Question

Imagine that you work for an organization that has administered a similar survey to employees, except the new survey has two stressor (interpersonal conflict, role ambiguity) and two strain (turnover intentions, burnout) variables, as opposed to just one stressor and one strain variable. Using data found in the Practice sheet of the dataset below, respond to the following questions as if you were explaining the data to a manager who is not familiar with statistical terminology:

1) Run a simple linear regression analysis with interpersonal conflict as the predictor and turnover intentions as the outcome. What did you find?
2) Run a simple linear regression analysis with role ambiguity as the predictor and turnover intentions as the outcome. What did you find?
3) Run a simple linear regression analysis with interpersonal conflict as the predictor and burnout as the outcome. What did you find?
4) Run a simple linear regression analysis with role ambiguity as the predictor and burnout as the outcome. What did you find?
5) How would you explain and communicate these findings to someone in the organization who does not know anything about data analytics?

Answer 1

Simple linear regression analyses would indicate the relationships between interpersonal conflict and role ambiguity as predictors for turnover intentions and burnout. Significant positive results would suggest that higher conflict and role ambiguity are associated with increased turnover intentions and higher burnout levels. Communicating these findings in a non-technical manner involves focusing on the direction and impact of these workplace factors on employee outcomes.

Step-by-step explanation:

To explain the findings from the various simple linear regression analyses performed using the dataset provided, we will imagine the outcomes as if they were done with the provided variables (interpersonal conflict, role ambiguity, turnover intentions, burnout).

1) When interpersonal conflict is used as a predictor for turnover intentions, the analysis would have likely shown how much turnover intentions change with an increase in interpersonal conflict. If this number is positive and significant, it suggests that as interpersonal conflict increases, so do the intentions of employees to leave the organization.

2) Using role ambiguity as a predictor for turnover intentions would similarly show the impact of unclear job roles on the likelihood of employees considering leaving. A significant positive outcome would indicate that unclear roles are potentially driving employees away.

3) A regression with interpersonal conflict predicting burnout would reveal how conflict among coworkers might contribute to employee burnout. A significant positive result implies that more conflict is associated with higher levels of burnout.

4) Lastly, using role ambiguity as a predictor for burnout would inform us about the relationship between unclear job roles and the level of burnout among employees. Again, a positive and significant finding would suggest that not knowing one's job responsibilities clearly is related to higher burnout.

5) To communicate these findings to someone without a data analytics background, it would be best to highlight the direction and impact of these workplace factors on employees' intentions to leave and their burnout levels rather than focusing on the statistical details. For example, you could say, "Our analysis has found that employees tend to think more about leaving and feel more burned out when they experience more conflicts with coworkers or when they are unclear about what their job expects of them."