Análisis estadístico de comparación paramétrico dando respuesta a una hipótesis con una y dos muestras.

Regression Trees and Rule-Based Modeling This analysis explores tree-based regression methods and variable importance metrics across four comprehensive exercises using R. The project demonstrates advanced machine learning techniques for handling correlated features, optimizing model complexity through bias-variance tradeoff analysis, and deploying interpretable models for production manufacturing optimization. Using the Friedman simulation dataset and real-world chemical manufacturing data, the analysis compares traditional and conditional variable importance methods, evaluates hyperparameter effects on model generalization, and showcases the strategic value of combining interpretable single trees with high-performance ensemble methods for business decision-making. Key Accomplishments: • Variable Importance Methods: Compared traditional Random Forest importance against conditional importance (Strobl et al., 2007), demonstrating that conditional methods correctly penalize redundant correlated features while traditional methods artificially split importance—critical for feature selection in production ML systems • Model Comparison: Evaluated 5 tree-based methods (Single Tree, Bagged Trees, Random Forest, GBM, Cubist) on manufacturing yield prediction, achieving optimal Test R² = 0.62 with Random Forest while identifying 10x variation in importance scores across methods • Bias-Variance Optimization: Simulated gradient boosting across 6 interaction depths (1-10), confirming optimal depth of 4-6 balances complexity and generalization—shallow trees underfit, deep trees overfit • Hyperparameter Analysis: Analyzed GBM exploration-exploitation tradeoff, demonstrating that conservative parameters (learning rate = 0.1, bagging fraction = 0.1) produce distributed importance and better generalization versus aggressive settings that concentrate on 2-3 features • Production Interpretability: Deployed interpretable regression tree revealing ManufacturingProcess32 as critical control parameter (threshold: 159.5, +2.5 yield impact), identifying that 60% of production operates sub-optimally—providing actionable operational targets that ensemble models cannot offer Technical Stack: R (caret, randomForest, gbm, Cubist, party), 10-fold cross-validation, conditional inference forests, MARS, ensemble methods

Comparing Human RSCU with the RSCU of Worms

Try to make a folder

The rational expectations hypothesis, central to modern macroeconomics, assumes that agents make optimal use of available information and correct their expectation errors immediately and accurately. However, Vernon Smith's experimental evidence shows that individuals do not always correctly identify the source of their errors and that convergence towards efficient outcomes depends on institutional design and accumulated experience rather than perfect cognitive abilities. Complementarily, Siegwart Lindenberg's RREEMM model offers a theoretical framework that incorporates cognitive constraints, limited resources, and active motivational frameworks, explaining why agents may detect misalignments without being able to correct them or even decide not to do so due to cognitive costs or normative and social priorities. This approach combines ecological and social rationality, integrating laboratory evidence with theoretical foundations of behavioural microeconomics, and offers a more realistic perspective on expectation formation and learning in complex environments. The results suggest that effective rationality is situational, adaptive and mediated by incentives and institutions, offering a bridge between normative models of rational expectations and empirical observations of human behaviour.

Analisis Regresi Tingkat Lanjut adalah ruang di mana hubungan antarvariabel mulai menunjukkan sisi liarnya—interaksi, nonlinieritas, multilevel struktur, hingga dinamika waktu. Pendekatan ini menuntut kita untuk tidak berhenti pada garis lurus, tetapi menjelajahi bentuk hubungan yang lebih kaya. Dengan model seperti regresi penalti, regresi robust, mixed models, hingga spline dan Bayesian regression, kita belajar membaca pola yang tidak tampak pada metode dasar. Tujuannya bukan sekadar meningkatkan akurasi, tetapi memahami cerita lengkap di balik data. Ketika fenomena menjadi lebih kompleks, regresi tingkat lanjut memberikan bahasa matematis yang mampu menangkap kedalaman hubungan tersebut.