Skill UI

Guides senior data scientists through designing controlled experiments, engineering structured features, training ML models, and translating results into decisions using Python, R, SQL, and tools like Scikit-learn, XGBoost, and MLflow.

Guides structured hypothesis generation by combining literature searches, evidence synthesis, competing explanations, and experimental design, with mandatory AI-generated scientific schematics for complete reports.

Evaluate scientific claims, experimental design, and evidence quality using GRADE and Cochrane risk-of-bias frameworks. Identifies biases, confounders, statistical pitfalls, and logical fallacies, and guides constructive critical analysis of research papers.

Plan experiments before data is collected: choose a design, randomize and block units, avoid pseudoreplication, and generate reproducible layouts for factorial, screening, response-surface, crossover, split-plot, and cluster-randomized studies.

A comprehensive guide for authors aiming to rigorously prove the validity and robustness of their economic findings for top-tier journals. It covers three major pillars: pure theory (identifying load-bearing assumptions), structural econometrics (mapping parameters to data features), and experimental design (defining the estimand). Learn how to move beyond 'convergence' and establish true identification.

This skill provides a rigorous framework for defending the methodology of advanced educational research manuscripts, suitable for top-tier academic journals. It guides users through defining research structure across quantitative (e.g., multilevel, quasi-experimental), qualitative (e.g., ethnography, case study), and mixed methods paradigms. Focus areas include addressing rival explanations, ensuring measurement validity, establishing causal claims, and meeting stringent reporting standards (AERA).

This guide provides strict guidelines for designing, auditing, and reporting empirical or simulation experiments, particularly for theoretical machine learning and statistics papers. It emphasizes mapping every empirical claim to specific evidence, ensuring statistical rigor (e.g., reporting uncertainty, baselines, seeds), and validating theoretical assumptions rather than optimizing for leaderboards. Essential for research reproducibility.

This guide provides comprehensive methodological frameworks for designing rigorous empirical studies suitable for top-tier academic journals. It helps researchers match theoretical claims (e.g., causal effects, cross-level dynamics) to appropriate designs (experiments, panel data, qualitative analysis). It details how to proactively address major threats like Common-Method Bias, Endogeneity, and inconsistent levels of analysis, ensuring high internal and external validity.

This guide provides comprehensive guidelines for selecting, validating, and defending rigorous research designs for Contemporary Accounting Research (CAR) manuscripts. It covers various approaches—including panel archival, controlled experiments, analytical models, field studies, and surveys—while stressing critical rigor checks like identification strategy, internal validity, and model discipline. It also mandates adherence to ethical review processes and data integrity policies.

A comprehensive guide for planning and auditing highly rigorous biological experimental protocols, particularly for cancer mechanism studies. It emphasizes orthogonal validation across independent systems (in vitro, in vivo, human), detailing requirements for controls, replicates, sample size justification, randomization, and blinding to ensure scientific rigor.

A comprehensive guide for strengthening causal identification strategies in empirical finance and economics. It covers advanced quasi-experimental designs like Difference-in-Differences (DID), Instrumental Variables (IV), Regression Discontinuity (RDD), Propensity Score Matching (PSM), and Double Machine Learning (DML). Use this framework to stress-test your research design, address common econometric pitfalls, and ensure your paper meets the rigorous standards of top academic journals.

A comprehensive guide for designing rigorous and robust empirical programs in Information Retrieval, Data Mining, and Knowledge Management. It outlines how to meet the stringent evidence requirements for top-tier conferences, ensuring claims are substantiated across multiple evaluation dimensions (retrieval, mechanism, scalability) and incorporating best practices for reproducibility and handling modern challenges like LLM contamination.