powered by
Simulates (partial) rank data for multiple groups together with object variables.
data_sim(m, M, n, p, K, delta, eta)
A list consisting of \(K\) matrices with each matrix containing (partial) rankings across \(n\) observations for group \(k\).
A \(M \times p\) matrix containing the values for the \(p\) objects variables across the \(M\) objects.
A \(p \times K\) matrix containing the true value of \(\beta\), which was used to generate \(y\).
Length of the partial ranking for each observation.
Total number of objects.
Number of observations (rankers) per group.
Number of object variables.
Number of groups.
Approximate fraction of different coefficients across the \(\beta^{(k)}\).
Approximate fraction of sparse coefficients in \(\beta^{(k)}\) for all \(k\).
Sjoerd Hermes Maintainer: Sjoerd Hermes sjoerd.hermes@wur.nl
1. Hermes, S., van Heerwaarden, J., and Behrouzi, P. (2024). Joint Learning from Heterogeneous Rank Data. arXiv preprint, arXiv:2407.10846
data_sim(3, 10, 50, 5, 2, 0.25, 0.25)
Run the code above in your browser using DataLab