Measurement Model Quality, Sample Size, and Solution Propriety in Confirmatory Factor Models

Gagné, Phill; Hancock, Gregory R.

doi:10.1207/s15327906mbr4101_5

Cited by 302 publications

(227 citation statements)

References 20 publications

Supporting

Mentioning

215

Contrasting

Unclassified

Order By: Relevance

“…PLS is often hyped as being an estimator that works well even under "ridiculously small" conditions (Marcoulides & Saunders, 2006, p. iii); however, in this regard and as soberly noted by the editors of MIS Quarterly, "PLS is not a silver bullet" (Marcoulides & Saunders, 2006, p. vii). In fact SEM estimators have excellent properties even at very small sample sizes Goodhue, Lewis, & Thompson, 2012), though there will be convergence issues if the estimated ratio of parameters to sample size is extremely small (Gagne & Hancock, 2006). Issues of convergence can affect PLS too (Henseler, 2010).…”

Section: The Future Of Methodsmentioning

confidence: 99%

What makes articles highly cited?

Antonakis

Bastardoz

Liu

et al. 2014

The Leadership Quarterly

104

View full text Add to dashboard Cite

We examined drivers of article citations using 776 articles that were published from 1990-2012 in a broad-based and high-impact social sciences journal, The Leadership Quarterly. These articles had 1,191 unique authors having published and received in total (at the time of their most recent article published in our dataset) 16,817 articles and 284,777 citations, respectively. Our models explained 66.6% of the variance in citations and showed that quantitative, review, method, and theory articles were significantly more cited than were qualitative articles or agentbased simulations. As concerns quantitative articles, which constituted the majority of the sample, our model explained 80.3% of the variance in citations; some methods (e.g., use of SEM) and designs (e.g., meta-analysis), as well as theoretical approaches (e.g., use of transformational, charismatic, or visionary type-leadership theories) predicted higher article citations. Regarding the statistical conclusion validity of quantitative articles, articles having endogeneity threats received significantly fewer citations than did those using a more robust design or an estimation procedure that ensured correct causal estimation. We make several general recommendations on how to improve research practice and article citations.

show abstract

Section: The Future Of Methodsmentioning

confidence: 99%

What makes articles highly cited?

Antonakis

Bastardoz

Liu

et al. 2014

The Leadership Quarterly

104

View full text Add to dashboard Cite

show abstract

“…High construct reliability would increase the accuracy of parameter estimation within the limitation of sample size (Gagné & Hancock, 2006). Analysis was in LISREL version 8.72 (Jöreskog & Sörbom, 2005).…”

Section: Analytical Proceduresmentioning

confidence: 99%

Elucidating the roles of motives and gains in exercise participation.

Ingledew

Markland

Strömmer

2014

Sport, Exercise, and Performance Psychology

View full text Add to dashboard Cite

Previous research into the role of exercise motives (what people want from exercise) has overlooked the possible role of gains (what people get) and hence the possible benefits of motive fulfillment (when people get what they want). To redress this imbalance, we examined the additive and interactive effects of motives and subjective gains on exercise-specific outcomes. Young adults (N = 196) completed measures of exercise motives and gains, and exercise behavioral regulation, amount, satisfaction, and intention. Four representative motives/gains were selected: appearance, positive health, challenge, and affiliation. Path analysis was used to test the effects of motives, gains, and their products (the interactive effects) on behavioral regulations, and thereby exercise amount, satisfaction, and intention. Controlled regulation increased with appearance motive, unless appearance gain was high. Controlled regulation had a negative effect on exercise satisfaction. Autonomous regulation increased with positive health motive, provided positive health gain was high; with challenge motive and gain; and with affiliation motive. Autonomous regulation had positive effects on exercise amount, satisfaction, and intention. The study corroborates previous findings about the effects of motives. It establishes the value of also studying gains, as moderators of the effects of motives, and in their own right. The findings are interpretable in terms of self-determination theory. Exercise promotion could be more effective if it focused on gains in conjunction with motives.

show abstract

“…However, it appears that a sample of 300 does not provide enough information for an accurate estimate of the weight matrix, thereby leading to more discrepant estimates of the parameters. Obtaining a solution, regardless of the estimation method, does not ensure an accurate solution (Gagné & Hancock, 2006).5 Equivalent estimates are obtained using more recent versions (3 and 4) of Mplus. 6 Data and code for Mplus, MULTILOG, and R can be found online at the supplemental material Web site identified at the beginning of the article.…”

mentioning

confidence: 99%

Item factor analysis: Current approaches and future directions.

Wirth

Edwards

2007

Psychological Methods

749

601

View full text Add to dashboard Cite

The rationale underlying factor analysis applies to continuous and categorical variables alike; however, the models and estimation methods for continuous (i.e., interval or ratio scale) data are not appropriate for item-level data that are categorical in nature. The authors provide a targeted review and synthesis of the item factor analysis (IFA) estimation literature for ordered-categorical data (e.g., Likert-type response scales) with specific attention paid to the problems of estimating models with many items and many factors. Popular IFA models and estimation methods found in the structural equation modeling and item response theory literatures are presented. Following this presentation, recent developments in the estimation of IFA parameters (e.g., Markov chain Monte Carlo) are discussed. The authors conclude with considerations for future research on IFA, simulated examples, and advice for applied researchers. Keywordsitem factor analysis; parameter estimation; categorical data; confirmatory factor analysis; item response theory Item-level data within the social and behavioral sciences are often categorical in nature. Dichotomous (e.g., disagree vs. agree) or polytomous (e.g., strongly disagree, disagree, neither, agree, and strongly agree) item response formats may fail to maintain the scale and distributional properties assumed by models such as ordinary least squares regression or common linear factor analysis. Traditional regression techniques describe the outcome variable as an optimal linear function of observed predictors. The proper implementation of these techniques requires assumptions such as independent and normally distributed residuals, a continuous conditionally normal outcome, and that the model is correctly specified (i.e., a linear relationship exists between the outcome and predictors). The common linear factor model, which describes the covariances among observed variables as a function of a smaller number of latent factors, makes many of the same assumptions. It is assumed that the unique factors (those that affect only one measured variable) are normally distributed, the outcomes are continuous and conditionally normally distributed, and a linear relationship exists between the observed and latent variables. Although this list of assumptions is not exhaustive, it does represent assumptions that are easily violated with itemlevel ordered-categorical data. Attempting to estimate model parameters, for example, NIH-PA Author ManuscriptNIH-PA Author Manuscript NIH-PA Author Manuscript with dichotomous outcomes within the standard confirmatory factor model (as described by Jöreskog, 1969) results in parameter estimates that are biased and impossible to interpret accurately (Di-Stefano, 2002). However, all is not lost; just as logistic and ordinal regression techniques offer appropriate alternatives to linear regression when modeling dichotomous or polytomous (e.g., ordinal, Likert-type scales) outcomes, item factor analysis (IFA) offers an appropriate alternative to the common line...

show abstract

Measurement Model Quality, Sample Size, and Solution Propriety in Confirmatory Factor Models

Cited by 302 publications

References 20 publications

What makes articles highly cited?

What makes articles highly cited?

Elucidating the roles of motives and gains in exercise participation.

Item factor analysis: Current approaches and future directions.

Contact Info

Product

Resources

About