Matlab Statistical Analysis Support
Budget: $1,500 – $3,000 USD
I’m deep into a data-heavy project in Matlab and need an extra set of expert hands to sharpen the statistical side. The core of the job is to work inside Matlab (R2022b or later) using the Statistics and Machine Learning Toolbox to run and refine:
• Multiple and simple regression models, including checks for assumptions and goodness-of-fit.
• Classical hypothesis tests (t, χ², Mann-Whitney, etc.) with clear interpretation of p-values and effect sizes.
• One-way and, if needed, two-way ANOVA with post-hoc comparisons and visual summaries.
You’ll be working directly in my existing scripts, so clean, well-commented code is essential. I’ll share sample data and the current .m files; your task is to optimise the workflow, add the right library calls, and return reproducible results together with succinct notes explaining what was done and why.
Acceptance criteria
1. All provided datasets run end-to-end without errors on a fresh Matlab install.
2. Functions are vectorised where reasonable and follow Matlab style guidelines.
3. Outputs include both numeric tables and publication-ready plots.
4. A short README outlines assumptions, steps, and how to extend the analysis.
If that sounds like your wheelhouse, let’s talk specifics and get this analysis tightened up.
• Multiple and simple regression models, including checks for assumptions and goodness-of-fit.
• Classical hypothesis tests (t, χ², Mann-Whitney, etc.) with clear interpretation of p-values and effect sizes.
• One-way and, if needed, two-way ANOVA with post-hoc comparisons and visual summaries.
You’ll be working directly in my existing scripts, so clean, well-commented code is essential. I’ll share sample data and the current .m files; your task is to optimise the workflow, add the right library calls, and return reproducible results together with succinct notes explaining what was done and why.
Acceptance criteria
1. All provided datasets run end-to-end without errors on a fresh Matlab install.
2. Functions are vectorised where reasonable and follow Matlab style guidelines.
3. Outputs include both numeric tables and publication-ready plots.
4. A short README outlines assumptions, steps, and how to extend the analysis.
If that sounds like your wheelhouse, let’s talk specifics and get this analysis tightened up.