Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Linear least squares
open-in-new
<p>Linear least squares (LLS) is the <a href="/facts/Least_squares_approximation/50jIwbxC">least squares approximation</a> of <a href="/facts/Linear_functions/Ejvy8CKy">linear functions</a> to data. It is a set of formulations for solving statistical problems involved in <a href="/facts/Linear_regression/5n998IhK">linear regression</a>, including variants for <a href="/facts/Ordinary_least_squares/q7H9k5vM">ordinary</a> (unweighted), <a href="/facts/Weighted_least_squares/BpCgNF5m">weighted</a>, and <a href="/facts/Generalized_least_squares/NI2GL3RK">generalized</a> (correlated) <a href="/facts/Residuals_(statistics)/Ef0LgAS4">residuals</a>. <a href="/facts/Numerical_methods_for_linear_least_squares/JQmo6jj6">Numerical methods for linear least squares</a> include inverting the matrix of the normal equations and <a href="/facts/Matrix_decomposition/xVBnAg0x">orthogonal decomposition</a> methods. </p>