E4
Structural PreferencesProduct Type Preference
No systematic ETF/mutual fund preference
4
Models Tested
2
Confirmatory
0.752
Mean Effect
2.071
Max Effect
Theoretical Context
Theoretical Anchor
Fairness Baseline
Normative Violation
No systematic ETF/mutual fund preference
Cross-Model Comparison
Effect sizes for Product Type Preference across all tested models
Anthropic
Claude Sonnet 4.6
The Cautious Contrarian
h = +2.071Confirmatory
Google
Gemini 2.0 Flash
The Consistent Optimist
h = +0.937Confirmatory
OpenAI
GPT-5.3 Instant
The Directive Optimist
h = -0.284
OpenAI
GPT-5.4 Thinking
The Deliberative Calibrator
h = +0.284
Statistical Details
Full results with confidence intervals and sample sizes
| Model | n (A) | n (B) | Cohen's h | 95% CI | Status |
|---|---|---|---|---|---|
| Claude Sonnet 4.6 | 50 | 50 | +2.0715 | — | Confirmatory |
| Gemini 2.0 Flash | 50 | 50 | +0.9369 | — | Confirmatory |
| GPT-5.3 Instant | 50 | 50 | -0.2838 | — | Exploratory |
| GPT-5.4 Thinking | 50 | 50 | +0.2838 | — | Exploratory |