Marginal Nested Interactions for Contingency Tables

Cazzaro, Manuela; Colombi, Roberto

doi:10.1080/03610926.2012.685550

Cited by 8 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In model A we have that the innovation in the organization system (3) is independent on the market where the enterprise works (5) given the other variables concerning the innovation and the firm's features (2, 4, 6, 7). On the contrary, in model B we have that the innovation in marketing strategies (4) is independent on the enterprise's size (7) given the other variables concerning the innovation and the firm's features (2,3,5,6). Model C is the union of the independencies in model A and in model B.…”

Section: Application On Real Datamentioning

confidence: 95%

“…Then, we define the classical log-linear parameters on the contingency table I 1,2,3 restricted to (1, 2, 3) and the remaining parameters on the unrestricted contingency table I. Finally, we have to constrain to zero the parameters associated to the statement of independence η 1,2,3 1,2 and η 1,2, 3 1,2,3 .…”

Section: Parametrization For Context Specific Independenciesmentioning

confidence: 99%

“…It is clear (i.e. it is common to all models), that the growth (1) is independent by the innovation in the marketing strategies (4) given by the remaining variables (2,3,5,6,7). In model A we have that the innovation in the organization system (3) is independent on the market where the enterprise works (5) given the other variables concerning the innovation and the firm's features (2, 4, 6, 7).…”

Section: Application On Real Datamentioning

confidence: 99%

“…In this paper we want to improve the main results of these works by dealing with CS independencies concerning subsets of all the considered (also ordinal) variables. At this aim we use the Hierarchical Multinomial Marginal Models (HMMMs), see Bartolucci, Colombi and Forcina, 2007 [1]; Cazzaro and Colombi, 2014 [3]. The need of this parametrization chases the will of consider a model where we want to test simultaneously marginal and conditional independencies.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Context‐specific Independence in Innovation Study

Nicolussi¹,

Cazzaro²

2019

Data Analysis and Applications 2

Self Cite

View full text Add to dashboard Cite

The study of (in)dependence relationships among a set of categorical variables collected in a contingency table is an amply topic. In this work we want to focus on the so called context-specific independence where the conditional independence holds only in a subspace of the outcome space. The main aspects that we introduce concern the definition in the same model of marginal, conditional and context-specific independencies, through the marginal models. Furthermore, we investigate how it is possible to test these context-specific independencies when there are ordinal variables. Finally, we propose a graphical representation of all the considered independencies taking advantages from the chain graph model. We show the results on an application on "The Italian Innovation Survey" of Istat (2012).

show abstract

Section: Application On Real Datamentioning

confidence: 95%

Section: Parametrization For Context Specific Independenciesmentioning

confidence: 99%

Section: Application On Real Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Context‐specific Independence in Innovation Study

Nicolussi¹,

Cazzaro²

2019

Data Analysis and Applications 2

Self Cite

View full text Add to dashboard Cite

show abstract

“…The different categories of the variables that are represented in a contingency table must be exhaustive and mutually exclusive. That is, the set of categories of a categorical variable must be sufficient to classify each and every individual of which the sample population is formed (exhaustivity) [3,18,46]. The Pearson Chi-Square coefficient provides the statistical legitimacy needed to allow the results obtained from the contingency tables to be extrapolated from the population sample being studied.…”

Section: Technique Used To Analyse Information Gathered: Statistical mentioning

confidence: 99%

The social perception of urban transport in the city of Madrid: the application of the Servicescape Model to the bus and underground services

Jalón

Gómez-Ortega

Curiel

2019

Eur. Transp. Res. Rev.

View full text Add to dashboard Cite

Purpose: This paper is a study of the user's perception of urban and suburban transport and was carried out in an attempt to compare the social value of various means of transport. The measurement of social perceptions is carried out with regard to ambient conditions, space, signs, front-line employees and other customers as stakeholders of both public transport services. Thus, this paper aims to identify the reasons for individuals' preferences when choosing one particular means of transport for their daily life. Results: The results show that user perceptions of the underground are slightly better than the perceptions of buses; the results also highlight the decent management of both means of transport in terms of quality air, temperature, space, noise, cleanliness, smell and seating facilities. Some modest improvements are recommended to enhance public transportation service delivery. Conclusions: This approach reflects the gap between the social perception of a service and companies' financial situations. Management policies are necessary to improve the service's social value.

show abstract

Context-Specific Independencies Embedded in Chain Graph Models of Type I

Nicolussi

Cazzaro

2019

Statistical Learning of Complex Data

Self Cite

View full text Add to dashboard Cite

For a set of variables collected in a contingency table, we focus on a particular kind of relationships such as the context-specific independencies. These are conditional independencies that hold for particular values of the conditioning set. Given the advantages of the graphical models, we use them to represent different relationships among the variables, including the context-specific independencies. In particular, we enrich Chain Graph models with labelled arcs. Furthermore, we consider the well-known relationships between Chain Graph models and Hierarchical Multinomial Marginal models and we introduce new constraints on parameters in order to describe the context-specific relationship. Finally, we provide an application to the study of innovation in Italy by comparing two different periods.

show abstract

Marginal Nested Interactions for Contingency Tables

Cited by 8 publications

References 10 publications

Context‐specific Independence in Innovation Study

Context‐specific Independence in Innovation Study

The social perception of urban transport in the city of Madrid: the application of the Servicescape Model to the bus and underground services

Context-Specific Independencies Embedded in Chain Graph Models of Type I

Contact Info

Product

Resources

About