A Cautionary Note on Incremental Fit Indices Reported by LISREL

Abstract. Incremental fit indices (IFIs) are regularly used when assessing the fit of structural equation models. IFIs are based on the comparison of the fit of a target model with that of a null model. For maximum-likelihood estimation, IFIs are usually computed by using the χ2 statistics of the maximum-likelihood fitting function (ML-χ2). However, LISREL recently changed the computation of IFIs. Since version 8.52, IFIs reported by LISREL are based on the χ2 statistics of the reweighted least squares fitting function (RLS-χ2). Although both functions lead to the same maximum-likelihood parameter estimates, the two χ2 statistics reach different values. Because these differences are especially large for null models, IFIs are affected in particular. Consequently, RLS-χ2 based IFIs in combination with conventional cut-off values explored for ML-χ2 based IFIs may lead to a wrong acceptance of models. We demonstrate this point by a confirmatory factor analysis in a sample of 2449 subjects.

Download Full-text

Gıda İsrafının Davranışsal Belirleyicileri; Çorum İli Örneği

Turkish Journal of Agriculture - Food Science and Technology ◽

10.24925/turjaf.v7i3.467-474.2415 ◽

2019 ◽

Vol 7 (3) ◽

pp. 467 ◽

Cited By ~ 1

Author(s):

Gungor Karakas

Keyword(s):

Factor Analysis ◽

Confirmatory Factor Analysis ◽

Food Waste ◽

Structural Equation ◽

Structural Equation Models ◽

Influential Factor ◽

Human Consumption ◽

Fit Indices ◽

Confirmatory Factor ◽

United Nations Food

Food waste and loss is an ecological, economic and social problem. The United Nations Food and Agriculture Organization states that approximately one third of all edible foods produced for human consumption are wasted or lost after harvest. The aim of this study is to determine the factors affecting food waste behavior of consumers. In order to reach this aim, a questionnaire was conducted with 583 people in November and December of 2018 in Çorum province. The obtained data were analyzed and explained through Structural Equation Models. As a result of the exploratory factor analysis, a 5-factor structure explaining 76,612% of the total variance was obtained. These factors were named as norm, intention, result awareness, purchasing behavior and planning. These factors were found to have validity, reliability and internal consistency. In addition, it was investigated whether the factors were compatible with the fit indices by means of Confirmatory Factor Analysis. As a result of confirmatory factor analysis, it was determined that the obtained factors met the fit indices values. As a result of Confirmatory Factor Analysis, it was determined that the obtained factors met the fit index values. The effect of the factors on the relationship between each other and the waste behavior were measured by means of the path analysis. As a result of this study, although consumers have positive statements regarding consequence awareness, intent and norms, they have been determined to be unstable in planning and purchasing. Besides, although there was a direct effect of intent and result awareness on waste behavior, it was determined that planning and norms had indirect effects. Considering that the intention is the most influential factor on waste behavior, it should be focused on the activities that will create result awareness in society.

Download Full-text

Croon’s Bias-Corrected Factor Score Path Analysis for Small- to Moderate-Sample Multilevel Structural Equation Models

Organizational Research Methods ◽

10.1177/1094428119879758 ◽

2019 ◽

Vol 24 (1) ◽

pp. 55-77 ◽

Cited By ~ 1

Author(s):

Benjamin Kelcey ◽

Kyle Cox ◽

Nianbo Dong

Keyword(s):

Maximum Likelihood ◽

Path Analysis ◽

Latent Variables ◽

Structural Equation ◽

Structural Equation Models ◽

Factor Score ◽

Likelihood Estimation ◽

Bias Error ◽

Parameter Estimates ◽

Multilevel Structural Equation

Maximum likelihood estimation of multilevel structural equation model (MLSEM) parameters is a preferred approach to probe theories involving latent variables in multilevel settings. Although maximum likelihood has many desirable properties, a major limitation is that it often fails to converge and can incur significant bias when implemented in studies with a small to moderate multilevel sample (e.g., fewer than 100 organizations with 10 or less individuals/organization). To address similar limitations in single-level SEM, literature has developed Croon’s bias-corrected factor score path analysis estimator that converges more regularly than maximum likelihood and delivers less biased parameter estimates with small to moderate sample sizes. We derive extensions to this framework for MLSEMs and probe the degree to which the estimator retains these advantages with small to moderate multilevel samples. The estimator emerges as a useful alternative or complement to maximum likelihood because it often outperforms maximum likelihood in small to moderate multilevel samples in terms of convergence, bias, error variance, and power. The proposed estimator is implemented as a function in R using lavaan and is illustrated using a multilevel mediation example.

Download Full-text

The Effects Of Estimator Choice And Weighting Strategies On Confirmatory Factor Analysis With Stratified Samples

Applied Multivariate Research ◽

10.22329/amr.v13i2.3019 ◽

2010 ◽

Vol 13 (2) ◽

pp. 113 ◽

Cited By ~ 1

Author(s):

Bradley J. Brummel ◽

Fritz Drasgow

Keyword(s):

Factor Analysis ◽

Maximum Likelihood ◽

Confirmatory Factor Analysis ◽

Likelihood Estimation ◽

Standard Errors ◽

Parameter Estimates ◽

Estimation Technique ◽

Confirmatory Factor ◽

Pseudo Maximum Likelihood Estimation ◽

Pseudo Maximum Likelihood

Survey researchers often design stratified sampling strategies to target specific subpopulations within the larger population. This stratification can influence the population parameter estimates from these samples because they are not simple random samples of the population. There are three typical estimation options that account for the effects of this stratification in latent variable models: unweighted maximum likelihood, weighted maximum likelihood, and pseudo-maximum likelihood estimation. This paper examines the effects of these procedures on parameter estimates, standard errors, and fit statistics in Lisrel 8.7 (Jöreskog & Sörbom, 2004) and Mplus 3.0 (Muthén & Muthén, 2004). Options using several estimation methods will be compared to pseudo-maximum likelihood estimation. Results indicated the choice of estimation technique does not have a substantial effect on confirmatory factor analysis parameter estimates in large samples. However, standard errors of those parameter estimates and RMSEA values for assessing of model fit can be substantially affected by estimation technique.

Download Full-text

Maximum likelihood estimation of nonlinear structural equation models

Psychometrika ◽

10.1007/bf02294842 ◽

2002 ◽

Vol 67 (2) ◽

pp. 189-210 ◽

Cited By ~ 75

Author(s):

Sik-Yum Lee ◽

Hong-Tu Zhu

Keyword(s):

Maximum Likelihood ◽

Maximum Likelihood Estimation ◽

Structural Equation ◽

Structural Equation Models ◽

Likelihood Estimation ◽

Nonlinear Structural ◽

Nonlinear Structural Equation

Download Full-text

Examining the ParticipACTION brand using the brand equity pyramid

Journal of Social Marketing ◽

10.1108/jsocm-11-2017-0071 ◽

2018 ◽

Vol 8 (4) ◽

pp. 378-396 ◽

Cited By ~ 3

Author(s):

Alexander Lithopoulos ◽

Peter A. Dacin ◽

Tanya R. Berry ◽

Guy Faulkner ◽

Norm O’Reilly ◽

...

Keyword(s):

Factor Analysis ◽

Confirmatory Factor Analysis ◽

Exploratory Factor Analysis ◽

Brand Equity ◽

Structural Equation ◽

Structural Equation Models ◽

Equation Modeling ◽

Content Type ◽

Activity Promotion ◽

Confirmatory Factor

Purpose The brand equity pyramid is a theory that explains how people develop loyalty and an attachment to a brand. The purpose of this study is to test whether the predictions made by the theory hold when applied to the brand of ParticipACTION, a Canadian non-profit organization that promotes active living. A secondary objective was to test whether this theory predicted intentions to be more physically active. Design/methodology/approach A research agency conducted a cross-sectional, online brand health survey on behalf of ParticipACTION. Exploratory factor analysis and confirmatory factor analysis established the factor structure. Structural equation modeling was used to test the hypothesized model. Findings A nationally representative sample of Canadian adults (N = 1,191) completed the survey. Exploratory factor analysis and confirmatory factor analysis supported a hypothesized five-factor brand equity framework (i.e. brand identity, brand meaning, brand responses, brand resonance and intentions). A series of structural equation models also provided support for the hypothesized relationships between the variables. Practical implications Though preliminary, the results provide a guide for understanding the branding process in the activity-promotion context. The constructs identified as being influential in this process can be targeted by activity-promotion organizations to improve brand strength. A strong organizational brand could augment activity-promotion interventions. A strong brand may also help the organization better compete against other brands promoting messages that are antithetical to their own. Originality/value This is the first study to test the brand equity pyramid using an activity-promotion brand. Results demonstrate that the brand equity pyramid may be useful in this context.

Download Full-text