In everyday life ranking and classification are basic cognitive skills that people use in order to gradeeverything that they experience. Grouping and ordering a set of elements is considered easy andcommunicative; thus, rankings of sport‐teams, universities, countries and so on are often observed. Aparticular case of ranking data is represented by preference data, where individuals show theirpreferences over a set of items. When individuals specific characteristics are available, an important issueconcerns the identification of the profiles of respondents (or judges) giving the same/similar rankings. Inorder to incorporate respondent‐specific covariates distance‐based decision tree models (D'Ambrosio2007, Lee and Yu 2010, Yu et al. 2010, D’Ambrosio and Heiser, 2016, Plaia and Sciandra, 2017) have beenrecently proposed. Actually, it can happen that one or some of the k items is more important than others,or, similarly, the top of the ordering can deserve more attention than the bottom. In these situations,changing the rank of very important items or changing the top of the ranking require different“weighting”. In this contribution we want analyze the role of element and positional information (Kumarand Vassilvitskii 2010) when some distance measures for rankings are evaluated. Several weightingstructures will be assumed for both positional and item weights, and we aim at identifying someparticular behavior in the distance measures used. Analysis will be carried out both by simulation and byapplication to real dataset, especially in the framework of tree‐based methods for rank data.
|Numero di pagine||1|
|Stato di pubblicazione||Published - 2018|