This study introduces a longitudinal diagnostic classification model, called the LTA+HDCM, which is a fusion of latent transition analysis (LTA; Collins & Flaherty, 2002; Collins & Wugalter, 1992) and the hierarchical diagnostic classification model (HDCM; Templin & Bradshaw, 2014). The primary goals in this study are (1) to evaluate the adequacy of the LTA+HDCM to recover the order of theoretical levels of learning progressions (LPs) with attributes in a linear hierarchy, and (2) to recover measurement model parameters (item and person parameters) and structural model parameters (latent status prevalences and transition probabilities) under different study conditions in which the LTA+HDCM is employed. A simulation study is used to achieve the study goals. The design factors are selected to reflect aspects of the measurement model that can be manipulated to infer learners' statuses on LP levels: number of measurement occasions T = (2, 3), test lengths consisting of J = (12, 18, 24) items, Q-matrix designs consisting of Q = (3, 6) item types, and sample sizes N = (500, 1000, 1500). Convergence rates, X[superscript 2] goodness-of-fit statistics, classification accuracy statistics, and graphical displays are used to evaluate the adequacy of the model to achieve the study goals. An empirical study using data from the Mathematization in Science (MTS; Jin et al., 2019) LP is then conducted to recover LP levels. The simulation study identified three important design factors which impacted the ability of the LTA+HDCM to recover LP theoretical levels and evidence and competency growth parameters. These factors are test length J, sample size N, and Q-matrix design. Of the three factors, complexity of Q-matrix design is most influential in recovery of LP theoretical levels and evidence and competency growth model parameter. In study conditions in which the Complete Q-matrix design (Q = 6 item types) was implemented, the LTA+HDCM fully recovered LP theoretical levels and provided ignorable bias of parameter estimates. In contrast, LP theoretical levels and parameters were only partially recovered in study conditions with the Partial Q-matrix design (Q = 3 item types). [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.]