My dissertation research explored responder behaviors (e.g., demonstrating response styles, carelessness, and possessing misconceptions) that compromise psychometric quality and impact the interpretation and use of assessment results. Identifying these behaviors can help researchers understand and minimize their potentially construct-irrelevant…

A research question that is of interest across many disciplines is whether and how relationships in a network are related to the attributes of the nodes of the network. In this dissertation, we propose two joint frameworks for modeling the relationship between the network and attributes. In the joint latent space model in Chapter 2, shared latent…

This study investigated teacher-driven change efforts. A review of existing literature posits that the current education system is largely driven by top-down mandates, such as the implementation of evidence-based practices generated by large scale and randomized controlled trials. While these approaches provide the field with important knowledge,…

Personalized learning, which has the potential to raise student achievement, requires understanding the competencies of students. Visualizations can help provide this understanding. Jeon et al. (2021) presented a latent space model that creates interaction maps visualizing response patterns from item response data. My dissertation proposes…

Binary item response theory (IRT) models are widely used in educational testing data. These models are not perfect because they simplify the individual item responding process, ignore the differences among different response patterns, cannot handle multidimensionality that lay behind options within a single item, and cannot manage missing response…

When measuring latent constructs, for example, language ability, we use statistical models to specify appropriate relationships between the latent construct and observe responses to test items. These models rely on theoretical assumptions to ensure accurate parameter estimates for valid inferences based on the test results. This dissertation…

Educational research outcomes frequently rely on an assumption that measurement metrics have interval-level properties. While most investigators know enough to be suspicious of interval-level claims, and in some cases even question their findings given such doubts, there is a lack of understanding regarding the measurement conditions that create…

Response processes are an important component of validity to support the use and interpretation of test scores. Response processes information can provide insight into how students engage with assessment tasks and the type of errors made when solving items, as well as allow for the study of cognitive properties in items that may be associated with…

The Q-diffusion model is a cognitive process model that considers decision making as an unobservable information accumulation process. Both item and person parameters decide the trace line of the cognitive process, which further decides observed response and response time. Because the likelihood function for the Q-diffusion model is intractable,…

There is growing consensus that data-informed decision-making through human-centered inquiry and design process results in improved outcomes for designed artifacts. Among the latest trends is a group of tools and processes loosely assimilated under the umbrella term, "design thinking." These "designerly ways of knowing" are…

This study examined whether athletic training students in a four-year undergraduate entry-level accredited athletic training program in a postsecondary institution perceived the PEARLS model as effective in providing feedback. Although students look to the feedback process to help them better understand their skill and performance level when…

Item Response Theory (IRT) models are a popular analytic method for self report data. We show how traditional IRT models can be vulnerable to specific kinds of asymmetric measurement error (AME) in self-report data, because the models spread the error to all estimates -- even those of items that do not contribute error. We quantify the impact of…

While countless studies have collected data on the effectiveness of various problem-solving models, few have attempted to identify which components of the training process are helpful to participants. Two teacher teams consisting of seven participants were trained in an adapted version of the Team-initiated Problem Solving (TIPS) model, observed…

Fitting wrongly specified models to observed data may lead to invalid inferences about the model parameters of interest. The current study investigated the performance of the posterior predictive model checking (PPMC) approach in detecting model-data misfit of the hierarchical rater model (HRM). The HRM is a rater-mediated model that incorporates…

The observation and supervision of New Jersey educators stand as a critical professional component to ensure that school staff is provided with timely feedback about their performance and recommendations and support for continual improvement. As a result of the TeachNJ Act (2012), efforts were made to formalize this process across New Jersey's…