Skill UI

This skill builds and executes automated pipelines to clean, validate, and transform data for machine learning, covering ETL workflows, error handling, and quality reporting so Claude can deliver analysis-ready datasets.

This guide provides strict guidelines for compiling and formatting scholarly exhibits (tables, figures, and appendices) for top-tier accounting journals, such as CAR. It ensures compliance with academic style guides, requiring variable definitions, clustered standard errors, and self-contained presentation so that the results are immediately interpretable by reviewers. It is crucial for transforming raw analysis output into submission-ready academic materials.

This skill provides rigorous standards and best practices for running and reporting analyses within Comparative Political Studies (CPS). It addresses common pitfalls in cross-national data, such as measurement error, few clusters, and spurious correlation, ensuring the resulting research is transparent, robust, and replication-ready for academic review.

This skill provides comprehensive guidance for authors submitting Information Retrieval (IR) manuscripts to the European Conference on Information Retrieval (ECIR). It assists in strategically positioning the work by defining scope fit, structuring the evidence (e.g., baselines, error analysis), aligning with the rigorous standards of the European IR community, and guiding the differentiation of the contribution against similar top-tier venues like SIGIR or CIKM. Essential tool for pre-submission refinement.

A comprehensive framework for conducting rigorous empirical data analysis required for top-tier academic journals. It guides users through building transparent archival samples, specifying appropriate panel data estimators (like firm/year fixed effects), ensuring correct standard error clustering, and executing sophisticated identification strategies (e.g., Difference-in-Differences, Instrumental Variables). Essential for addressing endogeneity and passing deep reviewer scrutiny.

A comprehensive guide for executing and reporting the full empirical robustness battery required by top accounting journals. It covers modern econometric techniques like standard error clustering, advanced Difference-in-Differences (DiD) estimators for staggered timing, Regression Discontinuity (RD) diagnostics, and Instrumental Variables (IV/2SLS). The guide emphasizes rigorous validation of accounting constructs, executing multiple sensitivity tests, and ensuring full data-and-code reproducibility for academic publication.

A comprehensive guide for conducting advanced empirical analysis required for top-tier finance journals. It covers assembling multi-source firm panels (Compustat, CRSP, etc.), constructing complex corporate finance variables, implementing advanced econometric techniques (high-dimensional fixed effects, clustered errors), and systematically planning robustness checks and replication strategies.

A comprehensive guide for conducting rigorous empirical analysis on field and survey data in low- and middle-income settings. It covers advanced methods for handling clustered sampling, measurement error, differential attrition, and treatment-effect heterogeneity, ensuring results meet the high standards of reproducibility and robustness required by leading developmental economics journals.

This comprehensive guide assists in executing and documenting rigorous empirical finance research, tailored for top-tier journals like JFQA. It covers the entire pipeline, including complex financial data construction (CRSP, Compustat), advanced data cleaning (winsorizing, outlier handling), and sophisticated econometrics (fixed effects, clustered standard errors, Fama-MacBeth). The core focus is achieving absolute reproducibility, ensuring that all filters, robustness checks, and analytical steps are meticulously documented for archival and peer review.

A comprehensive guide for conducting and reporting rigorous statistical analysis for academic marketing manuscripts, particularly tailored for the Journal of Marketing (JM) standards. It covers selecting appropriate estimators for various designs (e.g., panel, choice, field experiments), managing identification, testing robustness, and adhering to the mandatory reporting of p-values, standard errors, and managerial effect sizes. Also covers data replication and advanced econometric techniques.

A comprehensive guide for researchers conducting advanced data analysis and reporting for top marketing journals. It details selecting the appropriate econometric estimator (e.g., ANOVA, DiD, IV, mediation models) based on the study design (experimental, observational, panel). It emphasizes meeting rigorous journal mandates, including exact p-values, standard errors, and effect sizes, and linking statistical findings to practical managerial claims.

A comprehensive guide for conducting reproducible empirical analysis in labor economics, adhering to high academic standards (e.g., JOLE norms). It covers essential steps including sample construction from CPS/ACS/registers, advanced wage decompositions (Oaxaca/RIF), proper handling of standard errors, and robust sensitivity checks to ensure results are fully replicable.