An entropy criterion for assessing the number of clusters in a mixture model
Open accessThe DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Entropy above .80 also indicates a good-fitting model [40, 41].”
From Symptom experiences in post-treatment cancer survivors: associations with acceptance and commitment therapy constructs. (2021) · cites this paper as [40]
In the citing paper
“These values can vary between 0 and 1 with higher values representing greater accuracy of classification and values above 0.80 evidencing classification with minimal uncertainty.”
From Coping profiles and their association with psychological functioning: A latent profile analysis of coping strategies during the COVID-19 pandemic (2022) · cites this paper as Celeux & Soromenho, 1996
In the citing paper
“the entropy values of greater than .80 showed a 220 clear delineation of classes in the 'quadratic' GMM models with two or three classes 221 (Celeux and Soromenho, 1996).”
From Time in treatment: Examining mental illness trajectories across inpatient psychiatric treatment (2020) · cites this paper as Celeux and Soromenho, 1996
Citations
Cites
A new look at the statistical model identification
Akaike, H. (1974) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1974.1100705 · Cited by 51,879
Maximum Likelihood from Incomplete Data Via the EM Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444
Estimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033
(1967) · Cited by 23,719
Pattern Recognition with Fuzzy Objective Function Algorithms
Bezdek, J. C. (1981) · doi:10.1007/978-1-4757-0450-1 · Cited by 9,881
Statistical Analysis of Finite Mixture Distributions.
Lindsay, B. G., Titterington, D. M., Smith, A. F. M., & Makov, U. E. (1987) · Journal of the American Statistical Association · doi:10.2307/2289504 · Cited by 2,905
Model-Based Gaussian and Non-Gaussian Clustering
Banfield, J. D., & Raftery, A. E. (1993) · Biometrics · doi:10.2307/2532201 · Cited by 2,395 · cited 2×
“…have considered the problem of choosing the number of clusters, in a partitioning setting, within the context of multivariate mixture models (see Bock 1985; Celeux 1986; Bozdogan 1993; Banfield and Raftery 1993; McLachlan and Basford 1988; Windham and Cutler 1992; Bryant 1993, among others).”
MethodMixture models : inference and applications to clustering
McLachlan, G. J., & Basford, K. E. (1988) · M. Dekker eBooks · Cited by 2,094
Statistical Analysis of Finite Mixture Distributions.
Newton, J., Titterington, D. M., Smith, A. F. M., & Makov, U. E. (1986) · Biometrics · doi:10.2307/2531224 · Cited by 1,986
Proceedings of the 6th Berkeley Symposium on Mathematical Statistics and Probability
Cam, L. M. L., Neyman, J., & Scott, E. L. (1972) · Medical Entomology and Zoology · Cited by 1,679
Research works printed but not linked: 1
- BRYANT, P. G., and WILLIAMSON, J. A. (1986), ?Maximum Likelihood and Classification: a Comparison of Three Approaches,? inClassification as a tool of research, Eds., W. Gaul and M. Schader, North-Holland, pp. 33?45.
Cited by
Items 401–500 of 1,010
Podlogar, M. C., Rogers, M. L., Stanley, I. H., Hom, M. A., Chiurliza, B., & Joiner, T. E. (2017) · Cognition & Emotion · doi:10.1080/02699931.2017.1303452 · Cited by 43
“Entropy is a bounded measure from 0 to 1, with higher entropy values indicating more precise classification, and is used to assess the degree of clarity in class membership based on posterior probabilities (Celeux & Soromenho, 1993).”
BackgroundXiao, Q., Wu, M., & Zeng, T. (2019) · Aging & Mental Health · doi:10.1080/13607863.2018.1488941 · Cited by 38
“Entropy of the four class model was 0.90, indicating a reasonable delineation of classes (Celeux & Soromenho, 1996).”
MethodInfluentialSocial demands and resources predict job burnout and engagement profiles among Finnish employees
Upadyaya, K., & Salmela‐Aro, K. (2020) · Anxiety Stress & Coping · doi:10.1080/10615806.2020.1746285 · Cited by 65
“…low p value indicates that the k model has to be rejected in favor of a model with at leat k + 1 classes); (d) entropy values, which determine classification quality (values close to 1 indicate clear classification) (Celeux & Soromenho, 1996); and (e) the clarity and interpretation of the classes.”
BackgroundStudent engagement with school and personality: a biopsychosocial and person‐centred approach
Moreira, P., Inman, R. A., Cloninger, K. M., & Cloninger, C. R. (2020) · British Journal of Educational Psychology · doi:10.1111/bjep.12388 · Cited by 44
Tóth, F., Mihelj, S., Štětka, V., & Kondor, K. (2022) · The International Journal of Press/Politics · doi:10.1177/19401612211072552 · Cited by 53
“…criterion (AIC) and Schwarz ’ s Bayesian information criterion (BIC) for determining best fi t in terms of parsimony, and the entropy criterion value to select the model providing the greatest evidence for partitioning data in terms of well separated groups or clusters (Celeux and Soromenho 1996).”
BackgroundPeugh, J., & Fan, X. (2014) · Structural Equation Modeling A Multidisciplinary Journal · doi:10.1080/10705511.2014.919823 · Cited by 43
“…entropybased enumeration indices that reward GMM models producing well-defined trajectory profiles have been proposed (e.g.,Bauer & Curran, 2003a, 2004): the normalized entropy criterion (NEC; Celeux & Soromenho, 1996), and the classification likelihood criterion (CLC; Biernacki & Govaert, 1997).”
BackgroundMultilevel Functional Clustering Analysis
Serban, N., & Jiang, H. (2012) · Biometrics · doi:10.1111/j.1541-0420.2011.01714.x · Cited by 43
“In the soft clustering context, this translates into overestimation of the number of clusters (Soromenho, 1994; Celeux and Soromenho, 1996).”
BackgroundDeLuca, C., Rickey, N., & Coombs, A. (2021) · Cogent Education · doi:10.1080/2331186x.2021.1921903 · Cited by 55
“The entropy value ranges from 0 to 1, with higher values indicating smaller classification error for the model (Celeux & Soromenho, 1996).”
BackgroundYalçın, İ., Boysan, M., Eşkısu, M., & Çam, Z. (2022) · Current Psychology · doi:10.1007/s12144-022-02987-2 · Cited by 53
“The entropy index is an indicator of quality of class membership classification (Celeux & Soromenho, 1996).”
Pickard, A., Croker, H. A., Edwards, K., Farrow, C. V., Haycraft, E., Herle, M., Kininmonth, A. R., Llewellyn, C. H., & Blissett, J. M. (2023) · Appetite · doi:10.1016/j.appet.2023.107050 · Cited by 40
Babusa, B., Czeglédi, E., Túry, F., Mayville, S. B., & Urbán, R. (2014) · Body Image · doi:10.1016/j.bodyim.2014.09.001 · Cited by 47
Brouns, B. H. J., de Wied, M. A., Keijsers, L., Branje, S., van Goozen, S. H. M., & Meeus, W. (2013) · Journal of Child Psychology and Psychiatry · doi:10.1111/jcpp.12052 · Cited by 47
“First, we used an entropy value of .75 or higher as indicative of good classification accuracy (Celeux & Soromenho, 1996).”
MethodRichter, D., Engelbert, M., Weirich, S., & Pant, H. A. (2013) · Zeitschrift für Pädagogische Psychologie · doi:10.1024/1010-0652/a000104 · Cited by 42
Reichenheim, M. E., Interlenghi, G. S., de Moraes, C. L., Segall‐Corrêa, A. M., Pérez‐Escamilla, R., & Salles‐Costa, R. (2016) · Journal of Nutrition · doi:10.3945/jn.116.231845 · Cited by 41
Frndak, S., Barg, G., Canfield, R. L., Quierolo, E. I., Mañáy, N., & Kordas, K. (2019) · NeuroToxicology · doi:10.1016/j.neuro.2019.04.004 · Cited by 42
McCabe, S. E., Veliz, P. T., Dickinson, K., Schepis, T. S., & Schulenberg, J. E. (2019) · The Lancet Psychiatry · doi:10.1016/s2215-0366(19)30299-8 · Cited by 40
Anxiety and self-esteem in cyber-victimization profiles of adolescents
Andrea, N., Álvarez-García, D., & Fuentes, M. D. C. P. (2020) · Comunicar · doi:10.3916/c67-2021-04 · Cited by 69
“Entropy takes values between zero and one, and the closer it is to one, the more accurate the classification (values higher than .80 indicate good classification quality; Celeux & Soromenho, 1996).”
BackgroundBrédart, A., Merdy, O., Sigal‐Zafrani, B., Fiszer, C., Dolbeault, S., & Hardouin, J.-B. (2015) · Supportive Care in Cancer · doi:10.1007/s00520-015-2799-1 · Cited by 45
“Then, the appropriate number of classes was selected according to the following five criteria listed in order of priority: (1) a smallest class size greater than 4 % of the total sample, (2) clinical interpretability, (3) a smallest “Sample-Size Adjusted Bayesian Information Criteria” (SABIC) [37–39], (4) model conver…”
MethodInterparental aggression and infant patterns of adrenocortical and behavioral stress responses
Towe‐Goodman, N. R., Stifter, C. A., Mills‐Koonce, W. R., Granger, D. A., & The Family Life Project Key Investigators (2012) · Developmental Psychobiology · doi:10.1002/dev.20618 · Cited by 37
“…and the optimal number of classes was selected based on a balance of model fit, interpretability, and parsimony (e.g., Bayesian information criterion (BIC), Akaike information criterion (AIC), Lo Mendell Rubin (LMR; Lo, Mendell, & Rubin, 2001), and entropy statistic (Celeux & Soromenho, 1996)).”
Individual Working-time Adjustments between Full-time and Part-time Working in European Firms
Fagan, C., & Walthéry, P. (2011) · Social Politics International Studies in Gender State & Society · doi:10.1093/sp/jxr011 · Cited by 37
Craig, J. M., Wolff, K. T., & Baglivio, M. T. (2022) · Child Abuse & Neglect · doi:10.1016/j.chiabu.2022.105878 · Cited by 39
Dropout intention: a valid predictor of actual dropout?
Findeisen, S., Brodsky, A., Michaelis, C., Schimmelpenningh, B., & Seifried, J. (2024) · Empirical research in vocational education and training · doi:10.1186/s40461-024-00165-1 · Cited by 36
“Higher entropy values indicate a better classification of the data, while an entropy above 0.80 indicates that the profile classification occurred with minimal uncertainty (Celeux and Soromenho 1996; Tein et al. 2013).”
BackgroundInfluentialHow to Model Heterogeneity in Costly Punishment: Insights from Responders' Response Times
Fischbacher, U., Hertwig, R., & Bruhin, A. (2013) · Journal of Behavioral Decision Making · doi:10.1002/bdm.1779 · Cited by 41
“To remedy this problem, Celeux and Soromenho (1996) proposed using the NEC.”
MethodParallel and serial reading processes in children’s word and nonword reading.
van den Boer, M., & de Jong, P. F. (2014) · Journal of Educational Psychology · doi:10.1037/a0037101 · Cited by 40
“In addition, entropy was used to evaluate the models, with a value close to 1 indicating low average likelihoods that a child assigned to one class could have been assigned to another (Celeux & Soromenho, 1996).”
MethodVariation in substance use relapse episodes among adolescents: A longitudinal investigation
Ramo, D. E., Prince, M. A., Roesch, S. C., & Brown, S. A. (2011) · Journal of Substance Abuse Treatment · doi:10.1016/j.jsat.2011.10.003 · Cited by 42
“…ensure a minimum level of good classification, entropy values that are close to 1.0 indicate that a model has clearly identified individuals of different types and it can be a useful summary measure (Celeux & Soromenho, 1996; Muthèn & Muthèn, 2000; Ramaswamy, DeSarbo, Reibstein, & Robinson, 1993).”
BackgroundInfluentialFlair, L. N. L., Reboussin, B. A., Storr, C. L., Letourneau, E. J., Green, K. M., Mojtabai, R., Pacek, L. R., Alvanzo, A. A. H., Cullen, B., & Crum, R. M. (2013) · Drug and Alcohol Dependence · doi:10.1016/j.drugalcdep.2013.03.012 · Cited by 40
“Entropy was used as a measure of classification accuracy distinction with values approaching 1 indicating a clear distinction of classes (Celeux and Soromenho, 1996).”
Unrestricted Mixture Models for Class Identification in Growth Mixture Modeling
Liu, M., & Hancock, G. R. (2014) · Educational and Psychological Measurement · doi:10.1177/0013164413519798 · Cited by 44
“…statistics were investigated in this study: entropy (Ramaswamy, DeSarbo, Reibstein, & Robinson, 1993), the normalized entropy criterion (NEC; Celeux & Soromenho, 1996), the integrated classification likelihood (ICL-BIC; McLachlan & Peel, 2000), and the classification likelihood information…”
MethodDevelopment of perceived job insecurity among young workers: a latent class growth analysis
Klug, K., Bernhard‐Oettel, C., Mäkikangas, A., Kinnunen, U. M., & Sverke, M. (2019) · International Archives of Occupational and Environmental Health · doi:10.1007/s00420-019-01429-0 · Cited by 43
“For entropy, values close to 1 indicate a clear classification (Celeux and Soromenho 1996).”
BackgroundGaining Insights into Aggressive Behaviour in Autism Spectrum Disorder Using Latent Profile Analysis
Sullivan, M. O., Gallagher, L., & Heron, E. A. (2019) · Journal of Autism and Developmental Disorders · doi:10.1007/s10803-019-04129-3 · Cited by 48
“Entropy values range from 0 to 1; higher values indicate superior predictive power (Celeux and Soromenho 1996).”
BackgroundXiao, F., & Sun, L. (2021) · Journal of Research on Technology in Education · doi:10.1080/15391523.2021.1876577 · Cited by 46
Normality-based validation for crisp clustering
Lago-Fernández, L. F., & Corbacho, F. (2009) · Pattern Recognition · doi:10.1016/j.patcog.2009.09.018 · Cited by 34
“There is a large literature that deals with cluster validation from different approaches [5, 6, 7, 8, 9, 10, 11, 12], both for crisp and fuzzy clustering.”
BackgroundPolyvictimization Across Social Contexts: Home, School, and Neighborhood Violence Exposure
Butcher, F., Holmes, M. R., Kretschmar, J. M., & Flannery, D. J. (2016) · Criminal Justice and Behavior · doi:10.1177/0093854816662679 · Cited by 35
“Entropy is a measure of the model’s ability to define classes accurately with values approaching 1 indicating a clear class separation (Celeux & Soromenho, 1996).”
BackgroundRoh, S., Lee, Y.-S., Lee, J. H., & Martin, J. I. (2013) · Aging & Mental Health · doi:10.1080/13607863.2013.848837 · Cited by 38
“…Sclove, 1987) – lower values suggest a better fitting model; (3) entropy that summarizes the extent to which a model generates classification errors (Celeux & Soromenho, 1996) – the larger the values and closer to 1, the less classification errors in the model; and (4) Vuong Lo Mendell Rubin…”
BackgroundLatent classes of PTSD symptoms in Iraq and Afghanistan female veterans
Hebenstreit, C. L., Madden, E., & Maguen, S. (2014) · Journal of Affective Disorders · doi:10.1016/j.jad.2014.04.061 · Cited by 37
Studer, J., Baggio, S., Mohler‐Kuo, M., Simon, O., Daeppen, J., & Gmel, G. E. (2015) · Journal of Gambling Studies · doi:10.1007/s10899-015-9547-9 · Cited by 41
“For AIC, BIC and ABIC, lower values indicate better fit (Yang 2006), whereas for entropy, values close to 1 indicate better fit (Celeux and Soromenho 1996).”
BackgroundNing, H. K., Lee, D. H. L., & Lee, W. O. (2015) · Teachers and Teaching · doi:10.1080/13540602.2015.1055447 · Cited by 46
Moran, L., Lengua, L. J., Zalewski, M., Ruberry, E., Klein, M., Thompson, S., & Kiff, C. (2017) · Journal of Research in Personality · doi:10.1016/j.jrp.2016.03.003 · Cited by 35
“Entropy was also examined, with values approaching 1 suggesting superior class identification (Celeux & Soromenho, 1996).”
MethodDropout typologies: Relating profiles of risk and support to later educational re-engagement
McDermott, E. R., Anderson, S., & Zaff, J. F. (2017) · Applied Developmental Science · doi:10.1080/10888691.2016.1270764 · Cited by 47
“Entropy is an index between 0 and 1, and a value closer to 1 indicates a higher level of accuracy in classifying people into profiles (Celeux & Soromenho, 1996).”
BackgroundGrest, C. V., Lee, J. O., Gilreath, T. D., & Unger, J. B. (2018) · Journal of Youth and Adolescence · doi:10.1007/s10964-017-0807-0 · Cited by 42
“…the Bayesian information criterion, entropy, an indicator of quality classification (ranging from 0 to 1, with higher scores indicating better fit; Celeux and Soromenho 1996), the Lo-Mendell-Rubin adjusted likelihood ratio test, the bootstrapped likelihood ratio test (Nylund et al. 2007; Tofighi…”
Yoneda, T. B., Ames, M. E., & Leadbeater, B. J. R. (2019) · Journal of Adolescence · doi:10.1016/j.adolescence.2019.03.009 · Cited by 41
Grit and peer relationships in early adolescence: A person-centered approach
Lan, X. (2020) · Journal of Social and Personal Relationships · doi:10.1177/0265407520921557 · Cited by 39
“Additionally, the entropy index (the uncertainty of classification; Celeux & Soromenho, 1996) was calculated.”
MethodTrajectories of suicidal ideation after first‐episode psychosis: a growth mixture modeling approach
Salagre, E., Grande, I., Jiménez, E., Mezquida, G., Cuesta, M. J., Llorente, C., Amoretti, S., Lobo, A., González-Pinto, A. M., Carballo, J. J., et al. (2021) · Acta Psychiatrica Scandinavica · doi:10.1111/acps.13279 · Cited by 39
Brett, B. L., Walton, S. R., Kerr, Z. Y., Nelson, L. D., Chandran, A. S., DeFreese, J. D., Echemendía, R. J., Guskiewicz, K. M., Meehan, W. P., III, & McCrea, M. (2021) · Journal of Neurology Neurosurgery & Psychiatry · doi:10.1136/jnnp-2020-324244 · Cited by 35
Typologies of coping in young adults in the context of the COVID-19 pandemic
Shigeto, A., Laxman, D. J., Landy, J. F., & Scheier, L. M. (2021) · The Journal of General Psychology · doi:10.1080/00221309.2021.1874864 · Cited by 37
“The statistic ranges from 0 to 1, where higher numbers indicate less class misspecification (Celeux & Soromenho, 1996).”
BackgroundHanlon, S. L., Pohlig, R. T., & Silbernagel, K. G. (2021) · Journal of Orthopaedic and Sports Physical Therapy · doi:10.2519/jospt.2021.10271 · Cited by 36
Development of the Addiction Dimensions for Assessment and Personalised Treatment (ADAPT)
Marsden, J., Eastwood, B., Ali, R. L., Burkinshaw, P., Chohan, G., Copello, A. G., Burn, D., Kelleher, M., Mitcheson, L., Taylor, S., et al. (2014) · Drug and Alcohol Dependence · doi:10.1016/j.drugalcdep.2014.03.018 · Cited by 45
Bootstrap methods for measuring classification uncertainty in latent class analysis
Dias, J. G., & Vermunt, J. K. (2007) · Physica-Verlag eBooks · doi:10.1007/978-3-7908-1709-6_3 · Cited by 35
“Its normalized version has been used as a model selection criterion indicating the level of separation of components [ CS96 ].”
MethodImproved statistics estimation and feature extraction for hyperspectral data classification
Kuo, B., & Landgrebe, D. A. (2001) · Cited by 35
Wullenkord, M. C., Johansson, M. V., Loy, L. S., Menzel, C., & Reese, G. (2024) · Journal of Environmental Psychology · doi:10.1016/j.jenvp.2024.102278 · Cited by 46
Patrick, M. E., Berglund, P. A., Joshi, S., & Bray, B. C. (2020) · Drug and Alcohol Dependence · doi:10.1016/j.drugalcdep.2020.108018 · Cited by 41
“Optimal model selection was based on the Akaike information criterion (AIC; Akaike, 1974), Bayesian information criterion (BIC; Schwartz, 1978), consistent AIC (CAIC; Bozdogan, 1987), sample size adjusted BIC (aBIC; Sclove, 1987), AIC3 (Andrews and Currim, 2003), and entropy (Celeux and Soromenho, 1996), as well as mo…”
MethodGottert, A., Pulerwitz, J., Heck, C. J., Cawood, C., & Mathur, S. (2020) · Journal of the International AIDS Society · doi:10.1002/jia2.25518 · Cited by 32
“The closer the entropy value is to 1, the stronger the separation between classes [43].”
BackgroundWantchekon, K. A., & Umaña-Taylor, A. J. (2021) · Journal of Youth and Adolescence · doi:10.1007/s10964-021-01451-x · Cited by 34
Justice, L. M., Jiang, H., Purtell, K. M., Lin, T., & Ansari, A. (2021) · Early Education and Development · doi:10.1080/10409289.2021.1946762 · Cited by 44
“…lower is better), the LMR adjusted likelihood ratio test (a significant p -value rejects the k -1 profile model in favor of the k profile model; Lo et al., 2001; Vuong, 1989), and the entropy statistic (values approaching one indicates higher classification accuracy; Celeux & Soromenho, 1996).”
Gulliver, P. J., & Fanslow, J. (2015) · Journal of Child Custody · doi:10.1080/15379418.2015.1037051 · Cited by 42
“The entropy value obtained for the three classes suggested that class assignment was comparatively stable (Celeux & Soromenho, 1996).”
BackgroundBecht, A., Prinzie, P., Deković, M., van den Akker, A. L., & Shiner, R. L. (2015) · Development and Psychopathology · doi:10.1017/s0954579415000577 · Cited by 46
“Entropy values range between 0 and 1, with 0 corresponding to randomness and 1 to a perfect classification (Celeux & Soromenho, 1996).”
BackgroundA Validation of the Factor Structure of OQ-45 Scores Using Factor Mixture Modeling
Kim, S., Beretvas, S. N., & Sherry, A. R. (2009) · Measurement and Evaluation in Counseling and Development · doi:10.1177/0748175609354616 · Cited by 40
“The normalized entropy criterion (NEC; Celeux & Soromenho, 1996) can also be used to choose the optimal number of classes for an FMM.”
MethodLiu, H., Li, X., & Guo, G. (2025) · IRAL - International Review of Applied Linguistics in Language Teaching · doi:10.1515/iral-2024-0013 · Cited by 44
“In addition, the entropy is examined, which represents the overall ability of a mixture model to return well-separated pro fi les and Soromenho 1996).”
Patterns of Poly-Victimization in a Sample of At-Risk Youth
Kretschmar, J. M., Tossone, K., Butcher, F., & Flannery, D. J. (2016) · Journal of Child & Adolescent Trauma · doi:10.1007/s40653-016-0109-9 · Cited by 40
Akoğul, S., & Erişoğlu, M. (2016) · Mathematical and Computational Applications · doi:10.3390/mca21030034 · Cited by 33
Contreras‐Reyes, J. E., & Cortés, D. (2016) · Entropy · doi:10.3390/e18110382 · Cited by 33
Prolonged grief and posttraumatic stress in bereaved children: A latent class analysis
Boelen, P. A., Spuij, M., & Reijntjes, A. H. A. (2017) · Psychiatry Research · doi:10.1016/j.psychres.2017.09.002 · Cited by 36
“We also considered entropy, which has values between 0 and 1, with higher values indicating better model fi t (Celeux and Soromenho, 1996).”
Shokoohi, M., Bauer, G. R., Kaida, A., Logie, C. H., Lacombe‐Duncan, A., Milloy, M., Lloyd‐Smith, E., Carter, A., & Loutfy, M. R. (2019) · Addiction · doi:10.1111/add.14566 · Cited by 38
“Two supporting statistics were also reported: Entropy as a measure of classification accuracy, with values approaching to 1 indicating better class separation [46], and the percentage of seeds associated with the fitting models, with values close to 100% indicating they were unlikely to have hit the local maxima.”
MethodDiscrimination based on sexual orientation against MSM in Brazil: a latent class analysis
Magno, L., da Silva, L. A. V., Guimarães, M. D. C., Veras, M. A. D. S. M., de Deus, L. F. A., Leal, A. F., Knauth, D. R., de Brito, A. M., Rocha, G. M., Lima, L. N. G. C., et al. (2019) · Revista Brasileira de Epidemiologia · doi:10.1590/1980-549720190003.supl.1 · Cited by 36
Predicting patterns of service utilization within children’s mental health agencies
Reid, G. J., Stewart, S. L., Barwick, M. A., Carter, J., Leschied, A. W., Neufeld, R. W. J., Pierre, J. S., Tobon, J. I., Vingilis, E. R., & Zaric, G. S. (2019) · BMC Health Services Research · doi:10.1186/s12913-019-4842-2 · Cited by 34
Cuesta-Vargas, A., Neblett, R., Nijs, J., Chiarotto, A., Kregel, J., van Wilgen, C. P., Pitance, L., Knezevic, A., Gatchel, R., Mayer, T., et al. (2020) · Pain medicine (Malden, Mass.) · doi:10.1093/pm/pnaa210 · Cited by 32
Conway, A., Krawczyk, N., McGaffey, F., Doyle, S., Baaklini, V., Marshall, A., Treloar, C., Davis, C., Colledge-Frisby, S., Grebely, J., et al. (2023) · The International journal on drug policy · doi:10.1016/j.drugpo.2023.104141 · Cited by 28
Latent Class Models in Social Work
Neely-Barnes, S. L. (2010) · Social Work Research · doi:10.1093/swr/34.2.114 · Cited by 34
Assessing the Number of Components in Mixture Models: an OverviewPreprint
Brochado, A. M., & Martins, F. V. (2005) · RePEc: Research Papers in Economics · Cited by 33
Worsley, A., Wang, W., Byrne, S., & Yeatman, H. R. (2014) · Journal of Nutritional Science · doi:10.1017/jns.2014.12 · Cited by 34
“Entropy is a measure of classification accuracy((36)), ranging from 0 to 1, higher values indicating better classification.”
BackgroundYu, H., & Park, J. (2014) · Multivariate Behavioral Research · doi:10.1080/00273171.2014.900431 · Cited by 32
“Several studies reported the tendencies to overestimate the number of latent classes (e.g., Celeux & Soromenho, 1996; Dias, 2004; Soromenho, 1993).”
BackgroundAtomic dynamic functional interaction patterns for characterization of ADHD
Ou, J., Lian, Z., Xie, L. Y., Li, X., Wang, P., Hao, Y., Zhu, D., Jiang, R., Wang, Y., Chen, Y., et al. (2014) · Human Brain Mapping · doi:10.1002/hbm.22548 · Cited by 34
“…in cluster analysis, and there are many validation methods [e.g., Fraley and Raftery, 2011; Halkidi et al., 2001], for instance, the Bayesian information criterion (BIC) [Schwarz, 1978], the entropy criterion [Celeux and Soromenho, 1996], and the gap statistic approach [Tibshir-ani et al., 2001].”
MethodNurses’ Beliefs About Caring for Patients With Traumatic Brain Injury
Oyesanya, T. O., Thomas, M. A., Brown, R., & Turkstra, L. S. (2016) · Western Journal of Nursing Research · doi:10.1177/0193945916636629 · Cited by 43
“Authors assessed (a) interpretability; (b) theoretical justification; (c) parsimony; (d) entropy variable > 0.7 (Celeux & Soromenho, 1996); (e) the lowest Akaike’s information criterion (AIC), Bayesian information criterion (BIC), and adjusted BIC (Fraley & Raftery, 1998); (f) average posterior…”
BackgroundInfluentialContribution of HVSR measures for seismic microzonation studies
Martorana, R., Capizzi, P., D’Alessandro, A., Luzio, D., Stefano, P. D., Renda, P., & Zarcone, G. (2018) · Annals of Geophysics · doi:10.4401/ag-7786 · Cited by 32
“Following Celeux and Soromenho (1996), the cut level was determined using internal entropy level criterion to maximize the homogeneity within classes.”
MethodCents-Boonstra, M., Lichtwarck‐Aschoff, A., Denessen, E. J. P. G., Haerens, L. L., & Aelterman, N. (2018) · Journal of Vocational Education and Training · doi:10.1080/13636820.2018.1549092 · Cited by 47
“In addition, entropy gives an indication of the precision with which cases are classi fi ed into the pro fi le, with values closer to 1 indicating a better classi fi cation (Celeux and Soromenho 1996).”
Seed selection algorithm through K-means on optimal number of clusters
Chowdhury, K., Chaudhuri, D., Pal, A. K., & Samal, A. K. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-7100-4 · Cited by 36
Family Emotional Climate and Children with Autism Spectrum Disorder
Hickey, E., Nix, R. L., & Hartley, S. L. (2019) · Journal of Autism and Developmental Disorders · doi:10.1007/s10803-019-04037-6 · Cited by 42
Initiative, A. D. N., Ezzati, A., Zammit, A. R., Habeck, C. G., Hall, C. B., & Lipton, R. B. (2019) · Brain Imaging and Behavior · doi:10.1007/s11682-019-00115-6 · Cited by 33
Gini, G., Marino, C., Xie, J.-Y., Pfetsch, J. S., & Pozzoli, T. (2019) · Cyberpsychology Journal of Psychosocial Research on Cyberspace · doi:10.5817/cp2019-4-1 · Cited by 42
“Moreover, we used entropy to indicate quality of correct classification (entropy ranges between 0 and 1, with values higher than 0.80 indicating good classification quality; Celeux & Soromenho, 1996).”
MethodInfluentialDistinct Symptom Experience Among Subgroups of Patients With ESRD Receiving Maintenance Dialysis
Ng, M. S. N., Miaskowski, C. A., Cooper, B. A., Hui, Y. H., Ho, E. H. S., Mo, S. K. L., Wong, S. S. H., Wong, C. L., & So, W. K. W. (2020) · Journal of Pain and Symptom Management · doi:10.1016/j.jpainsymman.2020.01.004 · Cited by 34
Latent class analysis of bipolar disorder symptoms and suicidal ideation and behaviors
Au, J. S., de Andino, A. M., Mekawi, Y., Silverstein, M. W., & Lamis, D. A. (2020) · Bipolar Disorders · doi:10.1111/bdi.12967 · Cited by 31
Henson, J. M., Pearson, M. R., & Carey, K. B. (2015) · Journal of Consulting and Clinical Psychology · doi:10.1037/a0038897 · Cited by 38
“…statistic of .83 in the data, surpassing the five- and seven-class solutions (entropies .79 and .76, respectively), which indicated better classification in the data (Celeux & Soromenho, 1996); entropy statistics for the 2 to 4 class solutions were as follows: .83, .80, and .89, respectively.”
A Cross-Cultural Comparison of Symptom Reporting and Symptom Clusters in Heart Failure
Park, J., & Johantgen, M. E. (2016) · Journal of Transcultural Nursing · doi:10.1177/1043659616651673 · Cited by 32
“In addition, the entropy R2 provides an indication of the overall degree of classification uncertainty in the solution (Celeux & Soromenho, 1996).”
BackgroundStressful Life Event Experiences of Pregnant Women in the United States: A Latent Class Analysis
Mukherjee, S., Coxe, S. J., Fennie, K., Madhivanan, P., & Trepka, M. J. (2016) · Women s Health Issues · doi:10.1016/j.whi.2016.09.007 · Cited by 37
Finite Mixture Models in Market Segmentation: A Review and Suggestions for Best Practices
Tuma, M. N., & Decker, R. (2013) · The Electronic Journal of Business Research Methods · Cited by 42
Elissen, A. M. J., Hertroijs, D. F. L., Schaper, N. C., Bosma, H., Dagnelie, P. C., Henry, R. M., van der Kallen, C. J., Koster, A., Schram, M. T., Stehouwer, C. D. A., et al. (2017) · PLOS ONE · doi:10.1371/journal.pone.0182053 · Cited by 31
“Higher entropy values indicate less ambiguity in class allocation [33].”
BackgroundRegularized Mixture Density Estimation With an Analytical Setting of Shrinkage Intensities
Halbe, Z., Bortman, M., & Aladjem, M. E. (2013) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2012.2234477 · Cited by 31
“Usually [4, Ch. 7], several models are considered and an appropriate one is chosen using a model selection criterion.”
MethodProfiles of Non-Suicidal Self-Injurers and Associated Patterns of Alcohol Use
Bracken, K. L., McDevitt‐Murphy, M. E., & Parra, G. R. (2012) · Journal of Psychopathology and Behavioral Assessment · doi:10.1007/s10862-012-9306-5 · Cited by 33
“number of classes in a model solution (Celeux and Soromenho 1996; Nylund et al. 2007), BIC is considered by some to be more accurate by having higher penalties for increased model parameters (Nylund et al.”
BackgroundWang, B., Eastwood, P. R., Becker, A., Isensee, C., Wong, J. W. Y., Huang, R., Runions, K., Stewart, R. M., Meyer, T., Brüni, L. G., et al. (2018) · SLEEP · doi:10.1093/sleep/zsy243 · Cited by 35
“Entropy values range from 0 to 1, with 0 corresponding to randomness and 1 to a perfect classification [61].”
BackgroundEstablishment and replication of emotion regulation profiles: implications for psychological health
Chesney, S. A., Timmer‐Murillo, S. C., & Gordon, N. S. (2019) · Anxiety Stress & Coping · doi:10.1080/10615806.2019.1573990 · Cited by 39
“Higher entropy values (i.e., values approaching 1) indicate better model classification of individuals into groups (Celeux & Soromenho, 1996).”
BackgroundProteus Effect Profiles: how Do they Relate with Disordered Gaming Behaviours?
Stavropoulos, V., Pontes, H. M., Gomez, R., Schivinski, B., & Griffiths, M. D. (2020) · Psychiatric Quarterly · doi:10.1007/s11126-020-09727-4 · Cited by 32
Kremer, K. P., Poon, C. Y. S., Jones, C. L., Hagler, M., Kupersmidt, J. B., Stelter, R. L., Stump, K. N., & Rhodes, J. E. (2020) · Journal of Child and Family Studies · doi:10.1007/s10826-020-01822-1 · Cited by 43
Determining the role of eudaimonic values in conservation behavior
Winkler‐Schor, S., van Riper, C. J., Landon, A. C., & Keller, R. (2020) · Conservation Biology · doi:10.1111/cobi.13622 · Cited by 35
“The preferred model had the lowest AIC and BIC values (Kuha 2004), entropy ≥0.80 (Celeux & Soromenho 1996), and a BLRT value indicating the addition of another latent profile would not significantly improve model fit (McLachlan 1987).”
BackgroundInfluentialUsing Normalized Entropy to Measure Uncertainty of Rankings for Network Meta-analyses
Wu, Y., Shih, M., & Tu, Y. (2021) · Medical Decision Making · doi:10.1177/0272989x21999023 · Cited by 34
Discrete Latent Variable Models
Bartolucci, F., Pandolfi, S., & Pennoni, F. (2021) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-040220-091910 · Cited by 39
DeMartini, K. S., Prince, M. A., & Carey, K. B. (2013) · Drug and Alcohol Dependence · doi:10.1016/j.drugalcdep.2013.02.020 · Cited by 37
Model Selection for the Binary Latent Class Model: A Monte Carlo Simulation
Dias, J. G. (2006) · Springer eBooks · doi:10.1007/3-540-34416-0_11 · Cited by 31
A longitudinal person-centred approach to the job demands-control model
Mauno, S., Mäkikangas, A., & Kinnunen, U. M. (2016) · European Journal of Work and Organizational Psychology · doi:10.1080/1359432x.2016.1187135 · Cited by 46
“…criterion (AIC), (2) the Bayesian information criterion (BIC), (3) the adjusted Bayesian information criterion (aBIC), (4) entropy values (Celeux & Soromenho, 1996), (5) the Lo– Mendell–Rubin (LMR) test, (6) the Vuong–Lo–Mendel– Rubin (VLMR) test, (7) the bootstrap likelihood ratio test…”
MethodSELF‐CONTROL AND ADOLESCENT INTERNALIZING AND EXTERNALIZING PROBLEMS: NEIGHBORHOOD‐BASED DIFFERENCES
McDermott, E. R., Donlan, A. E., Anderson, S., & Zaff, J. F. (2017) · Journal of Community Psychology · doi:10.1002/jcop.21848 · Cited by 35
Neurocognitive functioning in adolescents with non-suicidal self-injury
Mürner-Lavanchy, I. M., Koenig, J., Lerch, S., van der Venne, P., Höper, S., Resch, F., & Kaess, M. (2022) · Journal of Affective Disorders · doi:10.1016/j.jad.2022.05.029 · Cited by 37
Pre-clinical Cognitive Phenotypes for Alzheimer Disease: A Latent Profile Approach
Hayden, K. M., Kuchibhatla, M. N., Romero, H., Plassman, B. L., Burke, J. R., Browndyke, J. N., & Welsh-Bohmer, K. A. (2013) · American Journal of Geriatric Psychiatry · doi:10.1016/j.jagp.2013.07.008 · Cited by 34
“(42) Latent profile models were evaluated with the following methods: Vuong-LoMendell-Rubin likelihood ratio test, (43, 44) the −2LL χ2(for nested models), sample size adjusted BIC (SABIC), examination of the posterior probability classification table, entropy (45, 46), profile size, and face validity (for review of L…”
Metadata
- Authors
- Celeux, G., & Soromenho, G.
- Affiliations
- Institut national de recherche en sciences et technologies du numérique (FR)
- University of Lisbon (PT)
- ORCID
- Soromenho, Gilda
- Venue
- Journal of Classification
- Published
- 1996-09
- Volume
- 13
- Issue
- 2
- Pages
- 195-212
- ISSN
- 0176-4268 (ISSN-L)
- 1432-1343
- OpenAlex
- W2079817125
- Cited by
- 2,448
- References
- 37
- Citations by year
- 2026: 248 · 2025: 223 · 2024: 213 · 2023: 208 · 2022: 184 · 2021: 204 · 2020: 176 · 2019: 183 · 2018: 112 · 2017: 100 · 2016: 105 · 2015: 92 · 2014: 85 · 2013: 75 · 2012: 49
- FWCI
- 1.91
- Type
- journal article
- Language
- en
- Open access
- green
- inria.hal.science
- Licence
- other-oa
- www.springer.com/tdm (tdm)
- Locations
- Journal of Classification (publishedVersion)
- OpenGrey (Institut de l'Information Scientifique et Technique) (submittedVersion)
- HAL (submittedVersion, other-oa)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Methods and Mixture Models
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Clustering Algorithms Research
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Keywords
- entropy criterion, number of clusters, mixture models, model selection, likelihood ratios, optimal number of clusters
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.