Source: Wikipedia. Pages: 150. Chapters: Linear regression, Autocorrelation, Least squares, Linear model, Overfitting, Ordinary least squares, Optimal design, Linear least squares, Errors-in-variables models, Regression toward the mean, Non-linear least squares, Generalized linear model, Interaction, Prediction interval, Instrumental variable, Multivariate adaptive regression splines, Structural equation modeling, Coefficient of determination, Total least squares, Robust regression, Least squares support vector machine, Sliced inverse regression, Least absolute deviations, Multicollinearity, Logistic regression, Generalized additive model for location, scale and shape, Simple linear regression, Proportional hazards models, Polynomial and rational function modeling, Polynomial regression, Sufficient dimension reduction, Local regression, Quantile regression, Partial least squares regression, Curve fitting, Fixed effects model, Seemingly unrelated regressions, Dependent and independent variables, Proofs involving ordinary least squares, Growth curve, Poisson regression, Difference in differences, Regression dilution, Errors and residuals in statistics, Stepwise regression, Numerical smoothing and differentiation, Unit-weighted regression, Backfitting algorithm, Lack-of-fit sum of squares, Heckman correction, Segmented regression, Nonlinear regression, Semiparametric regression, Explained sum of squares, Smoothing spline, Bayesian linear regression, Projection pursuit regression, Tobit model, Propensity score matching, Multinomial logit, Probit model, Explained variation, Generalized least squares, Mixed model, Deming regression, Path analysis, Calibration, Regression model validation, Binomial regression, Hat matrix, Bayesian multivariate linear regression, Mallows' Cp, Generalized estimating equation, Omitted-variable bias, CHAID, Isotonic regression, Mean and predicted response, Heteroscedasticity-consistent standard errors, Nonparametric regression, Canonical analysis, Iteratively reweighted least squares, Outline of regression analysis, Newey-West estimator, Generalized linear array model, Multiple correlation, Variable rules analysis, Least trimmed squares, Standardized coefficient, First-hitting-time model, Sinusoidal model, Moderation, Savitzky-Golay smoothing filter, Residual sum of squares, Fraction of variance unexplained, General linear model, Ordered logit, Dummy variable, Separation, Trend analysis, Random multinomial logit, Limited dependent variable, Principal component regression, Specification, Truncated regression model, Total sum of squares, Censored regression model, Guess value, Design matrix, White test, Moving least squares, Frisch-Waugh-Lovell theorem, Linear probability model, Hosmer-Lemeshow test, Generalized linear mixed model, Scatterplot smoothing, Path coefficient, Leverage, Multivariate probit, Controlling for a variable, Kitchen sink regression, Antecedent variable, Conditional change model, Comparison of general and generalized linear models, Proper linear model, Smearing retransformation, Cross-sectional regression. Excerpt: In statistics and econometrics, ordinary least squares (OLS) or linear least squares is a method for estimating the unknown parameters in a linear regression model. This method minimizes the sum of squared vertical distances between the observed responses in the dataset, and the responses predicted by the linear approximation. The resulting estimator can be expressed by a simple formu...