Understand team effectiveness (Project Aristotle)
https://rework.withgoogle.com/intl/en/guides/understand-team-effectiveness
Method
"Using over 35 different statistical models on hundreds of variables, they sought to identify factors" meeting three criteria, with data from "hundreds of double-blind interviews with leaders" plus "over 250 items from the annual employee engagement survey and gDNA."
Population
"180 teams to study (115 project teams in engineering and 65 pods in sales)"
What it does not show
No peer-reviewed paper describing the methodology, raw data or effect sizes has ever been published, so the 35-model search cannot be audited for multiple comparisons or selection effects. Correlational and single-company; it establishes no causality and did not discover the construct — it re-found with proprietary items a relationship already established in 1999 with a transparent published method. The page itself concedes “every suggested measure could be inherently flawed.” It is routinely cited as if it proved psychological safety causes performance. It does not.
Google People Analytics / re:Work
Of the team-dynamics factors tested internally, psychological safety was the one most consistently associated with the four effectiveness measures used, ahead of composition variables like seniority, personality or team size.
Tier III: Single-organisation internal people-analytics report over 180 real teams with quantitative survey and outcome data — real numbers from one engineering report. Not peer reviewed, publishes no raw data or statistical tables, and describes a large multiple-comparisons search that cannot be audited.