MIMIC Models: from Neuroscience to Health Sciences
Article Sidebar
Main Article Content
Abstract
In medicine, situations are often encountered where regression (linear or logistic) is not feasible, due to latent constructs or factors that include several observed variables, since they try to reflect or estimate complex multidimensional phenomena. This limitation led to the search for alternative statistical methodologies, such as a subtype of Structural Equation Models called MIMIC (Multiple Indicators Multiple Causes) models, originally used in neurosciences. In this issue we explain what these models are, what they are used for, as well as the programs for their application, and the interpretation of results.
It is exemplified with a study on the quality of life of people who received a transplant, highlighting the graphical representation and the importance of parsimony in the models. These models allow the simultaneous inclusion of factors and single variables, solving complex causal relationships, making them useful tools in medical research.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
How to Cite
References
Rosen AFG, Auger E, Woodruff N, et al. The multiple indicator multiple cause model for cognitive neuroscience: an analytic tool which emphasizes the behavior in brain-behavior relationships. Front Psychol. 2022;13:943613. https://doi.org/10.3389/fpsyg.2022.943613. DOI: https://doi.org/10.3389/fpsyg.2022.943613
Costantini L, Pasquarella C, Odone A, et al. Screening for depression in primary care with Patient Health Questionnaire-9 (PHQ-9): a systematic review. J Affect Disord. 2021;279:473-483. https://doi.org/10.1016/j.jad.2020.09.131. DOI: https://doi.org/10.1016/j.jad.2020.09.131
Liu T, Peng MM, Wong FHC, et al. Differential associations between depressive symptom-domains with anxiety, loneliness, and cognition in a sample of community older chinese adults: a multiple indicators multiple causes approach. Innov Aging. 2023;7(7):igad075. https://doi.org/10.1093/geroni/igad075. DOI: https://doi.org/10.1093/geroni/igad075
Rubio L, Dumitrache CG, García AJ, et al. Coping strategies in Spanish older adults: a MIMIC model of socio-demographic characteristics and activity level. Aging Ment Health. 2018;22(2):226-232. https://doi.org/10.1080/13607863.2016.1247416. DOI: https://doi.org/10.1080/13607863.2016.1247416
Jöreskog KG, Goldberger AS. Estimation of a model with multiple indicators and multiple causes of a single latent variable. J Am Stat Assoc. 1975;70(351):631-639. https://doi.org/10.1080/01621459.1975.10482485. DOI: https://doi.org/10.1080/01621459.1975.10482485
Muthén BO. Goodness of fit with categorical and other nonnormal variables. En: Bollen KA, Long JS, editors. Testing structural equation models. Newbury Park, CA: Sage; 1993. p. 205-234.
Muthén B, du Toit SH, Spisic D. Robust inference using weighted least squares and quadratic estimating equations in latent variable modeling with categorical and continuous outcomes: technical report [Internet]. Los Angeles, CA: University of California; 1997 [consulta 2024 mar 01]. Disponible en https://www.statmodel.com/download/Article_075.pdf.
Flora DB, Curran PJ. An empirical evaluation of alternative methods of estimation for confirmatory factor analysis with ordinal data. Psychol Methods. 2004;9(4):466-491. https://doi.org/10.1037/1082-989X.9.4.466. DOI: https://doi.org/10.1037/1082-989X.9.4.466
Schumacker RE, Lomax RG. A beginner’s guide to structural equation modeling. 3rd ed. New York, NY: Routledge; 2012. DOI: https://doi.org/10.4324/9780203851319
Tekwe CD, Carter RL, Cullings HM, et al. Multiple indicators, multiple causes measurement error models. Stat Med. 2014;33(25):4469-4481. https://doi.org/10.1002/sim.6243. DOI: https://doi.org/10.1002/sim.6243
Espinoza-Bello M, Galindo-Vázquez Ó, Jiménez-Ríos MA, et al. Propiedades psicométricas de la Escala de Evaluación Funcional para el Tratamiento del Cáncer, versión próstata (FACT-P), en pacientes mexicanos. Cir Cir. 2020;88(6):745-752. https://doi.org/10.24875/CIRU.19001755. DOI: https://doi.org/10.24875/CIRU.19001755
Chang C, Gardiner J, Houang R, et al. Comparing multiple statistical software for multiple-indicator, multiple-cause modeling: an application of gender disparity in adult cognitive functioning using MIDUS II dataset. BMC Med Res Methodol. 2020;20(1):275. https://doi.org/10.1186/s12874-020-01150-4. DOI: https://doi.org/10.1186/s12874-020-01150-4
Littlewood Zimmerman HF. Mi primer modelamiento de ecuación estructural LISREL. 3ª ed. México: DF; 2022 [consulta 2024 mar 01]. Disponible en: https://www.researchgate.net/publication/364844144_Mi_primer_modelamiento_de_ecuacion_estructural_LISREL.
Zaky HHM, Armanious DM, Kalliny MA. Applying the structural equation model approach to study the simultaneous relationship between women's empowerment and mental disorder in Egypt. BMC Womens Health. 2024;24(1):26. https://doi.org/10.1186/s12905-023-02863-6. DOI: https://doi.org/10.1186/s12905-023-02863-6
Moral de la Rubia J, López Rosales F. Modelo recursivo de reacción violenta en parejas válido para ambos sexos. Bol Psicol. 2012;(105):61-74.