The Double-Edged Sword Of Diversity: How Diversity, Conflict, and Psychological Safety Impacts Agile Software Teams: Dataset and Supplementary Materials

This bundle contains supplementary materials for an upcoming academic publication The Double-Edged Sword Of Diversity: How Diversity, Conflict, and Psychological Safety Impacts Agile Software Teams, by Christiaan Verwijs and Daniel Russo. Included in the bundle are the dataset, SPSS syntaxes, and model definitions (AMOS). This replication package is made available by C. Verwijs under a "Creative Commons Attribution Non-Commercial Share-Alike 4.0 International"-license (CC-BY-NC-SA 4.0).

About the dataset

The dataset (SPSS) contains anonymized response data from 1.118 respondents aggregated into 161 Agile software teams that participated from the https://scrumteamsurvey.org. Data was gathered between September 2021, and January 2022. We cleaned the individual response data from careless responses and removed all data that could potentially identify teams, individuals, or their parent organizations. Because we wanted to analyze our measures at the team level, we calculated a team-level mean for each item in the survey. Such aggregation is only justified when at least 10% of the variance exists at the team level (Hair, 2019), which was the case (ICC = 35-45%). No data was missing on the team level.

The dataset contains question labels and answer option definitions. To conform to the privacy statement of [scrumteamsurvey.org](https://scrumteamsurvey.org), the bundle does not include response data from before the team-level aggregation.

About the model definitions

The bundle includes definitions for Structural Equation Models (SEM) for AMOS. We added the iterations of the measurement model, four models used to perform a test for common method bias, and the path model that includes interactions. Indirect effects were calculated with the "Indirect Effects" plugin for AMOS by James Gaskin.

About the SPSS syntaxes

The bundle includes the syntaxes we used to prepare the dataset from the raw import, as well as the syntax we used to generate descriptives. This is mostly there for other researchers to verify our procedure.