Using Loglinear Model for Discrimination Discovery and Prevention

2016 ◽  
Author(s):  
Yongkai Wu ◽  
Xintao Wu
Keyword(s):  
Loglinear Model ◽  
Discrimination Discovery

scholarly journals Loglinear Model Formation using Hierachial Backward Method

2020 ◽  
Vol 2 (1) ◽  
pp. 28-36
Author(s):  
Siti Fatimah Sihotang ◽  
Zuhri
Keyword(s):  
Linear Model ◽  
Good Method ◽  
General Linear Model ◽  
Loglinear Model ◽  
Complete Model ◽  
The Third ◽  
Several Variables ◽  
Model Formation ◽  
Special Case ◽  
Categorical Scale

The loglinear model is a special case of a general linear model for poissondistributed data. The loglinear model is also a number of models in statistics that are used todetermine dependencies between several variables on a categorical scale. The number ofvariables discussed in this study were three variables. After the variables are investigated,the formation of the loglinear model becomes important because not all the modelinteraction factors that exist in the complete model become significant in the resultingmodel. The formation of the loglinear model in this study uses the Backward Hierarchicalmethod. This research makes loglinear modeling to get the model using the HierarchicalBackward method to choose a good method in making models with existing examples.From the challenging examples that have been done, it is known that the HierarchicalReverse method can model the third iteration or scroll. Then, also use better assessmentmethods about faster workmanship and computer-sponsored assessments that are used moreefficiently through compatibility testing for each model made

Recognizing Submodels of a Loglinear Model

1992 ◽  
pp. 263-267
Author(s):  
F. M. Malvestuto
Keyword(s):  
Loglinear Model

A Quasi-Loglinear Model of Neighborhood Choice

1979 ◽  
pp. 57-82 ◽  
Author(s):  
DAVID SEGAL
Keyword(s):  
Loglinear Model ◽  
Neighborhood Choice

Hierarchical Clustering for Discrimination Discovery: A Top-Down Approach

2019 ◽  
Author(s):  
Neda Nasiriani ◽  
Anna Squicciarini ◽  
Zara Saldanha ◽  
Sanchit Goel ◽  
Nicola Zannone
Keyword(s):  
Hierarchical Clustering ◽  
Top Down ◽  
Discrimination Discovery

Loglinear Model

2005 ◽  
Author(s):  
Alicia L. Carriquiry ◽  
Stephen E. Fienberg
Keyword(s):  
Loglinear Model

Loglinear Model

2013 ◽  
pp. 1144-1144
Keyword(s):  
Loglinear Model

Lognormal Loglinear Model (Basics)

2016 ◽  
pp. 151-155
Author(s):  
Klaus D. Schmidt
Keyword(s):  
Loglinear Model

scholarly journals Aggression towards Referees in Amateur Football in Spain: A Loglinear Approach

2019 ◽  
Vol 18 (3) ◽  
pp. 1-13 ◽  
Author(s):  
Diego Fuente ◽  
Enrique Cantón ◽  
Francisco Montes ◽  
María Ángeles Sanruperto Abella
Keyword(s):  
Aggressive Behavior ◽  
Aggressive Behaviour ◽  
Ad Hoc ◽  
The Other ◽  
Loglinear Model ◽  
The Third ◽  
Youth Football ◽  
Other Hand ◽  
The City

Aggressive behavior towards football referees is becoming increasingly common, and as a result we are getting used to it and coming to see it as an inevitable and intrinsic element of football matches. Spectators, players and coaches are all prone to take this view. This article studies how the types of aggression shown by these three groups towards the referee are related to one another, and how they are perceived by the referee, in amateur football. For this purpose, the phenomenon was assessed, using an ad-hoc form, both by an expert and by the referee, in 119 regional and youth football matches in the city of Valencia and surrounding municipalities. We analysed the data using a loglinear model, which enabled us to establish that from the referee’s perspective pairs of the above-mentioned groups influenced each other regardless of the attitude of the third group. On the other hand, departing from the traditional idea that aggressive behaviour by one of the groups determines the behaviour of the other two, the analysis of the expert’s opinions on the attitudes of the three groups led us to a model in which their respective actions were independent of one another.

Estimation and Hypothesis Testing for the Loglinear Model

1989 ◽  
Vol 33 (3) ◽  
pp. 220-241 ◽  
Author(s):  
Patricia L. Busk ◽  
Leonard A. Marascuilo
Keyword(s):  
Hypothesis Testing ◽  
Confidence Intervals ◽  
Model Building ◽  
Loglinear Model ◽  
Frequency Data ◽  
Interval Estimates ◽  
Main Effect ◽  
Dependent Variables ◽  
Primary Focus ◽  
Post Hoc

In recent years, the loglinear model has been proposed and used for analysing frequency data in multidimensional contingency tables. The primary focus of the literature has been on model building and only secondarily on hypothesis testing and estimation. This paper extends Kennedy's (1988) description by presenting post hoc procedures for statistically evaluating treatment effects, contrasts, and confidence intervals. It illustrates methods for main effect and interaction contrasts and pays special attention to odds ratios and their interval estimates. Procedures are described for treating the variables as interdependent and for the case where there are independent and dependent variables—both ordered and unordered.

Sign in / Sign up

Export Citation Format

Share Document