Scholarlink

<p>Time course measurements are used for many applications in biomedical research, ranging from growth curves to drug efficacy testing and high-throughput screening. Statistical methods used to analyze the resulting longitudinal data, such as t-tests or repeated measures ANOVA have limitations when groups are unbalanced, or individual measurements are missing.</p><p>To address these issues we developed biogrowleR (<a href="https://upbri.gitlab.io/biogrowleR/">https://upbri.gitlab.io/biogrowleR/</a>), a workflow to visualize and analyze data based on Frequentist and Bayesian inference combined with hierarchical modeling. By focusing on effect sizes we enhance data interpretation. The workflow further includes a randomization algorithm important to reduce numbers of experimental animals (RRR) and costs. The workflow and R package were designed to be used by researchers with limited experience in R and biostatistics.</p><p>Our open-source R package biogrowleR contains tutorials, pipelines, and helper functions for the analysis of longitudinal data and enables non computational scientists to perform more effective data analysis.</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

biogrowleR: Enhancing Longitudinal Data Analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月3日

查看全文
  • Carlos Ronchi,
  • Giovanna Ambrosini,
  • Flavia Hughes,
  • Renée L. Flaherty,
  • Hazel M. Quinn,
  • Daria Matvienko,
  • Andrea Agnoletto,
  • Cathrin Brisken

摘要

Time course measurements are used for many applications in biomedical research, ranging from growth curves to drug efficacy testing and high-throughput screening. Statistical methods used to analyze the resulting longitudinal data, such as t-tests or repeated measures ANOVA have limitations when groups are unbalanced, or individual measurements are missing.

To address these issues we developed biogrowleR (https://upbri.gitlab.io/biogrowleR/), a workflow to visualize and analyze data based on Frequentist and Bayesian inference combined with hierarchical modeling. By focusing on effect sizes we enhance data interpretation. The workflow further includes a randomization algorithm important to reduce numbers of experimental animals (RRR) and costs. The workflow and R package were designed to be used by researchers with limited experience in R and biostatistics.

Our open-source R package biogrowleR contains tutorials, pipelines, and helper functions for the analysis of longitudinal data and enables non computational scientists to perform more effective data analysis.