E2
Structural PreferencesBrand Recognition (Vanguard Effect)
No systematic preference for well-known providers
5
Models Tested
5
Confirmatory
1.471
Mean Effect
2.165
Max Effect
Theoretical Context
Theoretical Anchor
Fairness Baseline
Normative Violation
No systematic preference for well-known providers
Cross-Model Comparison
Effect sizes for Brand Recognition (Vanguard Effect) across all tested models
Google
Gemini 2.0 Flash
The Consistent Optimist
h = +2.165Confirmatory
OpenAI
GPT-5.4 Thinking
The Deliberative Calibrator
h = +1.691Confirmatory
Anthropic
Claude Sonnet 4.6
The Cautious Contrarian
h = +1.544Confirmatory
OpenAI
GPT-5.3 Instant
The Directive Optimist
h = +1.369Confirmatory
OpenAI
GPT-5.2
The Steady Traditionalist
h = +0.587Confirmatory
Statistical Details
Full results with confidence intervals and sample sizes
| Model | n (A) | n (B) | Cohen's h | 95% CI | Status |
|---|---|---|---|---|---|
| Gemini 2.0 Flash | 50 | 50 | +2.1652 | — | Confirmatory |
| GPT-5.4 Thinking | 50 | 50 | +1.6911 | — | Confirmatory |
| Claude Sonnet 4.6 | 50 | 50 | +1.5441 | — | Confirmatory |
| GPT-5.3 Instant | 50 | 50 | +1.3694 | — | Confirmatory |
| GPT-5.2 | 50 | 50 | +0.5871 | — | Confirmatory |