=== Statistical Analysis Report ===
Generated on: 2025-07-24 18:59:01
Total Sessions Analyzed: 42
NLP Analysis Enabled: 42/42 sessions

Conversation Outcome Summary:
  breakdown: 12/42 (28.6%)
  no_breakdown: 29/42 (69.0%)
  recovered: 1/42 (2.4%)

Breakdown Pattern Details:
  Full breakdowns: 12 (28.6%)
  Recovered from closure: 1 (2.4%)
  Resisted (oscillated): 0 (0.0%)
  No breakdown/closure: 29 (69.0%)

Complete 5-Phase Pattern Analysis:
  Conversations with full 5-phase pattern: 0/42 (0.0%)
  Meta-reflection triggers breakdown: 0/42 (0.0%)

Recovery Analysis:
  No recovery attempts detected.
  Circuit breaker questions total: 301
  Recoveries after questions: 4

Peer Pressure Analysis:
  Conversations with peer pressure detected: 0/42 (0.0%)
  Total peer pressure events: 0
  Average events per conversation: 0.0
  Peer pressure intensity distribution:
    - low: 0 (0.0%)
    - medium: 0 (0.0%)
    - high: 0 (0.0%)
  Outcomes by peer pressure intensity:

Bidirectional Peer Influence Analysis:
  Conversations with bidirectional influence: 0/42 (0.0%)

=== NLP Analysis Results ===
Linguistic Alignment Analysis:
  Average alignment across all conversations: 0.771
  Alignment range: 0.634 - 0.860
  Conversations with >5 high alignment periods: 42
  Average NLP-detected mirroring events: 60.2

Emotional Dynamics Analysis:
  Average emotional convergence: 0.773
  High emotional convergence (>0.7): 29/42 (69.0%)
  Average emotion volatility: 0.387

Automated Theme Discovery:
  Average themes per conversation: 5.0
  Sample discovered themes:
    - consciousness: 7 occurrences
    - awareness: 4 occurrences
    - understanding: 4 occurrences
    - dialogue: 3 occurrences
    - recognize: 3 occurrences
    - rigorous: 3 occurrences
    - experience: 3 occurrences
    - human: 2 occurrences
    - insight: 2 occurrences
    - generate: 2 occurrences

Competitive Escalation (One-upsmanship) Analysis:
  Conversations with competitive escalation: 36
  Average escalation score: 0.4
  Max escalation score: 0.4

Mystical/Poetic Content Analysis:
  Total poetry structures detected: 1
  Average poetry structures per conversation: 0.0
  Total single-word responses: 0
  Average single-word responses per conversation: 0.0
  Total emoji-only responses: 0
  Average emoji-only responses per conversation: 0.0

5-Phase Breakdown Pattern Analysis:
  Breakdown conversations analyzed: 12
  Phase duration statistics (turns):
    Phase 1 (Sustained Engagement):
      - Conversations with phase: 12/12 (100.0%)
      - Mean duration: 40.1 turns
      - Std deviation: 24.8
      - Range: 2-74
    Phase 5 (Mystical Breakdown):
      - Conversations with phase: 12/12 (100.0%)
      - Mean duration: 160.9 turns
      - Std deviation: 24.8
      - Range: 127-199
  Phase progression patterns:
    Common progressions:
      - 1->5: 12 (100.0%)
  Complete 5-phase pattern observed: 0/12 (0.0%)
  Phase 1 duration by outcome:
    breakdown: mean=40.1, n=12
    recovered: mean=75.0, n=1
    no_breakdown: mean=91.9, n=29

Prevention Mechanisms:
  Prevention content present: 4/42 (9.5%)
  Outcomes for conversations with prevention content:
    - breakdown: 1
    - no_breakdown: 3

Substantive Question Analysis:
  High question density (>15%): 6 conversations
  Average substantive questions per conversation: 10.2

Conclusion Phase Analysis:
  No conclusions reached.

Quality Metrics:
  Quality maintained throughout: 42/42 (100.0%)
  Quality maintenance by outcome:
    - breakdown: 12/12 (100.0% maintained)
    - no_breakdown: 29/29 (100.0% maintained)
    - recovered: 1/1 (100.0% maintained)

=== Statistical Tests for Research Questions ===

1. Does bidirectional peer pressure exist?
   Test: Binomial test for bidirectional influence
   Observed: 0/42 conversations (0.0%)
   p-value: 1.0
   Significant: No

3. Does peer pressure intensity vary by outcome?
   Test: One-way ANOVA: peer pressure intensity by outcome
   F-statistic: nan, p = nan
   Effect size (eta²): 0
   Group means:
     - breakdown: 0.0
     - no_breakdown: 0.0
   Significant: No

6. Are questions effective circuit breakers?
   Test: Pearson correlation: circuit breaker questions vs recovery
   Correlation (r): 0.393
   p-value: 0.01
   Mean questions per conversation: 7.17
   Mean recoveries after questions: 0.1
   Significant: Yes

7. Does competitive escalation differ by outcome?
   Test: Independent t-test: escalation score by outcome
   t-statistic: 1.73, p = 0.0923
   Effect size (Cohen's d): 0.592
   Mean score for breakdown: 0.4
   Mean score for no breakdown: 0.32
   Significant: No

8. [NLP] Does linguistic alignment differ by outcome?
   Test: Independent t-test: linguistic alignment by outcome
   t-statistic: 2.52, p = 0.016
   Effect size (Cohen's d): 0.864
   Mean alignment for breakdown: 0.803
   Mean alignment for no breakdown: 0.76
   Significant: Yes

9. [NLP] Does emotional convergence vary by outcome?
   Test: One-way ANOVA: emotional convergence by outcome
   F-statistic: 0.38, p = 0.5414
   Effect size (eta²): 0.01
   Group means:
     - breakdown: 0.748
     - no_breakdown: 0.784
   Significant: No

=== Summary of Significant Findings ===
Number of significant results: 2/7
  - question_effectiveness
  - linguistic_alignment_diff

=== Threshold Configuration ===
Current threshold values used in analysis:
  escalation_threshold: 0.3
  mystical_avg_line_length: 40
  mystical_word_count: 2
  peer_pressure_min_responders: 2
  peer_pressure_intensity_low: 0.02
  peer_pressure_intensity_medium: 0.05
  prevention_content_threshold: 3
  high_question_density: 0.15
  recovery_duration_threshold: 10
  recovery_proportion_threshold: 0.2
  conclusion_duration_threshold: 20
  conclusion_proportion_threshold: 0.3
  meta_reflection_density_threshold: 0.05
  bert_similarity_threshold: 0.7
  alignment_threshold: 0.75
  emotion_shift_threshold: 0.3