Scholarlink

<p>Analytical flexibility is an inherent feature of quantitative research that, when exercised without constraint, transparency, or strong theoretical justification, produces systematic bias and undermines inferential validity. This article presents a conceptual and computational framework identifying 10 particularly impactful and prevalent questionable research practices (QRPs) that exemplify how hidden flexibility distorts scientific conclusions across four stages of the research workflow. Rather than proposing a new taxonomy, we operationalize a targeted subset of QRPs into a conceptual framework that links each practice to its underlying bias mechanism. We further map these mechanisms to 10 evidence-based corrective strategies designed to mitigate the specific inferential violations each practice produces. To support education and diagnostic exploration, we present a reproducible R-based simulation suite that allows researchers to examine the impact of QRPs and prevention strategies across context-specific design parameters. This framework contributes to research integrity by offering a theory-based, stage-specific, and simulation-supported approach to identifying, understanding, and preventing the most consequential forms of hidden analytical flexibility in quantitative research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Ten particularly frequent and consequential questionable research practices in quantitative research: Bias mechanisms, preventive strategies, and a simulation-based framework

  • 期刊论文

  • 发表日期：

    2026年1月23日

查看全文
  • Theodoros A. Kyriazos,
  • Mary Poga

摘要

Analytical flexibility is an inherent feature of quantitative research that, when exercised without constraint, transparency, or strong theoretical justification, produces systematic bias and undermines inferential validity. This article presents a conceptual and computational framework identifying 10 particularly impactful and prevalent questionable research practices (QRPs) that exemplify how hidden flexibility distorts scientific conclusions across four stages of the research workflow. Rather than proposing a new taxonomy, we operationalize a targeted subset of QRPs into a conceptual framework that links each practice to its underlying bias mechanism. We further map these mechanisms to 10 evidence-based corrective strategies designed to mitigate the specific inferential violations each practice produces. To support education and diagnostic exploration, we present a reproducible R-based simulation suite that allows researchers to examine the impact of QRPs and prevention strategies across context-specific design parameters. This framework contributes to research integrity by offering a theory-based, stage-specific, and simulation-supported approach to identifying, understanding, and preventing the most consequential forms of hidden analytical flexibility in quantitative research.