Enhanced Sensitivity Model

Primary Model with Conservative Sampling and Smooth Predictions

Generated: 2026-03-02

🎯 Primary Model Status

This enhanced sensitivity model is now the primary model for all analysis. It features conservative sampling (adapt_delta=0.99) for reliable inference and smooth continuous predictions.

📊 Comprehensive Report

Detailed analysis with parameter estimates, variance decomposition, and convergence diagnostics.

View Report

🔬 Technical Details

Mathematical foundations, Stan implementation, and sampling configuration.

View Details

📈 Predictions

Smooth continuous predictions with 95% credible intervals and component breakdown.

View Predictions

Key Features

Conservative Sampling: adapt_delta=0.99 reduces divergent transitions
Deep Exploration: max_treedepth=12 for complex posterior landscapes
Smooth Predictions: 200-point dense grid for continuous curves
Excellent Convergence: All parameters R-hat ≤ 1.1
Component Breakdown: Visual decomposition of model contributions
Uncertainty Quantification: Proper credible intervals from conservative sampling

Technical Specifications

Parameter	Value	Purpose
adapt_delta	0.99	Conservative sampling, reduces divergent transitions
max_treedepth	12	Deeper exploration of posterior
warmup iterations	1000	Extended warmup for better adaptation
sampling iterations	1000	Sufficient samples for reliable inference
chains	4	Multiple chains for convergence diagnostics
prediction points	200	Dense grid for smooth predictions

Key Findings

GP Constraint Test

alpha_gp = 0.7601 exceeds the 0.5 constraint, indicating the Gaussian Process needs more flexibility to capture trends.

Weight Effects

Expected physiological patterns detected: negative aerobic effects, positive long-term strength effects.

Variance Decomposition

83% of variance from GP trends, ~1% from fitness effects, 2.8% from daily cycles.

Running the Model

# Run enhanced sensitivity model
uv run python run_enhanced_sensitivity.py

# Check results
uv run python check_enhanced_model.py

# Generate report
uv run python create_enhanced_sensitivity_report.py

Enhanced Sensitivity Model: Primary Analysis

Generated on 2026-03-02 | Model: weight_state_space_four_fitness_sensitivity_pred.stan