Model Selection Indices for Polytomous Items

Kang, Taehoon; Cohen, Allan S.; Sung, Hyun-Jung

doi:10.1177/0146621608327800

Cited by 57 publications

(22 citation statements)

References 44 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three primary fit indices were used to test a model fit: Comparative Fit Index (CFI; best if close to .95 or greater); root-mean-square error of approx imation (RMSEA; best if close to .06 or less, acceptable if close to .08 or less); and standardized root-mean-square residual (SRMR; best if close to .08 or less, acceptable if close to .10 or less; see Hu & Bentler, 1999;Vandenberg & Lance, 2000). We also reported the Bayesian information criterion (BIC) that takes model com plexity into account; comparatively better fitting models indicate lower BIC values (Kang, Cohen, & Sung, 2009).…”

Section: Resultsmentioning

confidence: 99%

Development and validation of the Patriarchal Beliefs Scale.

Yoon¹,

Adams²,

Hogge³

et al. 2015

Journal of Counseling Psychology

View full text Add to dashboard Cite

The purpose of this research was to develop and validate a conceptually and psychometrically solid measure for patriarchal beliefs in samples of U.S. American adults from diverse demographic and geographic backgrounds. In Study 1, we identified 3 correlated factors of the Patriarchal Beliefs Scale (PBS) in data collected from the Internet (N = 279): Institutional Power of Men, Inferiority of Women, and Gendered Domestic Roles. In Study 2, data collected from the Internet (N = 284) supported both an oblique 3-factor structure and a bifactor structure of the PBS, through confirmatory factor analyses. Construct validity of the PBS was supported in relation to other gender-related measures. The PBS was correlated in expected directions with modern sexism, antifeminist attitudes, and egalitarian attitudes toward women. In Study 3, we examined measurement invariance across gender by using combined data from Study 1 and Study 2. All 3 factors of the oblique 3-factor model indicated measurement invariance, whereas the general factor represented in the bifactor model indicated nonequivalence. Mean differences in patriarchal beliefs were found for such demographic variables as gender, sexual orientation, education, and social class. Recommendations for using the PBS, as well as implications for research and practice, are discussed.

show abstract

Section: Resultsmentioning

confidence: 99%

Development and validation of the Patriarchal Beliefs Scale.

Yoon¹,

Adams²,

Hogge³

et al. 2015

Journal of Counseling Psychology

View full text Add to dashboard Cite

show abstract

“…To determine the optimal response model for the data set, four polytomous item response theory models were fitted to responses of the two samples with ltm (Rizopoulos, 2006) and compared on the basis of Schwarz's Bayesian information criterion (BIC; see Kang, Cohen, & Sung, 2009): (a) generalized partial credit model (GPCM; Muraki, 1992), (b) GPCM with equal discrimination parameters, (c) GRM (Samejima, 1969), and (d) GRM with equal discrimination parameters for all items. On the basis of the BIC criterion, the GRM was deemed the optimal response model for all three scales.…”

Section: Methodsmentioning

confidence: 99%

Polytomous Adaptive Classification Testing

Gnambs

Batinic

2011

Educational and Psychological Measurement

View full text Add to dashboard Cite

Computer-adaptive classification tests focus on classifying respondents in different proficiency groups (e.g., for pass/fail decisions). To date, adaptive classification testing has been dominated by research on dichotomous response formats and classifications in two groups. This article extends this line of research to polytomous classification tests for two-and three-group scenarios (e.g., inferior, mediocre, and superior proficiencies). Results of two simulation experiments with generated and real responses (N ¼ 2,000) to established personality scales of different length (12, 20, or 29 items) demonstrate that adaptive item presentations significantly reduce the number of items required to make such classification decisions while maintaining a consistent classification accuracy. Furthermore, the simulations highlight the importance of the selected test termination criterion, which has a significant impact on the average test length.

show abstract

“…Because for medium and large numbers of variables, traditional goodness-of-fit statistics such as the likelihood ratio statistic G 2 or Pearson's chi-square statistic X 2 fail to provide trustworthy fit results (e.g., Koehler & Larntz, 1980), one usually resorts to relative fit measures, such as the information criteria AIC (Bozdogan, 1987) and BIC (Schwarz, 1978). Recently, Kang and Cohen (2007); Kang, Cohen, and Sung (2009); and Li, Cohen, Kim, and Cho (2009) evaluated several relative fit measures including AIC and BIC for choosing the correct item response theory model. The choice is made as follows.…”

Section: Latent Class Reliability Coefficientmentioning

confidence: 99%

A Latent Class Approach to Estimating Test-Score Reliability

Ark

Palm

Sijtsma

2011

Applied Psychological Measurement

View full text Add to dashboard Cite

This study presents a general framework for single-administration reliability methods, such as Cronbach's alpha, Guttman's lambda-2, and method MS. This general framework was used to derive a new approach to estimating test-score reliability by means of the unrestricted latent class model. This new approach is the latent class reliability coefficient (LCRC). Unlike other single-administration reliability methods, LCRC places few restrictions on the item scores. A simulation study showed that if data are multidimensional or if double monotonicity does not hold, then LCRC is less biased relative to the true reliability than Cronbach's alpha, Guttman's lambda-2, method MS, and the split-half reliability coefficient.Test-score reliability, denoted r XX 0 , is one of the most reported statistics in social and behavioral science research. This study adopts the definition proposed by Lord and Novick (1968, p. 61). Let X be the test score, which is defined as the sum of the J item scores X j ðj ¼ 1; . . . ; J Þ, so that X ¼ P J j¼1 X j . In the population, test score X has expectation m X and variance s 2 X . Let T be the unobservable true score (Lord & Novick, 1968, chaps. 2 and 3), defined as a testee's expectation of X across his or her propensity distribution of independent test repetitions. In the population, T has expectation m T and variance s 2 T . Test-score reliability is defined as the product-moment correlation between two sets of independent test scores from two different but interchangeable tests known as parallel tests (which replace two independent repetitions), and equals the ratio of true score and test score variances,Article

show abstract

Model Selection Indices for Polytomous Items

Cited by 57 publications

References 44 publications

Development and validation of the Patriarchal Beliefs Scale.

Development and validation of the Patriarchal Beliefs Scale.

Polytomous Adaptive Classification Testing

A Latent Class Approach to Estimating Test-Score Reliability

Contact Info

Product

Resources

About