Typescript (photocopy). / Digitized by Kansas Correctional Industries

The purpose of this study was to revise and revalidate the scoring procedure of the DISCOVER Mathematics Assessment to allow evaluators to better measure creative problem solving ability in mathematics, identify gifted students, and evaluate the programs developed for fostering creative problem solving. The data for this study consisted of 233 students selected from five different grade levels. I conducted descriptive statistics and regression analyses to compare the relationships of both the original and revised versions of the scoring system with general creativity. I found that range increased from the original to the revised version of the scoring system for mathematical problem solving performance in semi-open-ended problems, however it decreased for overall performance and performance in open-ended problems. Variance, on the other hand, increased for both overall problem solving performance and performance in semi-open-ended problems, and decreased for performance in open-ended problems from the original to the revised version of the scoring system. Furthermore, in the revised model all three variables of the creative mathematical problem solving performance (overall performance, performance in semi-open-ended problems, and performance in open-ended problems) explained more variance in general creativity than the original version. Statistically, the differences between the original and the revised versions were significant for all three variables, except for creative mathematical problem solving performance in open-ended problems. Across grade levels, I found that for the group Lower Grade Levels (grade levels 1 and 2), the explained variance in general creativity increased from the original to the revised version for both overall performance and performance in semi-open-ended problems. However, it decreased for performance in open-ended problems. On the other hand for the group Higher Grade Levels (grade levels 3, 4, and 5) the explained variance in general creativity increased for all three variables from the original to the revised version. Statistically, the only significant difference between the original and the revised versions was for overall problem solving performance in Higher Grade Levels. I concluded that the revised version of the scoring system was more effective when predicting variance in general creativity for overall problem solving performance, and performance in semi-open-ended problems. Also, it predicted more variance in general creativity for the group Higher Grade Levels than the group Lower Grade Levels. Therefore, I suggested that quality should be considered as well as fluency, flexibility, and originality when scoring assessments for creative problem solving ability in mathematics.

The aim of this PhD project is to design profit scorecards for a revolving credit using alternative measures of profit that have not been considered in previous research. The data set consists of customers from a lending institution that grants credit to those that are usually financially excluded due to the lack of previous credit records. The study presents for the first time a relative profit measure (i.e.: returns) for scoring purposes and compares results with those obtained from usual monetary profit scores both in cumulative and average terms. Such relative measure can be interpreted as the productivity per customer in generating cash flows per monetary unit invested in receivables. Alternatively, it is the coverage against default if the lender discontinues operations at time t. At an exploratory level, results show that granting credit to financially excluded customers is a profitable business. Moreover, defaulters are not necessarily unprofitable; in average the profits generated by profitable defaulters exceed the losses generated by certain non-defaulters. Therefore, it makes sense to design profit (return) scorecards. It is shown through different methods that it makes a difference to use alternative profit measures for scoring purposes. At a customer level, using either profits or returns alters the chances of being accepted for credit. At a portfolio level, in the long term, productivity (coverage against default) is traded off if profits are used instead of returns. Additionally, using cumulative or average measures implies a trade off between the scope of the credit programme and customer productivity (coverage against default). The study also contributes to the ongoing debate of using direct and indirect prediction methods to produce not only profit but also return scorecards. Direct scores were obtained from borrower attributes, whilst indirect scores were predicted using the estimated probabilities of default and repurchase; OLS was used in both cases. Direct models outperformed indirect models. Results show that it is possible to identify customers that are profitable both in monetary and relative terms. The best performing indirect model used the probabilities of default at t=12 months and of repurchase in t=12, 30 months as predictors. This agrees with banking practices and confirms the significance of the long term perspective for revolving credit. Return scores would be preferred under more conservative standpoints towards default because of unstable conditions and if the aim is to penetrate relatively unknown segments. Further ethical considerations justify their use in an inclusive lending context. Qualitative data was used to contextualise results from quantitative models, where appropriate. This is particularly important in the microlending industry, where analysts’ market knowledge is important to complement results from scorecards for credit granting purposes. Finally, this is the first study that formally defines time-to-profit and uses it for scoring purposes. Such event occurs when the cumulative return exceeds one. It is the point in time when customers are exceedingly productive or alternatively when they are completely covered against default, regardless of future payments. A generic time-to-profit application scorecard was obtained by applying the discrete version of Cox model to borrowers’ attributes. Compared with OLS results, portfolio coverage against default was improved. A set of segmented models predicted time-to-profit for different loan durations. Results show that loan duration has a major effect on time-to-profit. Furthermore, inclusive lending programmes can generate internal funds to foster their growth. This provides useful insight for investment planning objectives in inclusive lending programmes such as the one under analysis.

Ingeniero Civil Mecánico / En Chile, los microempresarios son cada vez más. En el año 2004 el 81% de las empresas existentes correspondía a microempresarios. Es por esto que las oportunidades de crédito también están en aumento. Para que las instituciones puedan definir a quien asignar o no crédito, generalmente utilizan Credit Scoring. El problema que se presenta ante esta metodología, es que los modelos pierden poder discriminante en el tiempo, debido a cambios en la población y en la distribución de las variables que se evalúan. Esta memoria diseña un proceso de negocio, basado en test estadísticos, que permite determinar el momento óptimo para ajustar los modelos de riesgo de crédito a consumidores. La metodología que se sigue para obtenerlo, consiste en definir un test supervisado, test K-S, y un test no supervisado, Fieller Stability Measure, para estimar una medida de pérdida y el momento óptimo de la re-calibración. Con esto, se construye el proceso de negocio y se evalúa en datos de una institución financiera real. Los datos con los que se cuenta para realizar estas estimaciones consideran a carteras de microempresarios de sectores no rurales. El periodo de estudio va desde Enero del 2010 a Septiembre del 2012, y la muestra total incluye un total de 83.137 registros. Con estos datos se evalúa el comportamiento de la curva K-S versus la pérdida y se obtiene con un error del 22%, al medir el valor del aumento de la pérdida dada la baja porcentual del estadístico KS. Aplicando el método Fieller Stability Measure se verifica cuales meses las variables no cumplen con la condición de mantenerse dentro de los límites aceptables. Con esto se concluye que la alerta de acción (para re-calibrar el modelo) ocurre cuando durante tres meses seguidos el intervalo de la variable traspasa los límites del modelo. Así mismo se establece como alerta de precaución cuando el intervalo de la variable se sale de los límites por un mes. Se comprueba que para el caso de alerta de acción la pérdida que se recupera justifica el costo de re-calibración. Al contrario del caso de la alerta de precaución en donde no es rentable, e incluso aumenta la pérdida, al recalibrar el modelo.

No description available.

Background: Concussion assessments rely on a multifaceted approach where evaluation of balance and postural control plays an important role. Following a concussion, 67% of individuals report dizziness as a persistent symptom and 30% experience balance impairments. Studies incorporating the common Balance Error Scoring System (BESS) tool suggest that these impairments return to pre-injury baselines within ten days of incident. In contrast, however, studies incorporating more advanced posturography methods observe significant differences in balance up to one year following injury. While the BESS is consistently associated with low sensitivity and poor reliability scores, advanced posturography systems using force plates are not practical or accessible in most recreational sports environments. Recently, the Wii Balance Board (WBB) has been identified as a potential force plate proxy. Research confirms that the WBB is both valid and reliable in collecting center of pressure data. Thus, the WBB may be useful for investigating post-concussion balance deficits. Objective: The purpose of this study was to investigate the potential utility of a customized WBB program to assess postural balance in an athletic population. The study aimed to assess change in postural balance using the clinical BESS and WBB assessment tools to evaluate balance at fixed intervals during a regular athletic season and following concussion. Design: Prospective partial cohort. Methods: Balance was assessed at baseline, mid-, and post-season. Individuals who sustained a concussion during the study period were further assessed weekly for four weeks post-injury. Results: No significant differences were observed in raw BESS scores across regular season or post-concussion time points. In contrast, significant differences in several WBB outcome measures were observed. In the single stance condition, COPML worsened by 24% and COPT worsened by 9% between baseline and post-season time points (p=.002 and p=.007). In contrast, participants improved by 14% on a timed dynamic task (p=.003) between baseline and post-season time points. Following concussion, only the WBB dynamic outcome measures were found to be statistically significant. A positive trend was observed post-concussion, suggesting that a learning effect exists with the dynamic WBB program. Conclusion: Study results emphasize the importance of considering the progression of athletic season when interpreting baseline and post-concussion balance measurements. Study results support the use of a quantitative balance assessment, such as with a WBB, to improve measurement of static and dynamic postural balance. / Graduate / 0566 / hilarymcullen@gmail.com

The purpose of the present study was to determine whether Koppitz's developmental scoring techniques of mental maturity are applicable to mentally retarded children ages 5 to 12.

Doctor en Sistemas de Ingeniería / Medir la probabilidad de no pago de un gran número de solicitantes de crédito, el llamado riesgo de crédito a consumidores, es un problema clásico de la gestión financiera. Este problema requiere de una gran cantidad de herramientas estadísticas que lo hacen idóneo para su estudio por el área de Business Analytics. Su análisis se justifica en el fuerte impacto que los créditos a consumidores tienen en el mercado, pues por ejemplo en Chile más del 50% de los créditos se encuentran en carteras masivas, y en el resto del mundo se estima que superan a los créditos comerciales en más de un 50%. Esta tesis estudia este problema en base a la formalización de lo que se conoce sobre las determinantes del no pago (default) y la transformación de ese conocimiento en herramientas estadísticas para la medición del riesgo. Para lo anterior, durante el doctorado desarrollé una sucesión de publicaciones con el fin de unir el modelamiento económico con la práctica estadística predictiva, formalizando el conocido hecho que existen no pagadores por razones de falta de capacidad de pago, y por problemas en voluntad de pago. El trabajo comenzó generando un modelo económico que captura las utilidades de los solicitantes y la entidad prestamista, utilizando esta nueva definición de no pagadores, resultando en una serie de restricciones que definen un espacio de créditos factibles. Luego, los no pagadores son asignados a estas dos clases utilizando un nuevo método de clustering semi-supervisado que los agrupa tanto por sus características estadísticas como por su comportamiento económico, reflejado a través de las restricciones generadas previamente. El fin último de esta separación es mejorar la clasificación de los créditos y la comprensión del default, por lo que el siguiente paso correspondió al estudio de métodos de clasificación con múltiples clases. Para ello se exploró inicialmente la regresión logística multinomial, y luego se profundizó en el análisis de supervivencia, estudiando teóricamente los métodos de riesgos en competencia y los modelos mixtos, y desarrollando herramientas computacionales liberadas públicamente para apoyar futuras aplicaciones. Los métodos propuestos mejoran entre 1%-10% la discriminación por sobre los métodos clásicos en bases de datos reales, y enriquecen fuertemente la comprensión del default a través de las nuevas variables significativas y los patrones encontrados. Más aún, los modelos y herramientas desarrollados pueden ser perfectamente extrapolados a otras disciplinas, pues este trabajo ha mostrado cómo se puede enriquecer la clasificación donde típicamente se cuenta con dos clases, por la vía de añadir conocimiento adicional acerca de comportamientos económicos observados.

Thesis advisor: Henry Braun / The Next Generation Science Standards propose a multidimensional model of science learning, comprised of Core Disciplinary Ideas, Science and Engineering Practices, and Crosscutting Concepts (NGSS Lead States, 2013). Accordingly, there is a need for student assessment aligned with the new standards. Creating assessments that validly and reliably measure multidimensional science ability is a challenge for the measurement community (Pellegrino, et al., 2014). Multidimensional assessment tasks may need to go beyond typical item designs of standalone multiple-choice and short-answer items. Furthermore, scoring and modeling of student performance should account for the multidimensionality of the construct. This research contributes to knowledge about best practices for multidimensional science assessment by exploring three areas of interest: 1) item design, 2) scoring rubrics, and 3) measurement models. This study investigated multidimensional scaffolding and response format by comparing alternative item designs on an elementary assessment of matter. Item variations had a different number of item prompts and/or response formats. Observations about student cognition and performance were collected during cognitive interviews and a pilot test. Items were scored using a holistic rubric and a multidimensional rubric, and interrater agreement was examined. Assessment data was scaled with multidimensional scores and holistic scores, using unidimensional and multidimensional Rasch models, and model-data fit was compared. Results showed that scaffolding is associated with more thorough responses, especially among low ability students. Students tended to utilize different cognitive processes to respond to selected-response items and constructed-response items, and were more likely to respond to selected-response arguments. Interrater agreement was highest when the structure of the item aligned with the structure of the scoring rubric. Holistic scores provided similar reliability and precision as multidimensional scores, but item and person fit was poorer. Multidimensional subscales had lower reliability, less precise student estimates than the unidimensional model, and interdimensional correlations were high. However, the multidimensional rubric and model provide nuanced information about student performance and better fit to the response data. Recommendations about optimal combinations of scaffolding, rubric, and measurement models are made for teachers, policymakers, and researchers. / Thesis (PhD) — Boston College, 2018. / Submitted to: Boston College. Lynch School of Education. / Discipline: Educational Research, Measurement and Evaluation.

Purpose: To introduce the simplified therapeutic intervention scoring system (TISS-28), the original therapeutic intervention scoring system (TISS-76) and simplified acute physiological score (SAPS) version II in critically ill adult patients, in order to describe the validity and reliability of TISS-28 as a suitable measure of quantifying nursing workload in the adult intensive care units (ICU) of a public sector hospital in Johannesburg. Objectives: To describe the profile of patient admissions to the intensive care units, to investigate the impact of the patients’ profile on the requirements for nursing workload and to validate the use of TISS-28 as a measure of quantifying nursing workload in this setting. Design: A non-experimental, comparative descriptive, correlational and prospective two-staged design was utilized to meet the study objectives. Stage I involved face and content validation of TISS-28 by a panel of ICU nurse experts (n=6). Stage II involved assessment of concurrent and construct validity as well as inter-rater reliability of TISS-28 using participants (n=105) drawn from trauma, cardiothoracic and multidisciplinary ICUs. Data necessary for the calculation of TISS-28, TISS-76 and SAPS II were recorded for each patient in the ICU at 24 and 48 hours after admission and in the wards after discharge within 24-48 hours. Descriptive and inferential statistics were used to analyze data. Results: Content Validity Index (CVI) of 0.93 was found for TISS-28. A significant positive correlation was found between TISS-28 and TISS-76 scores (r = 0.7857, p = 0.0001) as well as TISS-28 and SAPS II scores (r = 0.2098, p = 0.0317). A significant difference was found between TISS-28 scores among patients in the ICU and patients in the ward (t = 25.59, p = 0.0001; t = 21.48, p = 0.0001) respectively. A significant correlation was found between the data collected from a sample of patients by the researcher and the expert assistant researcher with an intra-class correlation coefficient of 0.99 and a p-value of 0.0001. Conclusions: The findings support validity and reliability of TISS-28 hence its feasibility for use in South African ICUs. Recommendations for nursing education, practice, management and research are proposed.