When longitudinal data are modeled, the longitudinal DCM is used to measure the change in the attribute profiles and mastery status over time.Ĭurrently, two types of longitudinal DCMs have been proposed to analyze longitudinal data in the DCM framework. However, most applications of DCMs are static, meaning that DCMs are used to classify individuals at a single time point. DCMs have also been applied in one large-scale assessment program (Dynamic Learning Maps ® alternate assessment DLM ® Dynamic Learning Maps, 2016) to detect distinct patterns of skill mastery for students with significant cognitive disabilities. In addition, some researchers successfully demonstrated the practical uses of DCMs in test development ( Bradshaw et al., 2014). For example, DCMs have been retrofitted to existing large-scale assessments to identify examinees' mastery status of tested skills (e.g., Lee and Sawaki, 2009 George and Robitzsch, 2014 Sedat and Arican, 2015 Ravand, 2016). Since the traditional scale scores (e.g., IRT scores) have limits in providing enough information to inform classroom instruction and learning (e.g., de La Torre, 2009), DCMs have received growing attention in the educational measurement community as well as from educational practitioners in recent years.ĭCMs have been increasingly used for empirical data analysis in recent years. DCMs provide fine-grained and multidimensional diagnostic information, which could help educators adjust classroom instruction and improve student learning. DCMs evaluate the student's mastery status on each latent variable from a set of narrowly defined latent variables, referred to attributes in the DCM literature, and then classify students into attribute profiles that were determined as a priori ( DiBello et al., 1995). (4) Overall, the proposed model achieved acceptable recoveries on both the fixed and random effects in the generalized growth curve model.ĭiagnostic classification models (DCMs e.g., Rupp et al., 2010), also referred to as cognitive diagnosis models (CDMs e.g., Leighton and Gierl, 2007), are defined as a family of confirmatory multidimensional latent-variable models with categorical latent variables ( Rupp et al., 2010). The interaction effect parameters had a relatively large bias under the condition with a small sample size and fewer measurement occasions however, the recoveries were improved as the sample size and the number of measurement occasions increased. (3) Both the intercept and main effect parameters in the LCDM were recovered well. Cohen's kappa increased as the number of measurement occasions increased. For individuals who truly mastered the attributes, the correct classification rates increased as the measurement occasions increased however, for individuals who truly did not master the attributes, the correct classification rates decreased slightly as the numbers of measurement occasions increased. However, the correct classification rates depended on the cut point that was used to classify individuals. (2) Regarding the classification accuracy, the proposed model achieved good recoveries on the probabilities of attribute mastery. The results revealed the following: (1) In general, the proposed model provided good convergence rates under different conditions. One simulation study was conducted to evaluate the proposed model in terms of the convergence rates, the accuracy of classification, and parameter recoveries under different combinations of four design factors: the sample size, the growth patterns, the G matrix design, and the number of measurement occasions. The proposed model represents an improvement in the current longitudinal DCMs given its ability to incorporate both balanced and unbalanced data and to measure the growth of a single attribute directly without assuming that attributes grow in the same pattern. 2Institutional Research and Assessment, Howard University, Washington, DC, United StatesĪ multivariate longitudinal DCM is developed that is the composite of two components, the log-linear cognitive diagnostic model (LCDM) as the measurement model component that evaluates the mastery status of attributes at each measurement occasion, and a generalized multivariate growth curve model that describes the growth of each attribute over time.1Department of Educational Psychology, The University of Kansas, Lawrence, KS, United States. ![]() Qianqian Pan 1 *, Lu Qin 2 and Neal Kingston 1
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |