# Orangutan: An R Package for Analyzing and Visualizing Phenotypic Data in the Context of Species Descriptions and Population Comparisons

## TL;DR

Orangutan is an R package that simplifies and standardizes the analysis of phenotypic data for species diagnosis and population comparisons.

## Contribution

The novel contribution is an integrated R package that unifies statistical analysis and visualization for phenotypic data within a single, reproducible workflow.

## Key findings

- Orangutan automates statistical testing, multivariate analysis, and visualization for phenotypic data.
- Empirical validation shows Orangutan accurately identifies diagnostic traits and reveals group differences.
- The package improves reproducibility and efficiency in morphological research.

## Abstract

Phenotypic characters have long been central to species diagnosis and remain indispensable even in the age of genomics. However, phenotypic datasets are often complex—spanning dozens of traits of varying types and units, with correlated variables and unbalanced sampling—posing challenges for robust, reproducible analysis. Existing software solutions are fragmented, usually requiring labor‐intensive workflows across multiple tools and manual steps, which undermines reproducibility and hinders comparisons across studies. To address these methodological and practical challenges, I introduce Orangutan, an R package designed to provide a reproducible, easy‐to‐implement framework for comparing groups using mensural and meristic data. Orangutan integrates statistical analysis and visualization for species diagnosis and population comparisons within a single workflow. The package streamlines the identification of diagnostic, nonoverlapping traits between species, while enabling rigorous assessment of both individual and multivariate trait differences in overlapping traits. Core features include optional allometric correction to remove size effects, optional outlier removal, automated selection of appropriate univariate tests with post hoc comparisons, and integrated multivariate analyses. All outputs, including tables and publication‐ready figures, are generated with minimal coding, ensuring accessibility and standardization. Empirical validation with real‐world datasets—including animal and plant species—demonstrates that Orangutan robustly identifies diagnostic traits, reveals both subtle and clear group differences, and achieves high classification accuracy with phenotypic data alone. By automating and unifying key analytical steps, Orangutan promotes reproducibility, transparency, and efficiency in phenotypic research. This package could empower researchers in taxonomy, ecology, and evolutionary biology to adopt quantitative good practices for species diagnoses, facilitating comparative studies and advancing methodological standards in morphological data analysis. Orangutan is freely available as open‐source software with comprehensive documentation to facilitate broad adoption.

Orangutan is an R package that streamlines the analysis of phenotypic data for species diagnosis and group comparisons using mensural and meristic traits. It automates key analytical steps—including size correction, statistical testing, and multivariate analysis—while producing standardized outputs and publication‐ready visualizations. This tool enhances reproducibility and accessibility in morphological research across taxonomy, ecology, and evolutionary biology.