Vai ai contenuti. | Spostati sulla navigazione | Spostati sulla ricerca | Vai al menu | Contatti | Accessibilità

| Crea un account

Gheno, Gloria (2015) Structural equation models with interacting mediators: theory and empirical results. [Tesi di dottorato]

Full text disponibile come:

[img]
Anteprima
Documento PDF
3991Kb

Abstract (inglese)

In last decades researchers have focused on the analysis of SEM models with nonlinear effects involving exogenous variables, i.e. which are not linearly dependent on other variables. The main problems studied are the estimation process, the choice of the indicators for nonlinear terms, when the variables are unobserved and the possibility of distinguishing interaction models from curvilinear models, while the causal analysis is not taken into account.
In this thesis I introduce nonlinear terms involving endogenous variables in SEM model with 2 mediators. I focus my attention on the interaction and curvilinear effects as its particular case. This analysis is made both with observed variables and with unobserved or latent variables. To address causal analysis, I propose two different approaches and I compare them using simulated data with different sample sizes and different covariances between the 2 mediators.
I find that my model with Pearl's (2012) causal theory and exogenous interaction, i.e. which does not depend linearly on other variables, is preferable for its simplicity and because it requires a smaller sample size. Pearl's theory can be applied to very general models and for this reason it has problems when the mediators are correlated given the mediated variable. Then I propose a modified formula to apply this theory. This approach has good performances both for interaction models and for curvilinear models and I propose a procedure to recognize the true model.
Finally from a managerial perspective using the exogenous interaction model with Pearl's modified causal theory proposed by me, I show that, in a customer satisfaction context, positive emotions and negative emotions influence "jointly" future behavior. As emotions are in turn influenced by the design of the restaurant, managers can use it to enhance customers' loyalty both directly and indirectly by jointly inducing more positive emotions and less negative ones. This way a model with interacting mediators may help to better understand customers' behavior

Abstract (italiano)

Negli ultimi decenni i ricercatori hanno focalizzato la loro attenzione sull'analisi di modelli SEM con effetti non lineari che coinvolgono variabili esogene, ossia che non sono linearmente dipendenti da altre variabili. I principali problemi studiati sono il processo di stima, la scelta degli indicatori per i termini non lineari quando le variabili sono non osservate e la possibilità di distinguere i modelli con interazione dai modelli curvilinei, non prendendo in considerazione l'analisi causale.
Introduco in questa tesi i termini non lineari che coinvolgono variabili endogene nel modello SEM con 2 mediatori. Focalizzo la mia attenzione sull'interazione e, come suo caso particolare, sugli effetti curvilinei. Questa analisi viene effettuata sia con le variabili osservate sia con le variabili non osservate o latenti. Per esaminare l'analisi causale, propongo due approcci diversi e li confronto utilizzando i dati simulati con differenti dimensioni del campione e con diverse covarianze tra i 2 mediatori.
Ho trovato che il modello con la teoria causale di Pearl (2012) e con l'interazione esogena, cioè che non dipende linearmente da altre variabili, è preferibile per la sua semplicità richiedendo un campione di dimensioni più piccole. La teoria di Pearl può essere applicata a modelli molto generali e quindi presenta problemi quando i mediatori sono correlati data la variabile mediata.Per applicare questa teoria propongo una formula da me modificata. Propongo una procedura per riconoscere il vero modello dando questo approccio buoni risultati sia per modelli con interazione sia per modelli curvilinei.
Infine dal punto di vista gestionale, utilizzando il modello con l'interazione esogena e con la teoria causale modificata di Pearl, dimostro che, in un contesto di soddisfazione del cliente, le emozioni positive e le emozioni negative influenzano "congiuntamente" il comportamento futuro. Essendo le emozioni a loro volta influenzate dal design del ristorante, i manager possono utilizzarlo per migliorare la fidelizzazione dei clienti sia direttamente che indirettamente e indurre congiuntamente più emozioni positive e meno quelle negative. In questo modo un modello con i mediatori che interagiscono può aiutare a comprendere meglio il comportamento dei clienti

Statistiche Download - Aggiungi a RefWorks
Tipo di EPrint:Tesi di dottorato
Relatore:Paggiaro, Adriano
Dottorato (corsi e scuole):Ciclo 27 > scuole 27 > SCIENZE STATISTICHE
Data di deposito della tesi:27 Gennaio 2015
Anno di Pubblicazione:27 Gennaio 2015
Parole chiave (italiano / inglese):causality, customer satisfaction, nonlinear SEM, SEM
Settori scientifico-disciplinari MIUR:Area 13 - Scienze economiche e statistiche > SECS-S/01 Statistica
Struttura di riferimento:Dipartimenti > Dipartimento di Scienze Statistiche
Codice ID:7626
Depositato il:12 Nov 2015 11:11
Simple Metadata
Full Metadata
EndNote Format

Bibliografia

I riferimenti della bibliografia possono essere cercati con Cerca la citazione di AIRE, copiando il titolo dell'articolo (o del libro) e la rivista (se presente) nei campi appositi di "Cerca la Citazione di AIRE".
Le url contenute in alcuni riferimenti sono raggiungibili cliccando sul link alla fine della citazione (Vai!) e tramite Google (Ricerca con Google). Il risultato dipende dalla formattazione della citazione.

1)Bentler, P. M. (1989). EQS, structural equations, program manual, program Version 3.0, BMDP Cerca con Google

Statistical Software, Inc., Los Angeles, 6 Cerca con Google

2) Bradley, J. V. (1978).Robustness?, British journal of mathematical and statistical psychology, vol. 31(2), pp 144-152 Cerca con Google

3)Brandt, H., Keleva, A. and Klein, A. (2014). A simulation study comparing recent approaches for the estimation of nonlinear effect in SEM under the conditional nonnormality, Structural equation modeling: a multidisciplinary journal, 21, pp181-195 Cerca con Google

4)Chen, S-P, and Cheng,C-P. (2014) Model specification for latent interactive and quadratic effects in matrix form, Structural equation modeling: a multidisciplinary journal, 21, pp 94-101 Cerca con Google

5)Coenders, G., Batista-Foguet, J. M., Saris, W. E. (2008). Simple, efficient and distribution-free approach to interaction effects in complex structural equation models, Quality \& Quantity, 42, pp 369-396 Cerca con Google

6)Collins, L. M, Schafer, J. L., and Kam, C-M (2001).A comparison of inclusive and restrictive strategies in modern missing data procedures, Psychological methods, vol. 6(4), pp 330-351 Cerca con Google

7)Dimitruk, P., Schermelleh-Engel, K,Keleva, A. and Moosbrugger, H.(2007). Challenges in nonlinear structural equation modeling, Methodology, vol. 3(3),pp 100-114 Cerca con Google

8)Fornell, C. and Larcker, D. F. (1981). Evaluating structural equation models with unobservable variables and measuremnet error, 1981, Journal of marketing research, vol.18(1) Cerca con Google

9)Ganzach, Y. (1997). Misleading interaction and curvilinear terms, Psychological methods, vol. 2 (3), pp 235-247 Cerca con Google

10)Garver, M. S., and Mentzer, J. T. (1999). Logistics research methods: employing structural equation modeling to test construct validity, Journal of business logistics, vol. 20(1), pp 33-58 Cerca con Google

11)Grewal, R., Cote, J. A., and Baumgartner, H. (2004). Multicollinearity and measurement error in structural equation models: implications for theory testing, Marketing sciences, vol. 23(4), pp 519-529 Cerca con Google

12)Hair, J.F. Jr, Black, W.C., Babin, B. J. and Anderson R.E. (2010).Multivariate data analysis, Pearson Prentice Hall, Upper Saddle River, New Jersey Cerca con Google

13)Hayes,A. F. (2013).Introduction to mediation, moderation and conditional process analysis: a regression-based approach, The Guilford press, N.Y. Cerca con Google

14)Hayes, A. F., and Preacher, K. J. (2010). Quantifying and testing indirect effects in simple mediation models when the constituent paths are nonlinear, Multivariate Behavioral Research, 45, ppp 627-660 Cerca con Google

15)Hoogland, J., and Boomsma, A. (1998). Robustness studies in covariance structure modeling: an overview and meta-analysis, Sociological methods \& Research, vol.26(3), pp 329-367 Cerca con Google

16)Imai, K., Keele, L., Tingley, D., and Yamamoto, T. (2014). Comment on Pearl: practical implications of theoretical results for causal mediation analysis, Psychological Methods, vol. 19(4), 482-487 Cerca con Google

17)Joreskog, K. G., and Yang, F.(1996). Nonlinear structural equation models: the Kenny-Judd model with interaction effects, chapter in G. A. Marcoulides and R. E. Schumacker (Eds), Advanced strucural equation modeling: issue and tecniques. NJ: Erbaum Cerca con Google

18)Kelava, A., Moosbrugger, H., Dimitruk, P. and Schermelleh-Engel, K.(2008). Multicollinearity and missing constraints, Methodology, vol.4(2), pp 51-66 Cerca con Google

19)Lin, G. C., Wen, Z., Marsh, H. W., and Lin. H, S, (2010), Structural Cerca con Google

equation models of latent interactions: Clarification Cerca con Google

of orthogonalizing and double-mean-centering strategies, Cerca con Google

Structural equation modeling, vol. 17,pp 374-391 Cerca con Google

20)Marsh, H. W.,Wen, Z and Hau, K. T. (2004). Structural equation models of latent interactions: evaluation of alternative estimation strategies and indicator construction, Psychological Methods, 9, pp 275-300 Cerca con Google

21)Moosbrugger, H., and Klein, A. (2000). Maximum likelihood estimation of latent interaction effects with the LMS method, Psychometrika, vol. 65(4), pp 457-474 Cerca con Google

22)Moosbrugger, H.,Schermelleh-Engel, K.,Keleva, A., and Klein, A. (2009). Testing multiple nonlinear effects in structural equation modeling: a comparison of alternative estimation approaches, chapter in T. Teo and M. S. Khine (Eds), Structural equation modelling in educational research: concepts and application. Rotterdam, NL: Sense Publishers. Cerca con Google

23)Moosbrugger, H.,Schermelleh-Engel, K., and Klein, A. (1997). Methodological problems of estimating Cerca con Google

latent interaction effects, Methods of Psychological Research Online 1997, Vol. 2(2) Cerca con Google

24)Morgan-Lopez,A. A. and MacKinnon, D.P. (2006).Demonstration and Cerca con Google

evaluation of a method for assessing mediated moderation, Behavior Cerca con Google

Research Methods, vol. 38, 77-87 Cerca con Google

25)Muthèn, L. K., and Asparouhov, T. (2003). Modeling interactions between latent and observed continuous variables using maximum-likelihood estimation in Mplus, http://www.statmodel.com/download/webnotes Vai! Cerca con Google

26)Muthèn, L. K., and Muthèn, B. (2002).How to use a montecarlo study to decide on sample size and determine power, Structural equation modeling: a multidisciplinary journal, vol. 9(4), pp 599-620 Cerca con Google

27) Muthèn, B. , Kaplan, D. , and Hollis, M. (1987).On structural equation modeling with data that are not missing completely at random, Psychometrika, vol. 52(3), pp 431-462 Cerca con Google

28)Pearl, J. (1998):Graphs,causality, and structural equation models, Cerca con Google

Sociological Methods and Research, 27,pp 226-284 Cerca con Google

29)Pearl, J. (2009).Causal inference in statistics: an overview, Cerca con Google

Statistical Survey, 3, pp 96-146 Cerca con Google

30)Pearl,J.(2012). The mediation formula: A guide to the assessment of Cerca con Google

causal pathways in nonlinear models, chapter in Berzuini C., Dawid P. and Cerca con Google

Bernardinelli L. (Eds), Causality: Statistical Cerca con Google

perspectives and application, Wiley Cerca con Google

31)Pearl, J. (2014). Interpretation and identification of causal mediation, Psychological Methods, vol. 19, 459-481 Cerca con Google

32)Phillips, D. M, and Baumgartner, H. (2002). The role of consumption emotions in the satisfaction response. Jorurnal of Consumer Research, vol. 28, pp 167-188 Cerca con Google

33) Ping, R. A. (1995). A parsimonious estimating technique for interaction and quadratic latent variables. Journal of Marketing Research, vol. 32, pp 336-347 Cerca con Google

34) Ping, R. A. (1996). Latent variable interaction and quadratic effect estimation: a two-step technique using structural equation analysis. Psychological Bulletin, vol. 119, pp 166-175 Cerca con Google

35) Preacher, K. J., and Hayes, A. F. (2008). Asymptotic and resampling strategies Cerca con Google

for assessing and comparing indirect effects in multiple mediator models, Behavior Research Methods Cerca con Google

2008, vol. 40 (3), pp 879-891 Cerca con Google

36) Satorra, A. and Bentler, P. M. (1994). Corrections to test statistics and standard errors in covariance structure analysis, chapter in A. Von Eye and C. Clogg (Eds), Latent variables analysis: applications to developmental research. Thousand Oaks, CA: Sage, pp 399-419 Cerca con Google

37)Schermelleh-Engel, K., Moosbrugger, H. and Muller, H. (2003).Evaluating the fit of structural Cerca con Google

equation models: tests of significance and descriptive goodness-of-fit measures, Methods of Psychological Research Online,vol.(2), pp. 23-74 Cerca con Google

38) Ryu, K., Han, H. (2010). Influence of physical environment on disconfirmation, customer satisfaction, and customer loyalty for first-time and repeat customers in upscale restaurants. International CHRIE Conference-Refereed Track. Paper 13 Cerca con Google

39)Thoemmes, F. , Mackinnon, D. P., and Raiser, M. R. (2010). Power analysis for complex mediational designs using montecarlo methods, Structural equation modeling, vol. 17(3), pp. 510-534 Cerca con Google

40)Thorndike, R. M., Cunningham, G. K., Thorndike, R. L., and Hagen E. P. (1991). Measurement and evaluation in psychology and education, Macmillan Publishing Company, N.Y. Cerca con Google

41)Westland, J.C.( 2010).Lower bound on sample size in structural equation modeling, Electronic Commerce research and application, 9, pp 476-487 Cerca con Google

Download statistics

Solo per lo Staff dell Archivio: Modifica questo record