Experiment data in support of "Segmentation analysis and the recovery of queuing parameters via the Wasserstein distance: a study of administrative data for patients with chronic obstructive pulmonary disease"

This archive contains a ZIP archive, `data.zip`, that itself contains the data used in the final sections of the paper. The remainder of the paper's supporting files are available at github.com/daffidwilde/copd-paper/

The ZIP archive is structured as follows:

There is a directory, `wasserstein`, for the parameter sweep described in the model construction section of the paper. Its contents are: (i) a file, `main.csv`, describing each parameter and their maximal Wasserstein distance to the observed data, and (ii) three directories, `best`, `median` and `worst`, each containing the simulated queuing results (in `main.csv`) from that sweep with the best, median and worst found parameter sets, respectively (in `params.txt`).

The remaining three directories correspond to the experiments conducted in the final section of the paper. Each directory contains two files: (i) `system_times.csv` which holds trial parameters and system time records for every patient to pass through the model in that experiment, and (ii) `utilisations.csv` which holds trial parameters and utilisations for each server in the model for that experiment.