Model-Based Clustering With Dissimilarities: A Bayesian Approach

Oh, Man Suk; Raftery, Adrian E.

doi:10.1198/106186007x236127

Cited by 61 publications

(24 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The mclust package in R statistics was used to develop model‐based clustering of IPPA‐R scores ( N = 1,126; Fraley, Raftery, Murphy, & Scrucca, ; R Core Team, ). Model‐based clustering uses finite mixture modeling to determine a set of probability distributions, each probability distribution being a latent class or cluster (Oh & Raftery, ). Mclust applies 10 parameterizations across one to nine possible cluster solutions, and results yielded three optimal solutions as assessed by three fit‐statistics: (a) Bayesian information criterion, (b) integrated completed likelihood, and (c) l = log‐likelihood.…”

Section: Resultsmentioning

confidence: 99%

Inventory of Parent and Peer Attachment–Revised Scores in Adolescents: A Psychometric and Person‐Oriented Study

et al. 2017

View full text Add to dashboard Cite

Objective Identify perceived parental security profiles and examine differences across profiles with regard to self‐esteem and three domains of self‐efficacy (i.e., social, emotional, and academic). Background The Inventory of Parent and Peer Attachment–Revised (IPPA‐R) is an index of the quality of communication, feelings of trust, and degree of alienation that adolescents and young adults perceive in their parental and peer relationships. However, the factor structure of IPPA‐R scores has yet to be examined in adolescents, and no study to date has included a person‐oriented analysis using the assessment tool. Method Confirmatory factor analysis (CFA) and exploratory structural equation modeling (ESEM) were planned to examine the structural validity of IPPA‐R scores in a large sample of adolescents (N = 1,126; 61% male, 12–16 years of age). Model‐based clustering was employed to enumerate perceived parental security profiles, and Cohen's d effect sizes were used to interpret profile differences in outcomes. Results CFA (root mean square error of approximation, RMSEA = .06, comparative fit index, CFI = .90) and ESEM (RMSEA = .04, CFI = .95) substantiated the proposed three‐factor structure for IPPA‐R parent (but not peer) scores. Model‐based clustering led to the identification of five perceived parental security profiles: (a) high security, (b) moderately high security, (c) average security, (d) moderately low security, and (e) low security. Adolescents with high security and low security profiles, respectively, reported the highest and lowest levels of self‐esteem and self‐efficacy (0.48 ≤ Cohen's d ≤ 1.67). Conclusion IPPA‐R parent, but not peer, scores appear to be a valid index of perceived parental security in adolescents. Perceived parental security profiles are strongly associated with self‐concept. Implications A student's self‐confidence in his or her ability to manage emotions and cope with the academic demands of school is explained, in part, by perceived parental security. Therefore, interventions designed to develop feelings of trust and closeness with parents, as well as lines of communication, might result in improvements in how adolescents perceive their emotional and academic aptitude.

show abstract

Section: Resultsmentioning

confidence: 99%

Inventory of Parent and Peer Attachment–Revised Scores in Adolescents: A Psychometric and Person‐Oriented Study

et al. 2017

View full text Add to dashboard Cite

show abstract

“…This can be done by recasting the problem as one of statistical model selection and using Bayesian model selection to solve it. HRT did this for choosing the number of groups in their latent position cluster model, Oh and Raftery (2001) did so for choosing the dimension of the latent space for a related Bayesian multidimensional scaling model, and Oh and Raftery (2007) did this for choosing both the number of groups and the latent space dimension simultaneously in model-based clustering for dissimilarities. This work could be adapted and extended to the latent cluster random effects model.…”

Section: Discussionmentioning

confidence: 99%

Representing degree distributions, clustering, and homophily in social networks with latent cluster random effects models

et al. 2009

View full text Add to dashboard Cite

Social network data often involve transitivity, homophily on observed attributes, clustering, and heterogeneity of actor degrees. We propose a latent cluster random effects model to represent all of these features, and we describe a Bayesian estimation method for it. The model is applicable to both binary and non-binary network data. We illustrate the model using two real datasets. We also apply it to two simulated network datasets with the same, highly skewed, degree distribution, but very different network behavior: one unstructured and the other with transitivity and clustering. Models based on degree distributions, such as scale-free, preferential attachment and power-law models, cannot distinguish between these very different situations, but our model does.

show abstract

“…Thus, fi nite mixture modelling enables marketers to cope with heterogeneity in data by clustering observations and estimating parameters simultaneously, thus avoiding well-known biases that occur when models are evaluated separately. 4 Correspondingly, mixture regression models are prevalent in marketing literature. 5 -8 For example, in a recent study, Andrews et al .…”

Section: Introductionmentioning

confidence: 99%

Market segmentation with mixture regression models: Understanding measures that guide model selection

Sarstedt

2008

J Target Meas Anal Mark

View full text Add to dashboard Cite

Marko Sarstedtis an assistant professor at the Institute for Market-based Management at the Ludwig-Maximilians-University Munich. His research interests include research methodology, especially in the fi elds of fi nite mixture modelling and partial least-squares path analysis. Keywords information criteria , fi nite mixture models , unobserved heterogeneity , mixture regression , FIMIX-PLS, customer satisfactionAbstract Owing to their considerable potential for market segmentation studies, mixture regression models have recently received increasing attention from both academics and practitioners. One fundamental diffi culty with their application is related to the problem of model selection, that is, the choice regarding the number of segments. Retaining the correct number of segments is, however, crucial as many managerial decisions depend on this decision. Since the proper number of segments is unknown in real-world applications, a thorough understanding of measures that guide the model selection decision is of fundamental importance. Based on a simulation study, this paper addresses the issue by evaluating how the interaction of the most important infl uencing factors for the measures ' success -sample and segment size -affects the performance of four of the most widely used criteria for assessing the correct number of segments in mixture regression models. For the fi rst time, the quality of these criteria is evaluated with regard to a wide spectrum of possible constellations. Furthermore, relative and absolute performances are analysed in respect of outside criteria. Recommendations on criterion selection are thereafter deduced from the results when a certain sample size is given. These recommendations also help to establish the sample size that is needed in order to guarantee an accurate decision based on a specifi c criterion. An application based on customer satisfaction data illustrates the relevance of the fi ndings. In conclusion, theoretical and managerial implications are provided.

show abstract

Model-Based Clustering With Dissimilarities: A Bayesian Approach

Cited by 61 publications

References 39 publications

Inventory of Parent and Peer Attachment–Revised Scores in Adolescents: A Psychometric and Person‐Oriented Study

Inventory of Parent and Peer Attachment–Revised Scores in Adolescents: A Psychometric and Person‐Oriented Study

Representing degree distributions, clustering, and homophily in social networks with latent cluster random effects models

Market segmentation with mixture regression models: Understanding measures that guide model selection

Contact Info

Product

Resources

About