The Functional Limitation Profile (FLP), the Hospital Anxiety and Depression Scale (HADS) and the Recovery Locus of Control scale (RLOC) are three well established and useful measures used in Health Psychology. However, the reliable and valid measurement of these health predictors and outcomes has associated problems. The present thesis tackles measurement issues in all three instruments using item response theory (IRT). The Scientific Advisory Committee of the Medical Outcomes Trust has suggested the methodological and theoretical rationale for the conceptual and measurement model of available measurement instruments should be reported. The introduction chapter provides theoretical background in order to understand activity limitations and participation restrictions as behaviours affected by a certain health condition, as well as by thoughts and feelings. Within this theoretical framework, the present thesis investigates the measurement of mood using the HADS and functional limitations using the FLP in three different health conditions: (1) stroke patients, (2) patients with myocardial infarction, and (3) patients who underwent joint replacement surgery. The measurement of perceived personal control beliefs using the RLOC scale, and the relationship between control cognitions, mood and functional limitations were examined in stroke patients since all three measures were available for secondary analysis in this sample. The main findings are that (1) highly sensitive FLP items measure precisely different levels of disability and handicap, (2) removing 2 HADS items results in precise measurements of different levels of anxiety and depression, and (3) internal but not external perceived personal control beliefs measured sensitively different levels of the underlying construct.

No description available.

Bock and Aitkin (1981) developed an EM algorithm for the maximum marginal likelihood estimation of parametric item response curves, such that these estimates could be obtained in the absence of the estimation of examinee parameters. Using functional data analytic techniques described by Ramsay and Silverman (1997), this algorithm is extended to achieve nonparametric estimates of item response functions. Unlike their parametric counterparts, nonparametric functions have the freedom to adopt any possible shape, making the current approach an attractive alternative to the popular three-parameter logistic model. A basis function expansion is described for the item response functions, as is a roughness penalty which mediates a compromise between the fit of the data and the smoothness of the estimate. The algorithm is developed and applied to both actual and simulated data to illustrate its performance, and how the nonparametric estimates compare to results obtained through more classical methods.

Zugl.: Bonn, Univ., Diss., 2005

Thesis (Ph. D.)--Georgia State University, 2006. / Karen M. Zabrucky, committee chair; Laura D. Fredrick, John H. Neel, Dennis N. Thompson, committee members. Electronic text (142 p.) : digital, PDF file. Description based on contents viewed July 16, 2007. Includes bibliographical references (p. 129-135).

Universiẗat, Diss., 2003--Heidelberg. / Erscheinungsjahr an der Haupttitelstelle: 2003.

This study compares item and examinee properties, studies the robustness of IRT models, and examines the difference in robustness when using model-data-fit as a robustness criterion. A conceptualization of robustness as a statistical relationship between model assumption violation and invariance properties has been created in this study based on current understanding on IRT models. Using real data from British Columbia Science Assessments, a series of regressional and canonical analyses were conducted. Scatterplots were used to study possible non-linear relationships. The means and standard deviations of "a" and "c" parameter estimates obtained by applying the three-parameter model to a data sample were used as indices of equal discrimination and non-guessing assumption violation for the Rasch model. The assumption of local independence was taken as being equivalent to the assumption of unidimensionality, and Humphreys' pattern index "p" was used to assess the degree of unidimensionality assumption violation. Means and standard deviations of Yen's Q [i subscript] were used to assess the model-data-fit of items at the total test level. Another statistic to assess the model-data-fit of examinees (D [i subscript]) was created and validated in this study. The mean and standard deviation of D [i subscript] were used to assess model-data-fit of examinees at the total test level. The statistics used in this study for assessing item and ability parameter estimate invariance properties were correlations between estimates obtained from a sample and the estimates obtained from an assessment data file. It was found that model-data-fit of items and model-data-fit of examinees are two statistically independent total test properties of model-data-fit. Therefore, there is a necessity in practice to differentiate model-data-fit of items and model-data-fit of examinees. It was also found that item estimate invariance and ability estimate invariance are statistically independent total test properties of invariance. Therefore, there is also a necessity in practice to differentiate item invariance and ability invariance. When invariance is used as a criterion for robustness, the three-parameter model is robust for all the combinations of sample size and test length. The Rasch model is not robust in terms of ability estimate invariance when a large sample size is combined with a moderate test length, or when a moderate sample size is combined with a long test length. Finally, no significant relationship between model-data-fit and invariance was found. Therefore, results of robustness studies obtained when model-data-fit is used as a criterion and the results when invariance is used as a criterion may be totally different, or even contradictory. Because invariance is the fundamental premise of IRT models, invariance properties rather than model-data-fit should be used as criteria for robustness. / Education, Faculty of / Curriculum and Pedagogy (EDCP), Department of / Graduate

The purpose of this study was to determine what effect changes in the item order had on classical and on latent trait test statistics. As well, comparisons were made between students who were allowed to answer the questions in any order, and students who were required to answer the questions In the order presented in the test booklet. The results were then analyzed using the student's ability level as an additional independent factor. Four different formats of a forty item mathematics test were used with 590 students in grade eight. Half of the booklets had the items sequenced from easiest to hardest. The other booklets were sequenced from hardest to easiest. In addition, half of the tests of each sequence had special directions which prevented students from altering the given item difficulty sequence. The classroom teachers provided a rating of each student's ability in mathematics. The order of the items was found to have a significant effect. Tests which were sequenced from hard to easy had a lower mean score. Although students with test booklets with restrictive directions had lower scores on average, it was not a statistically significant difference. There were no significant interactions found. Classical and latent trait item difficulty statistics showed a high degree of correlation. It was concluded that under certain circumstances, the order of the items could effect both classical and latent trait statistics. It was also recommended that care should be taken when assumptions are made about parallel forms or local independence. / Education, Faculty of / Educational and Counselling Psychology, and Special Education (ECPS), Department of / Graduate

No description available.

Thesis advisor: Zhushan Mandy Li / Differential item functioning (DIF) occurs when examinees of equal ability from different groups have different probabilities of correctly responding to certain items. DIF analysis aims to identify potentially biased items to ensure the fairness and equity of instruments, and has become a routine procedure in developing and improving assessments. This study proposed a DIF detection method using regularization techniques, which allows for simultaneous investigation of all items on a test for both uniform and nonuniform DIF. In order to evaluate the performance of the proposed DIF detection models and understand the factors that influence the performance, comprehensive simulation studies and empirical data analyses were conducted. Under various conditions including test length, sample size, sample size ratio, percentage of DIF items, DIF type, and DIF magnitude, the operating characteristics of three kinds of regularized logistic regression models: lasso, elastic net, and adaptive lasso, each characterized by their penalty functions, were examined and compared. Selection of optimal tuning parameter was investigated using two well-known information criteria AIC and BIC, and cross-validation. The results revealed that BIC outperformed other model selection criteria, which not only flagged high-impact DIF items precisely, but also prevented over-identification of DIF items with few false alarms. Among the regularization models, the adaptive lasso model achieved superior performance than the other two models in most conditions. The performance of the regularized DIF detection model using adaptive lasso was then compared to two commonly used DIF detection approaches including the logistic regression method and the likelihood ratio test. The proposed model was applied to analyzing empirical datasets to demonstrate the applicability of the method in real settings. / Thesis (PhD) — Boston College, 2019. / Submitted to: Boston College. Lynch School of Education. / Discipline: Educational Research, Measurement and Evaluation.