Process: moderation and mediation in Excel

This tutorial will show you how to run and interpret a mediation model in Excel using the XLSTAT statistical software.

Dataset for mediation analysis

The original data came from a questionnaire completed by employees in the industry sector. The dataset contains, for 20 individuals, a measure of empowering leadership that was derived from criteria such as the meaning of work, participation in decision-making, confidence in high performance, and autonomy. The data table also contains a measure of job well-being and organizational commitment for each of the employees.

The purpose is to explain organizational commitment as a function of empowering leadership. Workplace well-being will be considered as a potential mediator of the relationship between empowering leadership and organizational commitment.

Setting up the mediation model

• Open XLSTAT.

• Select the Advanced features / Marketing tools / Process: moderation and mediation. The Process: Moderation and Mediation dialog box appears.

• Select the model number associated with the mediation model (the corresponding number is 4).

• You can then select the data on the Excel sheet. Here, the Dependent variable (or variable to model) is the organizational commitment.

• The Explanatory Variable corresponds to empowering leadership. Here we want to explain the variability of organizational commitment as a function of empowering leadership.

• In Mediator variable(s), select the Well-Being column. We want to test whether job well-being can be considered a mediator of the effect of empowering leadership on organizational commitment.

• As the name of each variable is displayed at the top of the table, we must check the Variable labels checkbox.

• The computations begin once you have clicked on the OK button.

Interpreting the results of a mediation model

The "Direct effect of X on Y" table gives the value of the estimate of the direct effect of X on Y as well as various elements (confidence interval, Student's t) that allow us to conclude that the direct effect is not significant.

The "Indirects effects of X on Y" table provides details about the indirect effect present in the model. Here, since the value 0 is not included in the confidence interval, the indirect effect is considered significant.

Conclusion on the mediation model

The mediation model formed between empowering leadership, job well-being, and organizational commitment was found to be significant, meaning that there is a causal relationship between these 3 variables: empowering leadership has an effect on job well-being, and the latter then influences organizational commitment.