Thesis (Ph. D.)--University of Hong Kong, 2002. / Includes bibliographical references (leaves 182-211).

Not available / text

Classification testing has been widely used to make categorical decisions by determining whether an examinee has a certain degree of ability required by established standards. As computer technologies have developed, classification testing has become more computerized. Several approaches have been proposed and investigated in the context of computer-based classification testing, including: 1) Computerized adaptive test (CAT); 2) Multistage test (MST); 3) Sequential probability ratio test (SPRT), among others. The purpose of this study was to systematically compare the differences in classification decision precision among several testing approaches (i.e., CAT, MST, and SPRT) given three test lengths and three cutoff scores using mixed-format tests based on the generalized partial credit model. The progressive-restricted exposure control procedure and constrained CAT content balancing procedure with test unit types were also incorporated as part of this study. All conditions were evaluated in terms of the classification decision precision and the exposure control property. Overall, this study’s results indicated that all three approaches performed well in terms of classifying people into two categories. The CAT and SPRT approaches produced, on average, comparable results with both performing relatively better than the MST approach in the precision of their classification decision. As the test length increased, the classification decision accuracy generally increased for all approaches; however, the CAT and SPRT approaches yielded more accuracy with the shorter test length. In terms of cutoff scores, predicting classification decision differed according to the location of cutoff scores based on the normal distribution of examinees. In terms of exposure control properties, the progressive-restricted exposure control procedure with the pre-set maximum test unit exposure rate was implemented effectively into the CAT and SPRT approaches. The CAT approach had, on average, a higher proportion of test units with low test unit exposure rates and produced better results in pool utilization rates than the SPRT approach. Finally, the MST approach administered all test units constructed for the panels for each condition. It had, on average, however, a higher proportion of test units with high test unit exposure rates because computations were based only on the proportion of whole test unit pool used for constructing the MST panels. / text

published_or_final_version / Applied Statistics / Master / Master of Social Sciences

Level of functioning (LOF) has increasingly become a critical issue within the mental health field. Policy makers use LOF to compare costs and benefits, mental health care organizations use LOF to track client progress and evaluate new treatments, and agencies use LOF to evaluate individuals who are seeking services. Clients with serious mental illness (SMI) are an extremely heterogeneous group in terms of presentation, characteristics, and needs; however a great deal of uniformity exists in their high level of service utilization. This study examines the reliability and validity of a structured clinical interview designed to assess level of functioning in SMI populations. The interview is designed to assess experiences along six dimensions: interpersonal relationships, family living situation, socio-legal issues, medical/physical functioning, role performance, and self care/basic needs. Each scale consists of related questions and problem severity ratings that aid in the assignment of a functional score for each of the six subscales. A random sample of 355 assessments were drawn from a larger sample of interviews conducted with SMI clients in Southern Arizona. Three key relationships among the scale's components were investigated: (1) questions to problem severity ratings, (2) questions to functional scores and, (3) problem severity ratings to functional scores. Results of correlation analyses and confirmatory factor analysis provided evidence of internal consistency reliability and both convergent and discriminant validity for the structured interview.

No description available.

The construct of craving is frequently invoked as a causal factor in on going substance use or in relapse after a period of abstinence. The aim of the present study is to develop a general self-report questionnaire of craving that can be used to assess craving at any point in addiction and recovery. The study was conducted in two phases. In the first phase of the study a sample of 23 addicts were interviewed about their subjective experience of craving. The purpose of this phase of the study was to develop a theory of the subjective experience of craving that could be used to guide the development of the self-report questionnaire. Analysis of the text of these interviews revealed nine dimensions of the subjective experience of craving: specificity, strength, positive outcomes, behavioral intention, physical symptoms, affect, internal cues, situations, and drug availability. The first six dimensions were hypothesized to load on a general craving factor, and the last three dimensions were hypothesized to load on a cue reactivity factor. Questionnaire items were generated to broadly sample each of these dimensions. In the second phase the questionnaire was administered to a heterogenous sample of 205 addicts. Confirmatory factor analytic procedures were used to assess the present theory of craving and the psychometric properties of the instrument. The two factor model of craving fit the data well based on practical fit indices (Robust CFI =.95) and the discriminant validity of the two factors was supported. These analyses supported the theory of craving underlying the development of the questionnaire and indicated that the questionnaire has acceptable psychometric properties. The theoretical, psychometric, and clinical implications of the results are discussed.

In this dissertation we explore signal detection with model and human observers in the setting of nuclear medicine. Regarding the model observer, the main focus is on the linear observer that maximizes detectability, which we call the Hotelling observer. In particular, we outline two methods for realizing an estimate of this observer. The first uses a Fourier representation. The second uses a representation with a small number of channels chosen for optimal performance. The work employs statistically defined lumpy backgrounds to test the methods and results. These backgrounds are more complicated than correlated Gaussian noise and are meant to complicate the signal-detection task by involving random structure. Regarding the human observer, we present a literature review of psychophysical models, including results based on these models. We then examine one current front runner--a channelized-Hotelling observer with channels modeling visual-response functions---for two experiments involving the lumpy backgrounds.

No description available.

<p> Military children are often unspoken or underrepresented casualties of modern day wars. The purpose of this study was to develop a method of empirically measuring civilian mental health professionals' perceived knowledge of the culture of the United States Army. The rational-empirical approach was used during instrument development. The study was divided into three phases: item generation, Army expert panel review, and a pilot study with mental health professionals. Ten experts provided quantitative and qualitative data to inform scale item revisions prior to the pilot study. A revised version of the scale was administered to 97 professionals. Three separate versions of the scale were tested throughout the course of the study. </p><p> Principal component analysis with varimax rotation extracted three factors (Army Knowledge, Army Family Processes, and Adaptability of Army Families) explaining 70.96% of the total scale variance. The Cronbach's alpha was 0.98 and the factor loadings ranged from .42 to .84. These findings show the presence of a strong factor structure. Face and content validity was established via the expert panel. The final result was a 30-item, self-report scale that measures the perceived knowledge of Army culture of mental health professionals in a variety of settings. The SACS-Charlie version reflects an initial attempt to measure the most potent knowledge that mental health professionals need to know in order to provide effective and appropriate services for Army children and families. Subsequent studies can further address this goal.</p>