On the evaluation of structural equation models
TL;DR: In this article, structural equation models with latent variables are defined, critiqued, and illustrated, and an overall program for model evaluation is proposed based upon an interpretation of converging and diverging evidence.
Abstract: Criteria for evaluating structural equation models with latent variables are defined, critiqued, and illustrated. An overall program for model evaluation is proposed based upon an interpretation of converging and diverging evidence. Model assessment is considered to be a complex process mixing statistical criteria with philosophical, historical, and theoretical elements. Inevitably the process entails some attempt at a reconcilation between so-called objective and subjective norms.
Citations
More filters
TL;DR: In this article, the authors investigated whether harmonious passion (HP) and obsessive passion (OP) make a distinctive contribution to explaining individual differences in knowledge management through self-regulation in e-learning contexts.
Abstract: Few studies have investigated whether harmonious passion (HP) and obsessive passion (OP) make a distinctive contribution to explaining individual differences in knowledge management through self-regulation in e-learning contexts. This study aimed to identify four types of passion (internal HP, external HP, internal OP, and external OP) in e-learning and, further, to examine the relationships between different types of passion, self-regulation, and knowledge management in e-learning. The participants were 1209 college students. Three 4-point Likert scales were employed to measure the concerned variables and structural equation modeling was employed to examine the proposed model. The findings revealed that the four types of passion were interrelated and that the proposed model was a good-fit model. Specifically, self-regulation mediated the influence of passion on knowledge management in e-learning. However, HP and OP predicted self-regulation and knowledge management in the opposite way, and HP played a more crucial role than OP in e-learning. The result in this study not only support the two-dimensional model of passion but also suggest that the four types of passion, though positively correlated, interact in ways that have different effects on college students’ self-regulation and knowledge management in e-learning.
11 citations
TL;DR: In this paper, the authors examined the effect of barriers to innovation in the business performance between companies of different business stages, measured through the years of operation using a multiple linear regression analysis of the sectors services and manufacturing industry in Chile.
11 citations
Cites methods from "On the evaluation of structural equ..."
...Furthermore, the Kaiser-Meyer-Olkin (KMO) analysis was also done, as well as Barlett’s sphericity test to measure the acceptability condition of the level of significance acceptable to proceed with a factor analysis (Bagozzi & Yi, 1988; Hair et al., 1995)....
[...]
...Furthermore, the average variance extracted (AVE) calculated for the constructs was above 0,60 for all factors (Bagozzi & Yi, 1988), Tables 4 and 5 present the detail of this analysis for each group of companies....
[...]
TL;DR: The authors derive and empirically validate a model that incorporates users’ perceptions of service/system quality as well as behavioral factors to explain usage and highlight important determinants of system/service quality perceptions that cloud providers should pay attention to in their attempts to increase marketshare.
Abstract: This study seeks to explain the adoption of cloud storage services as a means of personal archiving thereby focusing on users’ service and system quality perceptions and their drivers. The authors derive and empirically validate a model that incorporates users’ perceptions of service/system quality as well as behavioral factors to explain usage. Finally, the authors highlight important determinants of system/service quality perceptions that cloud providers should pay attention to in their attempts to increase marketshare.
11 citations
Cites background from "On the evaluation of structural equ..."
...The authors note that all values for all of the constructs in their model are above the commonly accepted minimum threshold of 0.7 (Bagozzi & Yi, 1988; Gefen, Straub, & Boudreau, 2000)....
[...]
TL;DR: In this paper, the authors examined how MBG generosity, store name familiarity, and consumer perception of price interacted to influence MBG believability and consumer store patronage and found that MBG's generosity positively affected consumer patronage intentions by increasing MBG trustworthiness.
Abstract: A money-back guarantee (MBG) is a service guarantee offered by a retailer. This research examined how MBG generosity, store name familiarity, and consumer perception of price interacted to influence MBG believability (the extent to which a consumer believes the MBG) and consumer store patronage. The results show that MBG generosity positively affected consumer patronage intentions by increasing MBG believability. When the perceived price was low, MBG generosity positively affected MBG believability for both well-known and lesser-known stores. When the perceived price was high, MBG generosity positively affected MBG believability only for well-known stores.
11 citations
TL;DR: In this paper, the authors analyze the relationship between congenital learning and work-life balance (WLB) culture and try to identify whether WLB culture impacts on business performance through an empirical study of 229 small and medium-sized enterprises (SMEs) in the Spanish metal industry.
Abstract: A possible explanation for the numerous failures in the implementation and use of work-life balance (WLB) practices may relate to the fact that the majority of companies have introduced them without exploring the nature and extent of their founders’ or owners’ prior knowledge of WLB and WLB practices. This paper analyses the relationships between congenital learning and WLB culture and tries to identify whether WLB culture impacts on business performance through an empirical study of 229 small and medium-sized enterprises (SMEs) in the Spanish metal industry. Our findings show that in order to create positive attitudes toward WLB, managers need to create and support a learning process. These findings provide interesting insights into the drivers of organisational performance for SMEs that develop and support a WLB-supporting culture.
11 citations
References
More filters
TL;DR: In this paper, the statistical tests used in the analysis of structural equation models with unobservable variables and measurement error are examined, and a drawback of the commonly applied chi square test, in additit...
Abstract: The statistical tests used in the analysis of structural equation models with unobservable variables and measurement error are examined. A drawback of the commonly applied chi square test, in addit...
56,555 citations
TL;DR: In this article, a new estimate minimum information theoretical criterion estimate (MAICE) is introduced for the purpose of statistical identification, which is free from the ambiguities inherent in the application of conventional hypothesis testing procedure.
Abstract: The history of the development of statistical hypothesis testing in time series analysis is reviewed briefly and it is pointed out that the hypothesis testing procedure is not adequately defined as the procedure for statistical model identification. The classical maximum likelihood estimation procedure is reviewed and a new estimate minimum information theoretical criterion (AIC) estimate (MAICE) which is designed for the purpose of statistical identification is introduced. When there are several competing models the MAICE is defined by the model and the maximum likelihood estimates of the parameters which give the minimum of AIC defined by AIC = (-2)log-(maximum likelihood) + 2(number of independently adjusted parameters within the model). MAICE provides a versatile procedure for statistical model identification which is free from the ambiguities inherent in the application of conventional hypothesis testing procedure. The practical utility of MAICE in time series analysis is demonstrated with some numerical examples.
47,133 citations
TL;DR: In this paper, the problem of selecting one of a number of models of different dimensions is treated by finding its Bayes solution, and evaluating the leading terms of its asymptotic expansion.
Abstract: The problem of selecting one of a number of models of different dimensions is treated by finding its Bayes solution, and evaluating the leading terms of its asymptotic expansion. These terms are a valid large-sample criterion beyond the Bayesian context, since they do not depend on the a priori distribution.
38,681 citations
01 Jan 2005
TL;DR: In this paper, the problem of selecting one of a number of models of different dimensions is treated by finding its Bayes solution, and evaluating the leading terms of its asymptotic expansion.
Abstract: The problem of selecting one of a number of models of different dimensions is treated by finding its Bayes solution, and evaluating the leading terms of its asymptotic expansion. These terms are a valid large-sample criterion beyond the Bayesian context, since they do not depend on the a priori distribution.
36,760 citations
TL;DR: In this article, a general null model based on modified independence among variables is proposed to provide an additional reference point for the statistical and scientific evaluation of covariance structure models, and the importance of supplementing statistical evaluation with incremental fit indices associated with the comparison of hierarchical models.
Abstract: Factor analysis, path analysis, structural equation modeling, and related multivariate statistical methods are based on maximum likelihood or generalized least squares estimation developed for covariance structure models. Large-sample theory provides a chi-square goodness-of-fit test for comparing a model against a general alternative model based on correlated variables. This model comparison is insufficient for model evaluation: In large samples virtually any model tends to be rejected as inadequate, and in small samples various competing models, if evaluated, might be equally acceptable. A general null model based on modified independence among variables is proposed to provide an additional reference point for the statistical and scientific evaluation of covariance structure models. Use of the null model in the context of a procedure that sequentially evaluates the statistical necessity of various sets of parameters places statistical methods in covariance structure analysis into a more complete framework. The concepts of ideal models and pseudo chi-square tests are introduced, and their roles in hypothesis testing are developed. The importance of supplementing statistical evaluation with incremental fit indices associated with the comparison of hierarchical models is also emphasized. Normed and nonnormed fit indices are developed and illustrated.
16,420 citations