Performance of some new Liu parameters for the linear regression model
2020 (English)In: Communications in Statistics - Theory and Methods, ISSN 0361-0926, E-ISSN 1532-415X, Vol. 49, no 17, p. 4178-4196Article in journal (Refereed) Published
Abstract [en]
This article introduces some Liu parameters in the linear regression model based on the work of Shukur, Månsson, and Sjölander. These methods of estimating the Liu parameter d increase the efficiency of Liu estimator. The comparison of proposed Liu parameters and available methods has done using Monte Carlo simulation and a real data set where the mean squared error, mean absolute error and interval estimation are considered as performance criterions. The simulation study shows that under certain conditions the proposed Liu parameters perform quite well as compared to the ordinary least squares estimator and other existing Liu parameters.
Place, publisher, year, edition, pages
Taylor & Francis, 2020. Vol. 49, no 17, p. 4178-4196
Keywords [en]
Liu estimator, Liu parameters, mean absolute error, mean squared error, Multicollinearity, Errors, Intelligent systems, Mean square error, Monte Carlo methods, Regression analysis, Parameter estimation
National Category
Probability Theory and Statistics
Identifiers
URN: urn:nbn:se:hj:diva-46440DOI: 10.1080/03610926.2019.1595654ISI: 000466204700001Scopus ID: 2-s2.0-85064660455OAI: oai:DiVA.org:hj-46440DiVA, id: diva2:1357289
2019-10-032019-10-032022-01-14Bibliographically approved