Quantitative Research Methods in Business and Management Studies: A Critical Review of Empirical Practices

Abstract

Quantitative methods continue to dominate business and management research, yet concerns persist about the rigor and relevance of prevailing empirical practices. This critical literature review (CLR) examines how ritualized reliance on statistical significance testing, linear modeling assumptions, and conventional measurement approaches has limited explanatory depth and reproducibility in contemporary studies. Drawing on a systematic analysis of 50 highly cited articles published between 2016 and 2025, the review identifies three recurring methodological shortcomings: overreliance on p-values, linear bias in complex and dynamic contexts, and persistent measurement challenges in advanced modeling. The review further synthesizes emerging methodological shifts, including Bayesian inference, machine learning (ML), and big data analytics, that seek to address these limitations. Building on this synthesis, the paper proposes a Multi-Dimensional Rigor Framework (MDRF) that reconceptualizes methodological rigor as an integrative construct comprising inferential, modeling, and data rigor. The framework emphasizes alignment between statistical reasoning, analytical modeling, and data characteristics rather than adherence to procedural benchmarks alone. The paper concludes by outlining implications for researchers, journal editors, and practitioners, advocating a shift from symbolic statistical compliance toward substantive, context-sensitive, and predictive quantitative inquiry.