A semiparametric approach for item response function estimation to detect item misfit.

When scaling data using item response theory, valid statements based on the measurement model are only permissible if the model fits the data. Most item fit statistics used to assess the fit between observed item responses and the item responses predicted by the measurement model show significant weaknesses, such as the dependence of fit statistics on sample size and number of items. In order to assess the size of misfit and to thus use the fit statistic as an effect size, dependencies on properties of the data set are undesirable. The present study describes a new approach and empirically tests it for consistency. We developed an estimator of the distance between the predicted item response functions (IRFs) and the true IRFs by semiparametric adaptation of IRFs. For the semiparametric adaptation, the approach of extended basis functions due to Ramsay and Silverman (2005) is used. The IRF is defined as the sum of a linear term and a more flexible term constructed via basis function expansions. The group lasso method is applied as a regularization of the flexible term, and determines whether all parameters of the basis functions are fixed at zero or freely estimated. Thus, the method serves as a selection criterion for items that should be adjusted semiparametrically. The distance between the predicted and semiparametrically adjusted IRF of misfitting items can then be determined by describing the fitting items by the parametric form of the IRF and the misfitting items by the semiparametric approach. In a simulation study, we demonstrated that the proposed method delivers satisfactory results in large samples (i.e., N ≥ 1,000).

Deciding between the Covariance Analytical Approach and the Change-Score Approach in Two Wave Panel Data.

The manuscript focuses on effects in nonrandomized studies with two outcome measurement occasions and one explanatory variable, and in which groups already differ at the pretest. Such study designs are often encountered in educational and instructional research. Two prominent approaches to estimate effects are (1) covariance analytical approaches and (2) latent change-score models. In current practice, both approaches are applied interchangeably, without a clear rationale for when to use which approach. The aim of this contribution is to outline under which conditions the approaches produce unbiased estimates of the instruction effect. We present a theoretical data generating model in which we decompose the variances of the relevant variables, and examine under which data generating conditions the estimated instruction effect is unbiased. We show that, under specific assumptions, both methods can be used to answer the general question of whether instruction has an effect. Another implication from the results is that practitioners need to consider which underlying data generating assumptions the approaches make, since a violation of those assumptions will lead to biased effects. Based on our results, we give recommendations for preferable research designs.

The Role of Relatedness in the Motivation and Vitality of University Students in Online Classes During Social Distancing.

As part of the social distancing measures for preventing the spread of COVID-19, many university courses were moved online. There is an assumption that online teaching limits opportunities for fostering interpersonal relationships and students' satisfaction of the basic need for relatedness - reflected by experiencing meaningful interpersonal connections and belonging - which are considered important prerequisites for student motivation and vitality. In educational settings, an important factor affecting students' relatedness satisfaction is the teachers' behavior. Although research suggests that relatedness satisfaction may be impaired in online education settings, to date no study has assessed how university lecturers' relatedness support might be associated with student relatedness satisfaction and therefore, student motivation and vitality. This study tested this mediating relationship using data collected during the early days of the COVID-19 pandemic. The study also investigated whether the relations were moderated by a high affiliation motive which reflects a dispositional wish for positive and warm relationships. The possible importance of the communication channel selected by the lecturers (video chat yes/no) and the format of a class (lecture/seminar) were also investigated. In a sample of N = 337 students, we tested our hypotheses using structural equation model (SEM). Results confirmed mediation, but not moderation. The use of video chat (video call) seems to facilitate the provision of relatedness support but our data did not show that the format of a class was associated with relatedness. Our findings indicate that both teaching behavior and the technical format used to deliver lectures play important roles in student experiences with online classes. The results are discussed in light of other research conducted during the pandemic.

Changes in Attentional Function in Patients From Before Through 12 Months After Breast Cancer Surgery.

CONTEXT: Although approximately 75% of patients with breast cancer report changes in attentional function, little is known about how demographic, clinical, symptom, and psychosocial adjustment (e.g., coping) characteristics influence changes in the trajectories of attentional function over time. OBJECTIVES: This study evaluated interindividual variability in the trajectories of self-reported attentional function and determined which demographic, clinical, symptom, and psychosocial adjustment characteristics were associated with initial levels and with changes in attentional function from before through 12 months after breast cancer surgery. METHODS: Before surgery, 396 women were enrolled. Attentional Function Index (AFI) was completed before and nine times within the first 12 months after surgery. Hierarchical linear modeling was used to determine which characteristics were associated with initial levels and trajectories of attentional function. RESULTS: Given an estimated preoperative AFI score of 6.53, for each additional month, the estimated linear rate of change in AFI score was an increase of 0.054 (P < 0.001). Higher levels of comorbidity, receipt of adjuvant chemotherapy, higher levels of trait anxiety, fatigue, and sleep disturbance, and lower levels of energy and less sense of control were associated with lower levels of attentional function before surgery. Patients who had less improvements in attentional function over time were nonwhite, did not have a lymph node biopsy, had received hormonal therapy, and had less difficulty coping with their disease. CONCLUSION: Findings can be used to identify patients with breast cancer at higher risk for impaired self-reported cognitive function and to guide the prescription of more personalized interventions.

Challenges and Opportunities for Cancer Predisposition Cascade Screening for Hereditary Breast and Ovarian Cancer and Lynch Syndrome in Switzerland: Findings from an International Workshop.

BACKGROUND: An international workshop on cancer predisposition cascade genetic screening for hereditary breast and ovarian cancer (HBOC) and Lynch syndrome (LS) took place in Switzerland, with leading researchers and clinicians in cascade screening and hereditary cancer from different disciplines. The purpose of the workshop was to enhance the implementation of cascade genetic screening in Switzerland. Participants discussed the challenges and opportunities associated with cascade screening for HBOC and LS in Switzerland (CASCADE study); family implications and the need for family-based interventions; the need to evaluate the cost-effectiveness of cascade genetic screening; and interprofessional collaboration needed to lead this initiative. METHODS: The workshop aims were achieved through exchange of data and experiences from successful cascade screening programs in the Netherlands, Australia, and the state of Ohio, USA; Swiss-based studies and scientific experience that support cancer cascade screening in Switzerland; programs of research in psychosocial oncology and family-based studies; data from previous cost-effectiveness analyses of cascade genetic screening in the Netherlands and in Australia; and organizational experience from a large interprofessional collaborative. Scientific presentations were recorded and discussions were synthesized to present the workshop findings. RESULTS: The key elements of successful implementation of cascade genetic screening are a supportive network of stakeholders and connection to complementary initiatives; sample size and recruitment of relatives; centralized organization of services; data-based cost-effectiveness analyses; transparent organization of the initiative; and continuous funding. CONCLUSIONS: This paper describes the processes and key findings of an international workshop on cancer predisposition cascade screening, which will guide the CASCADE study in Switzerland.

Practical Significance of Item Misfit in Educational Assessments.

Testing item fit is an important step when calibrating and analyzing item response theory (IRT)-based tests, as model fit is a necessary prerequisite for drawing valid inferences from estimated parameters. In the literature, numerous item fit statistics exist, sometimes resulting in contradictory conclusions regarding which items should be excluded from the test. Recently, researchers argue to shift the focus from statistical item fit analyses to evaluating practical consequences of item misfit. This article introduces a method to quantify potential bias of relationship estimates (e.g., correlation coefficients) due to misfitting items. The potential deviation informs about whether item misfit is practically significant for outcomes of substantial analyses. The method is demonstrated using data from an educational test.

Taking the Missing Propensity Into Account When Estimating Competence Scores: Evaluation of Item Response Theory Models for Nonignorable Omissions.

When competence tests are administered, subjects frequently omit items. These missing responses pose a threat to correctly estimating the proficiency level. Newer model-based approaches aim to take nonignorable missing data processes into account by incorporating a latent missing propensity into the measurement model. Two assumptions are typically made when using these models: (1) The missing propensity is unidimensional and (2) the missing propensity and the ability are bivariate normally distributed. These assumptions may, however, be violated in real data sets and could, thus, pose a threat to the validity of this approach. The present study focuses on modeling competencies in various domains, using data from a school sample (N = 15,396) and an adult sample (N = 7,256) from the National Educational Panel Study. Our interest was to investigate whether violations of unidimensionality and the normal distribution assumption severely affect the performance of the model-based approach in terms of differences in ability estimates. We propose a model with a competence dimension, a unidimensional missing propensity and a distributional assumption more flexible than a multivariate normal. Using this model for ability estimation results in different ability estimates compared with a model ignoring missing responses. Implications for ability estimation in large-scale assessments are discussed.