The Hat Matrix and Regression Diagnostics
نویسنده
چکیده
Myers, Montgomery, and Vining explain the matrix algebra of OLS with more clarity than any other source I’ve found. Carefuly study p. 9-14 or so. The only criticism I have of their style is that they don’t use the hat symbol to differentiate a parameter estimate from the symbol that represents the true value. So if you compare what I write with what they write, you see I try to differentiate β̂ from β, whereas I think they are inconsistent, sometimes using b for the estimates, but also sometimes β is either an estimate or a parameter. Basically, the theory of OLS is that this linear relationship holds:
منابع مشابه
Sensitivity of Leverage Scores and Coherence for Randomized Matrix Algorithms
Leverage Scores. Statistical leverage scores were introduced in 1978 by Hoaglin and Welsch [8] to detect outliers when computing regression diagnostics, see also [3, 12]. To be specific, consider the least squares problem minx ‖Ax− b‖2, where A is a real m× n matrix with rank(A) = n. The so-called hat matrix H ≡ A(AA)A is the orthogonal projector onto range(A), and determines the fit b̂ ≡ Hb. Th...
متن کاملNumerical Solution of Delay Fractional Optimal Control Problems using Modification of Hat Functions
In this paper, we consider the numerical solution of a class of delay fractional optimal control problems using modification of hat functions. First, we introduce the fractional calculus and modification of hat functions. Fractional integral is considered in the sense of Riemann-Liouville and fractional derivative is considered in the sense of Caputo. Then, operational matrix of fractional inte...
متن کاملSurvey weighted hat matrixand leverages
Regression diagnostics are geared toward identifying individual points or groups of points that have an important influence on a fitted model. When fitting a model with survey data, the sources of influence are the response variable Y, the predictor variables X, and the survey weights, W. This article discusses the use of the hat matrix and leverages to identify points that may be influential i...
متن کاملUsing operational matrix for numerical solution of fractional differential equations
In this article, we have discussed a new application of modification of hat functions on nonlinear multi-order fractional differential equations. The operational matrix of fractional integration is derived and used to transform the main equation to a system of algebraic equations. The method provides the solution in the form of a rapidly convergent series. Furthermore, error analysis of the pro...
متن کاملEstimation and Variable Selection in Additive Nonparametric Regression Models 1
Additive regression models have been shown to be useful in many situations. Numerical estimation of these models is usually done using the back-tting technique. This iterative numerical procedure converges very fast but has the disadvantage of a complicated`hat matrix.' This paper proposes an estimator with an explicit`hat matrix' which does not use backktting. The asymptotic normality of the e...
متن کامل