Erdugan, Funda2025-01-212025-01-2120240361-09181532-4141https://doi.org/10.1080/03610918.2022.2098329https://hdl.handle.net/20.500.12587/24156A biased estimator, compared to least squares estimators, is one of the most used statistical procedures to overcome the problem of multicollinearity. Liu-type estimators, which are biased estimators, are preferred in a wide range of fields. In this article, we propose an almost unbiased Liu-type (AUNL) estimator and discuss its performance under the mean square error matrix criterion among existing estimators. The proposed AUNL estimator is a general estimator and is based on the function of a single biasing parameter. It includes an ordinary least squares estimator, an almost unbiased ridge estimator, an almost unbiased Liu estimator, and an almost unbiased two-parameter estimator. Finally, real data examples and a Monte Carlo simulation are provided to illustrate the theoretical results.eninfo:eu-repo/semantics/closedAccessAlmost unbiased Liu-type estimator; Biased estimation; Liu-type estimator; Mean squared error; MulticollinearityArticle5373081309310.1080/03610918.2022.20983292-s2.0-85133953308Q2WOS:000824408100001Q4