Omar Fetitah
Omar Fetitah has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Mohammed Kadi Attouch
Laboratory of Statistics and Stochastic Processes, University of Djillali Liabes, BP 89, Sidi Bel Abbes 22000, Algeria
9 shared publications - Ibrahim Mufrah Almanjahie
Department of Mathematics, College of Science, King Khalid University, Abha, Saudi Arabia
6 shared publications - Tawfik Benchikh
Laboratory of Statistics and Stochastic Processes University of Djillali Liabes
6 shared publications - Ali Righi
Laboratoire de Statistique Processus Stochastique, University of Djillali Liabes, Sidi Bel Abbes, Algeria
2 shared publications - Fatimah Alshahrani
Department of Mathematical Sciences, College of Science, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
2 shared publications Ali Righi
Laboratory of Statistics and Stochastic Processes, University of Djillali Liabes
1 shared publication
Latest Publications
- Open Access
- 24 June 2025
- Published by Hacettepe University in Hacettepe Journal of Mathematics and Statistics
- Vol. 54 (3) , 1164-1186
Spatial $k$NN-Local linear estimation for semi-functional partial linear regression
The objective of this paper is to investigate a semi-functional partial linear regression model for spatial data. The estimators are constructed using a $k$-nearest neighbors local linear method.Then, under suitable regularity conditions, we establish the asymptotic distribution of the parametric component and derive the uniform almost sure convergence rate for the nonparametric component. To assess the performance of the proposed estimators, we performed both simulation studies and real-data analyses. The results are compared with existing methods for semi-functional partial linear regression models using cross-validation. Specifically, we evaluate the predictive performance in terms of mean squared error and compare it against several benchmark estimators, including the kernel estimator, the local linear estimator and the $k$NN estimator. This practical study clearly demonstrates the feasibility and superiority of the local linear method estimator $k$-nearest neighbors over competing methods. This is evidenced by the lower mean squared error achieved by this estimator in both the simulation study and the real data application. These results indicate that this hybrid approach effectively addresses the common issue of bandwidth selection and yields estimators with reduced bias.
- 24 June 2025
- Published by Hacettepe University in Hacettepe Journal of Mathematics and Statistics
- Vol. 54 (3) , 1164-1186
Open AccessSpatial $k$NN-Local linear estimation for semi-functional partial linear regression
The objective of this paper is to investigate a semi-functional partial linear regression model for spatial data. The estimators are constructed using a $k$-nearest neighbors local linear method.Then, under suitable regularity conditions, we establish the asymptotic distribution of the parametric component and derive the uniform almost sure convergence rate for the nonparametric component. To assess the performance of the proposed estimators, we performed both simulation studies and real-data analyses. The results are compared with existing methods for semi-functional partial linear regression models using cross-validation. Specifically, we evaluate the predictive performance in terms of mean squared error and compare it against several benchmark estimators, including the kernel estimator, the local linear estimator and the $k$NN estimator. This practical study clearly demonstrates the feasibility and superiority of the local linear method estimator $k$-nearest neighbors over competing methods. This is evidenced by the lower mean squared error achieved by this estimator in both the simulation study and the real data application. These results indicate that this hybrid approach effectively addresses the common issue of bandwidth selection and yields estimators with reduced bias.
- 25 February 2025
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 54 (22) , 7052-7083
Relative error regression function estimation using the Bernstein polynomials approach
- 25 February 2025
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 54 (22) , 7052-7083
Relative error regression function estimation using the Bernstein polynomials approach
- Open Access
- 1 January 2025
- Published by American Institute of Mathematical Sciences (AIMS) in AIMS Mathematics
- Vol. 10 (7) , 15929-15954
The k nearest neighbors local linear estimator of semi functional partial linear model with missing response at random
This paper aims to investigate a semi-functional partial linear regression model in the presence of missing data in the response variable under the missing at random mechanism. We construct estimators using the kNN-local linear method and establish the asymptotic distribution of the parametric component. Additionally, the uniform almost complete consistency rates for the nonparametric component with respect to the number of neighbors under appropriate conditions is derived. Through simulations and real data analysis, we assess the effectiveness of the proposed approach and demonstrate its superiority by comparing it with existing methods for semi-functional partial linear regression models.
- 1 January 2025
- Published by American Institute of Mathematical Sciences (AIMS) in AIMS Mathematics
- Vol. 10 (7) , 15929-15954
Open AccessThe k nearest neighbors local linear estimator of semi functional partial linear model with missing response at random
This paper aims to investigate a semi-functional partial linear regression model in the presence of missing data in the response variable under the missing at random mechanism. We construct estimators using the kNN-local linear method and establish the asymptotic distribution of the parametric component. Additionally, the uniform almost complete consistency rates for the nonparametric component with respect to the number of neighbors under appropriate conditions is derived. Through simulations and real data analysis, we assess the effectiveness of the proposed approach and demonstrate its superiority by comparing it with existing methods for semi-functional partial linear regression models.
- Open Access
- 1 January 2025
- Published by Walter de Gruyter GmbH in Demonstratio Mathematica
- Vol. 58 (1)
Estimation for spatial semi-functional partial linear regression model with missing response at random
The aim of this article is to study a semi-functional partial linear regression model (SFPLR) for spatial data with responses missing at random (MAR). The estimators are constructed using the kernel method, and some asymptotic properties, such as the probability convergence rates of the nonparametric component and the asymptotic distribution of the parametric and nonparametric components, are established under certain conditions. Next, the performance and superiority of these estimators are presented and examined through a study on simulated data, comparing our semi-functional partially linear model with the MAR estimator to the semi-functional partially linear model with the full-case estimator, and the functional nonparametric regression model estimator with MAR. The results indicate that the proposed estimators outperform traditional estimators as the amount of randomly missing data increases. Additionally, a study is conducted on real data regarding the modeling of pollution levels using our model, incorporating covariates such as average daily temperature as a functional variable, alongside maximum daily mixing height, total daily precipitation, and daily primary aerosol emission rates as explanatory variables.
- 1 January 2025
- Published by Walter de Gruyter GmbH in Demonstratio Mathematica
- Vol. 58 (1)
Open AccessEstimation for spatial semi-functional partial linear regression model with missing response at random
The aim of this article is to study a semi-functional partial linear regression model (SFPLR) for spatial data with responses missing at random (MAR). The estimators are constructed using the kernel method, and some asymptotic properties, such as the probability convergence rates of the nonparametric component and the asymptotic distribution of the parametric and nonparametric components, are established under certain conditions. Next, the performance and superiority of these estimators are presented and examined through a study on simulated data, comparing our semi-functional partially linear model with the MAR estimator to the semi-functional partially linear model with the full-case estimator, and the functional nonparametric regression model estimator with MAR. The results indicate that the proposed estimators outperform traditional estimators as the amount of randomly missing data increases. Additionally, a study is conducted on real data regarding the modeling of pollution levels using our model, incorporating covariates such as average daily temperature as a functional variable, alongside maximum daily mixing height, total daily precipitation, and daily primary aerosol emission rates as explanatory variables.
- Open Access
- 1 July 2024
- Published by Brazilian Journals in STUDIES IN ENGINEERING AND EXACT SCIENCES
- Vol. 5 (2) , e8039
Almost complete convergence of the functional local linear estimator of the expectile regression for data missing at random
In this article, the authors investigate the properties of a local linear estimator for the expectile regression function in scenarios where the scalar response variable is missing at random, and the covariate is a functional variable. The study addresses the challenge of estimating the expectile regression function when the response variable is not fully observed, a common issue in statistical analysis where missing data can significantly impact the accuracy of predictions and inferences. The key contribution of the paper lies in the establishment of the almost complete convergence of the proposed estimator. This convergence resultis derived under a set of appropriate conditions, ensuring that the estimator approaches the true expectile regression function with a probability tending to wards one as the sample size increases. The authors provide a rigorous theoretical foundation for this convergence, including assumptions about the smoothness of the functional covariate and the randomness of the missing data mechanism. To demonstrate the practical applicability of their method, the authors conduct a comprehensive simulation study. This study compares the performance of their local linear estimator with other existing methods in terms of bias, variance, and convergence speed. The simulation resultshighlight the effectiveness of the proposed approach, especially in settings where the response variable is partially missing and the covariates are functional in nature.
- 1 July 2024
- Published by Brazilian Journals in STUDIES IN ENGINEERING AND EXACT SCIENCES
- Vol. 5 (2) , e8039
Open AccessAlmost complete convergence of the functional local linear estimator of the expectile regression for data missing at random
In this article, the authors investigate the properties of a local linear estimator for the expectile regression function in scenarios where the scalar response variable is missing at random, and the covariate is a functional variable. The study addresses the challenge of estimating the expectile regression function when the response variable is not fully observed, a common issue in statistical analysis where missing data can significantly impact the accuracy of predictions and inferences. The key contribution of the paper lies in the establishment of the almost complete convergence of the proposed estimator. This convergence resultis derived under a set of appropriate conditions, ensuring that the estimator approaches the true expectile regression function with a probability tending to wards one as the sample size increases. The authors provide a rigorous theoretical foundation for this convergence, including assumptions about the smoothness of the functional covariate and the randomness of the missing data mechanism. To demonstrate the practical applicability of their method, the authors conduct a comprehensive simulation study. This study compares the performance of their local linear estimator with other existing methods in terms of bias, variance, and convergence speed. The simulation resultshighlight the effectiveness of the proposed approach, especially in settings where the response variable is partially missing and the covariates are functional in nature.
- Open Access
- 23 April 2024
- Published by Hacettepe University in Hacettepe Journal of Mathematics and Statistics
- Vol. 53 (2) , 537-555
Local linear-$k$NN smoothing for semi-functional partial linear regression
The aim of this paper is to study a semi-functional partial linear regression model. The estimators are constructed by $k$-nearest neighbors local linear method. Some asymptotic results are established for an i.i.d sample under certain conditions, including asymptotic normality of the parametric component and the almost certain convergence (with rate) of the non-parametric component. Lastly, using cross-validation, the performances of our estimation method are presented on simulated data and on real data by comparing them with other known approaches for semi-functional partial linear regression models.
- 23 April 2024
- Published by Hacettepe University in Hacettepe Journal of Mathematics and Statistics
- Vol. 53 (2) , 537-555
Open AccessLocal linear-$k$NN smoothing for semi-functional partial linear regression
The aim of this paper is to study a semi-functional partial linear regression model. The estimators are constructed by $k$-nearest neighbors local linear method. Some asymptotic results are established for an i.i.d sample under certain conditions, including asymptotic normality of the parametric component and the almost certain convergence (with rate) of the non-parametric component. Lastly, using cross-validation, the performances of our estimation method are presented on simulated data and on real data by comparing them with other known approaches for semi-functional partial linear regression models.
- Open Access
- 7 December 2023
- Published by MDPI AG in Preprints.org
Nonparametric Partial Linear Estimation for Spatial Functional Data with Missing At-Random
The aim of this paper is to study a semi-functional partial linear regression model (SFPLR) for spatial data with responses missing at random. The estimators are constructed by the kernel method, and some asymptotic properties such as probability convergence rates of the nonparametric component and asymptotic distribution of the parametric and nonparametric components are established under certain conditions. Next, the performances and the superiority of these estimators are presented and examined using a study on simulated data and on real data by carrying out a comparison between our semi-functional partially linear model with MAR estimator (SFPLRM), the semi-functional partially linear model with the full-case estimator (SFPLRC) and the nonparametric functional model estimator with MAR (FNPM). The results show that the proposed estimators outperform existing estimators as the number of random missing data increases.
- 7 December 2023
- Published by MDPI AG in Preprints.org
Open AccessNonparametric Partial Linear Estimation for Spatial Functional Data with Missing At-Random
The aim of this paper is to study a semi-functional partial linear regression model (SFPLR) for spatial data with responses missing at random. The estimators are constructed by the kernel method, and some asymptotic properties such as probability convergence rates of the nonparametric component and asymptotic distribution of the parametric and nonparametric components are established under certain conditions. Next, the performances and the superiority of these estimators are presented and examined using a study on simulated data and on real data by carrying out a comparison between our semi-functional partially linear model with MAR estimator (SFPLRM), the semi-functional partially linear model with the full-case estimator (SFPLRC) and the nonparametric functional model estimator with MAR (FNPM). The results show that the proposed estimators outperform existing estimators as the number of random missing data increases.
- 30 November 2023
- Published by Chiang Mai University in Chiang Mai Journal of Science
- Vol. 50 (6) , 1-22
Spatiotemporal Analysis of Ozone Concentration Using Semi-Functional Partial Linear Models
Chiang Mai Journal of Science, Faculty of Science, Chiang Mai University
- 30 November 2023
- Published by Chiang Mai University in Chiang Mai Journal of Science
- Vol. 50 (6) , 1-22
Spatiotemporal Analysis of Ozone Concentration Using Semi-Functional Partial Linear Models
Chiang Mai Journal of Science, Faculty of Science, Chiang Mai University
- Open Access
- 13 September 2023
- Published by Wiley in Journal of Mathematics
- Vol. 2023, 1-20
Asymptotic Normality of Nonparametric Kernel Regression Estimation for Missing at Random Functional Spatial Data
This study investigates the estimation of the regression function using the kernel method in the presence of missing at random responses, assuming spatial dependence, and complete observation of the functional regressor. We construct the asymptotic properties of the established estimator and derive the probability convergence (with rates) as well as the asymptotic normality of the estimator under certain weak conditions. Simulation studies are then presented to examine and show the performance of our proposed estimator. This is followed by examining a real data set to illustrate the suggested estimator’s efficacy and demonstrate its superiority. The results show that the proposed estimator outperforms existing estimators as the number of missing at random data increases.
- 13 September 2023
- Published by Wiley in Journal of Mathematics
- Vol. 2023, 1-20
Open AccessAsymptotic Normality of Nonparametric Kernel Regression Estimation for Missing at Random Functional Spatial Data
This study investigates the estimation of the regression function using the kernel method in the presence of missing at random responses, assuming spatial dependence, and complete observation of the functional regressor. We construct the asymptotic properties of the established estimator and derive the probability convergence (with rates) as well as the asymptotic normality of the estimator under certain weak conditions. Simulation studies are then presented to examine and show the performance of our proposed estimator. This is followed by examining a real data set to illustrate the suggested estimator’s efficacy and demonstrate its superiority. The results show that the proposed estimator outperforms existing estimators as the number of missing at random data increases.
- Open Access
- 31 March 2023
- Published by Hacettepe University in Hacettepe Journal of Mathematics and Statistics
- Vol. 52 (2) , 512-528
kNN robustification equivariant nonparametric regression estimators for functional ergodic data
We discuss in this paper the robust equivariant nonparametric regression estimators for ergodic data with the k Nearst Neighbour (kNN) method. We consider a new robust regression estimator when the scale parameter is unknown. The principal aim is to prove the almost complete convergence (with rate) for the proposed estimator. Furthermore, a comparison study based on simulated data is also provided to illustrate the finite sample performances and the usefulness of the kNN approach and to prove the highly sensitive of the kNN approach to the presence of even a small proportion of outliers in the data.
- 31 March 2023
- Published by Hacettepe University in Hacettepe Journal of Mathematics and Statistics
- Vol. 52 (2) , 512-528
Open AccesskNN robustification equivariant nonparametric regression estimators for functional ergodic data
We discuss in this paper the robust equivariant nonparametric regression estimators for ergodic data with the k Nearst Neighbour (kNN) method. We consider a new robust regression estimator when the scale parameter is unknown. The principal aim is to prove the almost complete convergence (with rate) for the proposed estimator. Furthermore, a comparison study based on simulated data is also provided to illustrate the finite sample performances and the usefulness of the kNN approach and to prove the highly sensitive of the kNN approach to the presence of even a small proportion of outliers in the data.