[Forum SIS] Seminario Prof. Gerhard Tut - Università di Brescia - 1° ottobre 2018

[Marica Manisera]

Lunedì 1° ottobre 2018, alle ore 11.30

Prof. Gerhard Tutz 
Professor Emeritus of Statistics 
Ludwig-Maximilians-University 
Munich, Germany 

terrà un seminario dal titolo:

Explaining Success in Sports Competitions:
Paired Comparison Methods with Explanatory Variables
 
presso il Dipartimento di Economia e Management dell’Università degli Studi di Brescia
Sala della Biblioteca, sede di San Faustino, via San Faustino 74/b

Iniziativa svolta nell'ambito delle attività del Big&Open Data Innovation Laboratory (BODaI-Lab) e 
del Data Methods and Systems Statistical Laboratory (DMS StatLab) e finanziata dal
Fondo di Ateneo per Attività a Carattere Internazionale
 
Abstract
In paired comparison models, the inclusion of covariates is a tool to explain the dominance of one of the teams
or players in a competition. There are three different types of covariates that can occur in paired comparisons,
 the covariates can either vary over the matches (subjects), the teams (objects) or both. A general framework to 
include covariate effects into Bradley-Terry models is presented. For each type of covariate, appropriate penalty
 terms that allow for sparser models and therefore easier interpretation are proposed. The whole framework is 
implemented in the R-package. The approach is illustrated by using data from the German Bundesliga season 
2015/16. The objective is to identify the on-field variables that are connected to the sportive success or failure 
of the single teams. The extended Bradley-Terry model that is proposed uses an ordinal response and (possibly
 team-specific) home effects. It is able to take into account on-field covariates and, therefore, allows for 
match-specific abilities of the teams depending on the values of the on-field covariates.

Tutti gli interessati sono cordialmente invitati a partecipare. Il seminario è gratuito;
per questioni organizzative si pregano tutti coloro che intendono partecipare ad inviare
un'email a marica.manisera a unibs.it <mailto:marica.manisera a unibs.it>

-- 


Informativa sulla Privacy: http://www.unibs.it/node/8155 
<http://www.unibs.it/node/8155>
-------------- parte successiva --------------
Un allegato HTML è stato rimosso...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20180914/95aef4a3/attachment.html>