The F test for comparing a complete model to a reduced model can be used to test

(a) The significance of a single regression parameter in a multiple regression model.

(b) H0: β1 = · · · = βp = 0 in a multiple regression equation.

(c) H0: no interaction, in the model E(y) = α+β1x1 +β2x2 +β3x3 +β4x1x2 +β5x1x3 +β6x2x3.

(d) Whether the model E(y) = α+β1x1+β2x2 gives a significantly better fit than the model E(y) = α+β1x1+β2x3.