Hat Matrix Is Symmetric
In hindsight it is geometrically obviousthat we should have hadH2H.
Hat matrix is symmetric. For anyy2Rnthe closest point toyinsideof MisHy. I 1 n is a data matrix of p explanatory variables and ϵ is a vector of errors. As a result we can concisely represent any skew symmetric 3x3 matrix as a 3x1 vector.
Also for the matrix for all the values of i and j. It follows thatthe hat matrixHis symmetric too. Square matrix issymmetric if it can be flippedaround its main diagonal that is xij xji.
In otherwords if Xis symmetric XX0. Where p is the number of coefficients and n is the number of observations rows of X in the regression model. R si r i p 1 H ii d si d i p 1 H ii Generally speaking the standardized deviance residuals tend to be preferable because they are more symmetric than the standardized Pearson residuals but both are commonly used.
The hat operator allows us to switch between these two representations. If the transpose of a matrix is equal to the negative of itself the matrix is said to be skew symmetric. Let A be a symmetric and idempotent n n matrix.
A symmetric idempotent matrix such asHis called a. A matrix can be skew symmetric only if it is square. Let hij indicate the ij-th element of H.
The hat matrix is symmetric The hat matrix is idempotent ie. Symmetric Because the hat matrix is a specific kind of projection matrix then it. HH I-HI-HH2H I-H2I-H2.