lasso Subsampling for High Dimensional Regression. Electronic Journal of Applied Statistical Analysis. 12 (1), 69–84 (2019). | |
dc.relation.references | [19] Uraibi H. S., Midi H. On Robust Bivariate and Multivariate Correlation Coefficient. Economic computation and economic cybernetics studies and research. 53 (2/2019), 221–239 (2019). | |
dc.relation.references | [20] Uraibi H. S., Midi H., Rana S. Robust stability best subset selection for autocorrelated data based on robust location and dispersion estimator. Journal of Probability and Statistics. 2015, Article ID 432986, 8 pages (2015). | |
dc.relation.references | [21] Uraibi H. S., Midi H., Rana S. Robust multivariate least angle regression. ScienceAsia. 43 (1), 56–60 (2017). | |
dc.relation.references | [22] Uraibi H. S., Midi H., Talib B. A., Yousif J. H. Linear regression model selection based on robust bootstrapping technique. American Journal of Applied Sciences. 6 (6), 1191–1198 (2009). | |
dc.relation.references | [23] Willems G. S., Aelst S. Fast and Robust Bootstrap for LTS. Computational Statistics & Data Analysis. 48 (4), 703–715 (2005). | |
dc.relation.referencesen | [1] Amado C., Pires A. M. Robust bootstrap with non random weights based on the influence function. Communications in Statistics – Simulation and Computation. 33 (2), 377–396 (2004). | |
dc.relation.referencesen | [2] Athreya K., Hinkley D. V. Bootstrap of the mean in the infinite variance case. Annals of Statistics. 15 (2), 724–731 (1987). | |
dc.relation.referencesen | [3] Croux C., Filzmoser P., Pison G., Rousseeuw P. J. Fitting multiplicative models by robust alternating regressions. Statistics and Computing volume. 13, 23–36 (2003). | |
dc.relation.referencesen | [4] Efron B. Bootstrap methods: another look at the jackknife. In Breakthroughs in Statistics. 569–593 (1992). | |
dc.relation.referencesen | [5] Giloni A., Simonoff J. S., Sengupta B. Robust weighted LAD regression. Computational Statistics & Data Analysis. 50 (11), 3124–3140 (2006). | |
dc.relation.referencesen | [6] Huber P. J. The place of the L1-norm in robust estimation. Computational Statistics & Data Analysis. 5 (4), 255–262 (1987). | |
dc.relation.referencesen | [7] Huber P. J., Ronchetti E. M. Robust statistics. Wiley Series in Probability and Mathematical Statistics. John Wiley & Sons, Inc. (1981). | |
dc.relation.referencesen | [8] Yohai J. V., Maronna A. R. Location estimators based on linear combinations of modified order statistics. Communications in Statistics – Theory and Methods. 5 (5), 481–486 (1976). | |
dc.relation.referencesen | [9] Koenker R. Quantile regression. Cambridge University Press (2005). | |
dc.relation.referencesen | [10] Midi H., Uraibi H. S., Talib B. A. Dynamic robust bootstrap method based on LTS estimators. European Journal of Scientific Research. 32 (3), 277–287 (2009). | |
dc.relation.referencesen | [11] Habshah M., Norazan M. R., Rahmatullah Imon A. H. M. The performance of diagnostic-robust generaliozed potential approach for the identification of multiple high leverage points in linear regression. Journal of Applied Statistics. 36 (5), 507–520 (2009). | |
dc.relation.referencesen | [12] Rousseeuw P. J. Least median of squares regression. Journal of the American Statistical Association. 79 (388), 871–880 (1984). | |
dc.relation.referencesen | [13] Rousseeuw P. J., Leroy A. M. Robust Regression and Outlier Detection. Wiley Series in Probability and Mathematical Statistics. John Wiley & Sons, Inc. (1987). | |
dc.relation.referencesen | [14] Shao J. Bootstrap estimation of the asymptotic variances of statistical functionals. Annals of the Institute of Statistical Mathematics. 42, 737–752 (1990). | |
dc.relation.referencesen | [15] Shao J. Bootstrap variance estimators with truncation. Statistics & Probability Letters. 15 (2), 95–101 (1992). | |
dc.relation.referencesen | [16] Singh K. Breakdown theory for bootstrap quantiles. Annals of Statistics. 26 (5), 1719–1732 (1998). | |
dc.relation.referencesen | [17] Stromberg A. J. Robust covariance estimates based on resampling. Journal of Statistical Planning and Inference. 57 (2), 321–334 (1997). | |
dc.relation.referencesen | [18] Uraibi H. S. Weighted Lasso Subsampling for High Dimensional Regression. Electronic Journal of Applied Statistical Analysis. 12 (1), 69–84 (2019). | |
dc.relation.referencesen | [19] Uraibi H. S., Midi H. On Robust Bivariate and Multivariate Correlation Coefficient. Economic computation and economic cybernetics studies and research. 53 (2/2019), 221–239 (2019). | |
dc.relation.referencesen | [20] Uraibi H. S., Midi H., Rana S. Robust stability best subset selection for autocorrelated data based on robust location and dispersion estimator. Journal of Probability and Statistics. 2015, Article ID 432986, 8 pages (2015). | |
dc.relation.referencesen | [21] Uraibi H. S., Midi H., Rana S. Robust multivariate least angle regression. ScienceAsia. 43 (1), 56–60 (2017). | |
dc.relation.referencesen | [22] Uraibi H. S., Midi H., Talib B. A., Yousif J. H. Linear regression model selection based on robust bootstrapping technique. American Journal of Applied Sciences. 6 (6), 1191–1198 (2009). | |
dc.relation.referencesen | [23] Willems G. S., Aelst S. Fast and Robust Bootstrap for LTS. Computational Statistics & Data Analysis. 48 (4), 703–715 (2005). | |
dc.rights.holder | © Національний університет “Львівська політехніка”, 2022 | |
dc.subject | бутстрап | |
dc.subject | надійна регресія | |
dc.subject | довірчі інтервали | |
dc.subject | точка | |
dc.subject | зважений бутстрап з ймовірністю | |
dc.subject | зважене M | |
dc.subject | перевірка гіпотези | |
dc.subject | bootstrap | |
dc.subject | robust regression | |
dc.subject | confidence intervals | |
dc.subject | point | |
dc.subject | WBP | |
dc.subject | weighted M | |
dc.subject | hypothesis test | |
dc.title | Robust bootstrap regression testing in the presence of outliers | |
dc.title.alternative | Робастне бутстрап регресійне тестування за наявності викидів | |
dc.type | Article |
Files
License bundle
1 - 1 of 1