Previous Page | Next Page

The Four Types of Estimable Functions

Examples

A One-Way Classification Model

For the model

     

the general form of estimable functions is (from the previous example)

     

Thus,

     

Tests involving only the parameters , , and must have an of the form

     

Since this for the parameters involves only two symbols, hypotheses with at most two degrees of freedom can be constructed. For example, letting be and , respectively, yields

     

The preceding can be used to test the hypothesis that . For this example, any with two linearly independent rows with column 1 equal to zero produces the same sum of squares. For example, a joint test for linear and quadratic effects of

     

gives the same SS. In fact, for any of full row rank and any nonsingular matrix of conformable dimensions,

     

A Three-Factor Main-Effects Model

Consider a three-factor main-effects model involving the CLASS variables , , and , as shown in Table 15.1.

Table 15.1 Three-Factor Main-Effects Model

Obs

 

 

 

1

 

1

 

2

 

1

2

 

1

 

1

 

2

3

 

2

 

1

 

3

4

 

2

 

2

 

2

5

 

2

 

2

 

2

The general form of an estimable function is shown in Table 15.2.

Table 15.2 General Form of an Estimable Function for Three-Factor Main-Effects Model

Parameter

 

Coefficient

(Intercept)

 

 

 

 

 

 

 

 

Since only four symbols (, , , and ) are involved, any testable hypothesis will have at most four degrees of freedom. If you form an matrix with four linearly independent rows according to the preceding rules, then testing is equivalent to testing that is uniformly 0. Symbolically,

     

In a main-effects model, the usual hypothesis of interest for a main effect is the equality of all the parameters. In this example, it is not possible to unambiguously test such a hypothesis because of confounding: any test for the equality of the parameters for any one of A, B, or C will necessarily involve the parameters for the other two effects. One way to proceed is to construct a maximum rank hypothesis (MRH) involving only the parameters of the main effect in question. This can be done using the general form of estimable functions. Note the following:

  • To get an MRH involving only the parameters of , the coefficients of associated with , , , , , and must be equated to zero. Starting at the top of the general form, let , then , then . If and are not to be involved, then must also be zero. Thus, is not estimable; that is, the MRH involving only the parameters has zero rank and .

  • To obtain the MRH involving only the parameters, let . But then to remove and from the comparison, must also be set to 0. Thus, is not estimable and .

  • To obtain the MRH involving only the parameters, let . Thus, the MRH involving only parameters is

         

    or any multiple of the left-hand side equal to . Furthermore,

         


A Multiple Regression Model

Suppose

     

where the matrix has full rank. The general form of estimable functions is as shown in Table 15.3.

Table 15.3 General Form of Estimable Functions for a Multiple Regression Model When Matrix Is of Full Rank

Parameter

 

Coefficient

 

 

 

 

For example, to test the hypothesis that , let and let . Then SS. In this full-rank case, all parameters, as well as any linear combination of parameters, are estimable.

Suppose, however, that . The general form of estimable functions is shown in Table 15.4.

Table 15.4 General Form of Estimable Functions for a Multiple Regression Model When Matrix Is Not of Full Rank

Parameter

 

Coefficient

 

 

 

 

For this example, it is possible to test . However, , , and are not jointly estimable; that is,

     
     
     
Previous Page | Next Page | Top of Page