AUTHOR=Uraibi Hassan S. , Waheed Mohammed Qasim 

TITLE=Weighted fast-trimmed likelihood estimator for mixture regression models

JOURNAL=Frontiers in Applied Mathematics and Statistics

VOLUME=Volume 10 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/applied-mathematics-and-statistics/articles/10.3389/fams.2024.1471222

DOI=10.3389/fams.2024.1471222

ISSN=2297-4687

ABSTRACT=The fast-trimmed likelihood estimate is a robust method to estimate the parameters of a mixture regression model. Unfortunately, this method is not resistant to the presence of bad leverage points, which are outliers in the direction of independent variables. The weighted, fast-trimmed likelihood estimate has been proposed in this manuscript to overcome the problem of leverage points. The proposed method employs the weights of the minimum covariance determinant with the suspected rows that probably have leverage points. Notably, real data and simulation studies have been considered to determine the efficiency of the proposed method compared with the previous methods. Accordingly, the result reveals that the weighted fast-trimmed estimate method is more robust and reliable than the fast-trimmed estimate and Expectation-Maximization (EM) methods, where the sample sizes are small.