Open Conference Systems, 50th Scientific meeting of the Italian Statistical Society

Font Size: 
Constrained Extended Plackett-Luce model for the analysis of preference rankings
Cristina Mollica, Luca Tardella

Last modified: 2018-05-25


Choice behavior and preferences typically involve numerous and subjec- tive aspects that are difficult to be identified and quantified. For this reason, their ex- ploration is frequently conducted through the collection of ordinal evidence in the form of ranking data. Multistage ranking models, including the popular Plackett- Luce distribution (PL), rely on the assumption that the ranking process is performed sequentially, by assigning the positions from the top to the bottom one (forward order). A recent contribution to the ranking literature relaxed this assumption with the addition of the discrete reference order parameter, yielding the novel Extended Plackett-Luce model (EPL). In this work, we introduce the EPL with order con- straints on the reference order parameter and a novel diagnostic tool to assess the adequacy of the EPL parametric specification. The usefulness of the proposal is illustrated with an application to a real dataset.


  1. Alvo M, Yu PL (2014). Statistical methods for ranking data. Springer.

  2. Critchlow DE, Fligner MA, Verducci JS (1991). “Probability models on rankings.†Journal of

    Mathematical Psychology, 35(3), 294–318.

  3. Marden JI (1995). Analyzing and modeling rank data, volume 64 of Monographs on Statistics

    and Applied Probability. Chapman & Hall. ISBN 0-412-99521-2.

  4. Mollica C, Tardella L (2014). “Epitope profiling via mixture modeling of ranked data.†Statis-

    tics in Medicine, 33(21), 3738–3758. ISSN 0277-6715. doi:10.1002/sim.6224.

  5. Mollica C, Tardella L (2017). “Bayesian mixture of Plackett-Luce models for partially ranked

    data.†Psychometrika, 82(2), 442–458. ISSN 0033-3123. doi:10.1007/s11336-016-9530-0.

  6. Mollica C, Tardella L (2018). “Algorithms and diagnostics for the analysis of preference rank- ings with the Extended Plackett-Luce model.†arXiv preprint:

Full Text: PDF