Reseña

AI and modern data‑science methods extend traditional quantitative research by: scaling to high‑dimensional and multimodal data, offering flexible nonlinear predictive models, enabling automated feature extraction from text/voice/image, and embedding uncertainty quantification and prior knowledge via Bayesian methods. Bayesian approaches, in particular, shift emphasis from dichotomous hypothesis testing to estimation with full posterior uncertainty and principled model comparison, enhancing the “New Statistics” goals of estimation, meta‑analysis and power reasoning. Integrating AI and data‑science methods into quantitative research methodology delivers scalability, richer feature extraction, and powerful predictive tools; coupling these with Bayesian frameworks provides principled uncertainty quantification, model comparison and the ability to incorporate domain knowledge key for robust inference and reproducibility. For domains such as education and the humanities, rigorous interpretability, triangulation with qualitative evidence, and careful ethical scrutiny are essential to preserve meaning and social value of results.