Latent Variable Path Modeling with Partial Least Squares

Lohmöller, Jan-Bernd

doi:10.1007/978-3-642-52512-4

Cited by 1,561 publications

(986 citation statements)

References 129 publications

(141 reference statements)

Supporting

Mentioning

841

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, within a group of data, a M-estimator down-weights inhomogeneous observations when returning the segment-specific PLS solution. we determine the path model via the PLS algorithm (Lohmöller, 1989;Wold, 1982) and weighted regressions. The structural model residuals of all regressions determine the assignment of observations to the different groups.…”

Section: Methodsmentioning

confidence: 99%

“…For this purpose, we select a simulation design that represents different data constellations that frequently occur in empirical applications. In accordance with prior simulation studies on PLS and PLS segmentation (Becker et al, 2013;Reinartz, Haenlein, & Henseler, 2009;Ringle et al, 2013;Sarstedt, Becker, et al, 2011), we select the subsequent factors and factor levels which closely follow the design presented by Ringle et al (2014) Wold (1982) and Lohmöller (1989) for details on Mode A, Mode B, and Mode C.…”

Section: Design Of the Study And Data Generationmentioning

confidence: 99%

See 1 more Smart Citation

Segmentation of PLS path models by iterative reweighted regressions

Schlittgen

Ringle

Sarstedt

et al. 2015

Proceedings of the 2nd International Symposium on Partial Least Squares Path Modeling: The Conference for PLS Users

View full text Add to dashboard Cite

Uncovering unobserved heterogeneity is a requirement to obtain valid results when using the structural equation modeling (SEM) method with empirical data. Conventional segmentation methods usually fail in SEM since they account for the observations but not the latent variables and their relationships in the structural model. This research introduces a new segmentation approach to variance-based SEM. The iterative reweighted regressions segmentation method for PLS (PLS-IRRS) effectively identifies segments in data sets. In comparison with existing alternatives, PLS-IRRS is multiple times faster while delivering the same quality of results. We believe that PLS-IRRS has the potential to become one of the primary choices to address the critical issue of unobserved heterogeneity in PLS-SEM.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Design Of the Study And Data Generationmentioning

confidence: 99%

Segmentation of PLS path models by iterative reweighted regressions

Schlittgen

Ringle

Sarstedt

et al. 2015

Proceedings of the 2nd International Symposium on Partial Least Squares Path Modeling: The Conference for PLS Users

View full text Add to dashboard Cite

show abstract

“…To test our hypotheses and the structural relationships we applied Partial Least Squares Path Modelling (PLS-PM; Lohmöller, 1989;Wold, 1982;Wold, 1985). SmartPLS 2.0 statistical software was used to estimate the model parameters (Ringle et al ., 2005).…”

Section: Model Estimationmentioning

confidence: 99%

Staff turnover in hotels: Exploring the quadratic and linear relationships

2015

View full text Add to dashboard Cite

Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-pro t purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details.

show abstract

“…O presente trabalho utilizou o software WarpPLS 3.0 (Kock, 2012), uma ferramenta que permite a estimação de modelos de equações estruturais baseados em variância, estimados por Partial Least Squares (PLS) (Hair, Sarstedt, Ringle, & Mena, 2011 (Lohmöller, 1989). Assim, não apresentam indicadores de ajuste agregados baseados na estatística quiquadrado, que testa a aderência da matriz de correlações reproduzidas à matriz observada.…”

Section: Técnicas De Análiseunclassified

Motivações da Comunicação Boca a Boca Eletrônica Positiva entre Consumidores no Facebook

Tubenchlak¹,

Lima²,

Zanini³

et al. 2015

Rev. adm. contemp.

View full text Add to dashboard Cite

ResumoEste estudo buscou investigar as motivações subjacentes ao comportamento de comunicação boca a boca eletrônica (BAB-e) positiva sobre produtos, serviços e marcas no site de redes sociais Facebook, no contexto brasileiro. Para tanto, foram desenvolvidas hipóteses de pesquisa e um modelo teórico para se entender as motivações da comunicação BAB-e positiva nesse contexto. A fim de testar a validade do modelo proposto, um levantamento amostral foi conduzido com 468 usuários do site no Brasil. Os dados foram analisados por meio de modelos de equações estruturais. Os resultados sugerem como motivações significantes a preocupação com outros consumidores e o desejo de interação social, assim como os desejos de extravasar emoções positivas e de ajudar a empresa. A hipótese que previu que as recompensas econômicas afetam positivamente a comunicação BAB-e positiva não foi confirmada, assim, sugerindo que as motivações deste comportamento no Facebook são de natureza social e psicológica mais do que puramente econômica. O teste empírico deu suporte ao papel moderador da força dos laços sociais na relação entre preocupação com outros consumidores e comunicação BAB-e positiva.Palavras-chave: comunicação boca a boca eletrônica; motivações; redes sociais; sites; Facebook. AbstractThe purpose of the present study is to investigate the underlying motivations for positive electronic word of mouth (eWOM) behavior about products, services and brands by Brazilian Facebook users. Research hypotheses and a theoretical model were developed to further our understanding of positive eWOM communication motivations. A survey was conducted with 468 Facebook users in Brazil in order to empirically test the validity of the proposed model. Data was analyzed using structural equations models. Results suggest that concern for other consumers, the desire to engage in social interactions, as well as the desire to share positive emotions and help companies are significant motivations. The hypothesis which predicted that economic rewards are correlated with positive eWOM communication was not confirmed, suggesting that social and psychological motivations are more correlated with eWOM behavior than purely economic reasons for Brazilian Facebook users. The empirical test supported the moderating role of tie strength in the relationship between concern for other consumers and positive eWOM communication.

show abstract

Latent Variable Path Modeling with Partial Least Squares

Cited by 1,561 publications

References 129 publications

Segmentation of PLS path models by iterative reweighted regressions

Segmentation of PLS path models by iterative reweighted regressions

Staff turnover in hotels: Exploring the quadratic and linear relationships

Motivações da Comunicação Boca a Boca Eletrônica Positiva entre Consumidores no Facebook

Contact Info

Product

Resources

About