R Distribution Fitting & Plots
Budget: $15 – $25 AUD
I have seven ready-to-use datasets that must each be fitted to two candidate distributions: Gamma and LogNormal. Using R, please run the fits, calculate the full set of goodness-of-fit statistics (AIC, BIC, KS, AD, CvM) and produce four kinds of diagnostic graphics for every dataset / distribution pair:
• PDF overlay on the empirical density
• CDF overlay on the empirical CDF
• P-P plot
• Q-Q plot
The plots should be delivered as high-resolution PDF files and must carry clear axis labels, legends, and concise annotations so that the reader can see which distribution is which and how well it performs. All file names should be systematic and self-explanatory.
What I expect to receive
1. A clean, well-commented R script that reproduces the entire workflow on my machine, indicating any CRAN or tidyverse packages required.
2. A folder containing the annotated PDF plots, one page per dataset.
3. A summary table (CSV) with the goodness-of-fit numbers for easy comparison across datasets and distributions.
Acceptance criteria
• Script runs end-to-end on R ≥4.0 without manual intervention.
• All seven datasets processed; no hard-coded paths.
• Every plot type present, legible and properly labelled.
• Reported statistics match those generated by the script.
A more detailed specification is ready to share once you confirm interest; it clarifies variable names and required annotation wording.
• PDF overlay on the empirical density
• CDF overlay on the empirical CDF
• P-P plot
• Q-Q plot
The plots should be delivered as high-resolution PDF files and must carry clear axis labels, legends, and concise annotations so that the reader can see which distribution is which and how well it performs. All file names should be systematic and self-explanatory.
What I expect to receive
1. A clean, well-commented R script that reproduces the entire workflow on my machine, indicating any CRAN or tidyverse packages required.
2. A folder containing the annotated PDF plots, one page per dataset.
3. A summary table (CSV) with the goodness-of-fit numbers for easy comparison across datasets and distributions.
Acceptance criteria
• Script runs end-to-end on R ≥4.0 without manual intervention.
• All seven datasets processed; no hard-coded paths.
• Every plot type present, legible and properly labelled.
• Reported statistics match those generated by the script.
A more detailed specification is ready to share once you confirm interest; it clarifies variable names and required annotation wording.