TESTING THE MEDIATING AND MODERATING EFFECTS OF OVERALL

SATISFACTION ON LOYALTY IN BROADBAND

HAFIZAH ZAINITA BINTI MOHAMAD ALWI

PENYELIA: DR. NUR RIZA MOHD SURADI

Research Objective

1. The purpose of this study was to test the mediating and moderating effects of the overall satisfaction on the relationship between overall satisfaction on loyalty in broadband services.

2. To test either the overall satisfaction is a full mediator, partial mediator or no mediator.

3. To test either the overall satisfaction is a moderator or not.

4. To understanding the mediating and moderating effects of the overall satisfaction on loyalty in broadband.

Objectives :-

Methodology

1) Test of Mediator

A mediator is defined as a variable that explains the relation between a predictor and an outcome ( Baron & Kenny,1986). Judd and Kenny (1981 b) recommended a series of regression models should be estimated.

To test for mediation, one should estimate the three following regression equations (Baron and Kenny ,1982) :-

- first, regressing the mediator (M) on the independent variable (x). - second, regressing the dependent variable (y) on the independent variable (x).

- third, regressing the dependent variable on both the independent variable and on the mediator.

If one or more of these relationship is nonsignificant, researcher usually conclude that mediation is not possible or likely.

1y

1

1y

Full mediation - If independent variable (X) is no longer significant when mediator

(M) is controlled, the finding supports. Partial mediation - If X is still significant (i.e., both X and significantly predict

dependent variable (Y) ,

Figure of mediator model by (Baron and Kenny ,1982) :-

2) Test of Moderator

Moderator can defined as a qualitative (e.g., sex, race, class) or quantitative (e.g., level of reward) variable that affects the direction and/or strength of the relation between an independent or predictor variable and a dependent or criterion variable.

figure of moderator model by (Baron and Kenny ,1982) :-

• The way to measure and test the differential effects depends in part on the level of measurement of the independent variable and the moderator variable. We will consider four eases:

- Case 1, both moderator and independent variables are categorical variables The analysis is a 2 X 2 ANOVA, and moderation is indicated by an interaction.

- Case 2, the moderator is a categorical variable and the independent variable a continuous variable. The typical way to measure this type of moderator effect is to correlate intentions with behavior separately for each gender and then test the difference. Test of difference between regression coefficient are given by Cohen and Cohen (1983).

- Case 3, the moderator is a continuous variable and the independent variable is a categorical variable.

1) If the independent variable is denote as X, the moderator as Z, and the dependent variable as Y, Y is regressed on X, Z, and XZ. Moderator effects are indicated by the significant effect of XZ while X and Z are controlled.

2) The second function in the figure is a quadratic function. The quadratic moderation can be tested by hierarchical regression procedures described by Cohen and Cohen (1983). Y is regressed on X, Z, XZ, Z², and XZ². The test of quadratic moderation is given by the test of XZ².

3) The third function is a step function. This pattern is tested by dichotomizing the moderator at the point where the step is supposed to occur and proceeding as in Case 1.

- Case 4, both variables are continuous variables.

- If dichotomizing the moderator, the pattern becomes Case 2.

- If one the effect of the independent variable (X) on the dependent variable

(Y) varies linearly or quadratically with respect to the moderator (Z), the

product variable approach described in Case 3 should be used.

• Assume that all the categorical variables are dichotomies.

Full mediation and moderation model adapted from Jones and Suh (2000);-

Transaction-specific satisfaction

Attitudinal Loyalty

Overall Satisfaction