linear models

general linear models

anova

regression

10. Let Px denote the perpendicular projection matrix onto C(X). (a) Give a detailed argument showing that I-Px is the perpendicular projection matrix onto N(X). (b) Let X= 110 1 1 0 1 0 1 101 101 Compute Px and I - Px. (c) Express Y = - as the sum of two vectors, one in C(X) and one in N(X). (d) For the X matrix in part (b), describe in words what C(X) and N(X') are