Esse trabalho consiste em uma sugestão de metodologia para análise de concessões de crédito a pessoas físicas a partir do estudo matemático e estatístico de informações sobre créditos concedidos no passado recente da carteira de crédito em questão, tais como os hábitos de pagamentos e variáveis cadastrais, financeiras, patrimoniais e de relacionamento com a instituição credora dos clientes analisados. A análise parte da definição da qualidade de crédito (bom ou ruim) dos créditos estudados, sendo seguida pelo estudo das variáveis dos clientes que influenciam na capacidade destes em honrar os compromissos do crédito obtido, a partir de técnicas estatísticas de agrupamento de indivíduos em categorias homogêneas de influência sobre a qualidade de crédito e estimação de coeficientes para as variáveis relevantes estatisticamente, através do método de regressão logística, gerando um modelo de fácil interpretação e implementação. O estudo sugere, também, ferramentas práticas para a verificação da qualidade do modelo estimado e de acompanhamento da performance da utilização do modelo durante os meses seguintes à sua implementação. Assim, o trabalho apresenta todos os aspectos vitais para análise de concessões de crédito, a partir de um enfoque bastante pragmático e tecnicamente viável.

Práce pojednává o řízení rizik v leasingové společnosti. Popisuje proces hodnocení bonity klienta a faktory ovlivňující schvalování obchodních případů. Charakterizuje ratingový a scoringový model v konkrétní leasingové společnosti, hodnotí jejich nedostatky a navrhuje změny na jejich vylepšení. Obsahuje i praktický příklad komplexního hodnocení obchodního případu včetně posouzení bonity klienta prostřednictvím ratingového modelu a nástrojů finanční analýzy.

Keywords: Equating, IRT, Testlet Respons Model, Rasch Testlet Model, LSC, Concurrent, FPC / Test equating allows direct comparison of test scores from alternative forms measuring the same construct by employing equating procedures to put the test scores on the same metric. Three equating procedures are commonly used in the literature including the concurrent calibration method, the linking separate calibration methods (e.g. the moment methods and the characteristic curve methods), and FPC (Fixed Parameter Calibration) method. The first two types of methods for traditional IRT model have been well developed. FPC is being emphasized recently because of its utility for constructing item bank and computerized adaptive testing (CAT). However, there are few studies that examine the equating accuracy of the FPC method compared to that of the linking separate calibration method and the concurrent calibration method. / The equating methods for the traditional IRT model are not appropriate for linking testlet-based tests because the local independence assumption of IRT model cannot be held for this type of tests. Some measurement models, such as testlet response model, bi-factor model, and Rasch testlet model, were advanced to calibrate the models for the testlet-based tests. Few equating methods, however, that take into consideration the additional local dependence among the examinees' responses to items within testlets have been developed for linking testelet-based tests. / The first study compared the equating accuracies of the FPC, the linking separate calibration, and the concurrent calibration method based on the IRT model to equate item parameters under different conditions. The results indicated that the FPC method using BILOG-MG performed as well as the linking separate calibration method and the concurrent calibration method for linking the equivalent groups. However, the FPC method produced larger equating errors than the other two methods did when the ability distributions of the base and target groups were substantially nonequivalent. Differences in difficulties between the common items set and the total test did not substantially affect the equating results with the three methods, with other conditions being held equal. As expected, both small sample size and less number of common items led to slight greater equating errors. / The last study used the concurrent calibration method under the multidimensional Rasch testlet model to link the testlet-based tests in which the testlets were composed of dichotomous, polytomous, and mixed-format items. The results demonstrated that the concurrent calibration method under the Rasch testlet model worked well in recovering the underlying item parameters. Again, equating errors were substantially increased if the local dependences were ignored in model calibration. And smaller testlet variances for the common testlets led to more accurate equating results. / The results of the studies contribute to a better understanding of the effectiveness of the different equating methods, particularly those for linking testlet-based tests. They also help clarify influences of the other factors, such as characteristics of the examinees, features of the common items and common testlets on equating results. Testing practitioners and researchers may draw useful recommendations from the findings about equating method selection. Nevertheless, generalizations of the findings from the simulated studies to practical testing programs should be cautious. / The second study developed an item characteristic curve method and a testlet characteristic curve method for the testlet response model to transform the scale of item parameters. It then compared the effectiveness of the characteristic curve methods and the concurrent calibration methods under different conditions in linking item parameters from alternate test forms which were composed of dichotomously scored testlet-based items. The newly developed item characteristic curve method and the testlet characteristic curve method were shown to perform similarly as or even better than the Stocking-Lord test characteristic curve method and the concurrent calibration method did. Ignoring the local dependence in model calibration substantially increased equating errors. And larger testlet variances for the common testlets led to greater equating errors. / To address the need to better understand the FPC method and to develop new equating methods for linking testlet-based tests, the studies were to compare the effectiveness of the three types of equating methods under different linking situations and to develop equating methods for linking testlet-based tests. Besides the equating methods concerned, other factors, including sample size, ability distribution, and characteristics of common items and testlets that might affect equating results were also considered. Three simulation studies were carried out to accomplish the research purposes. / Zhang, Zhonghua. / Adviser: Yujing Ni. / Source: Dissertation Abstracts International, Volume: 72-01, Section: A, page: . / Thesis (Ph.D.)--Chinese University of Hong Kong, 2010. / Includes bibliographical references (leaves 156-166). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese.

Graduation date: 1995

Objective: The purpose of the present study is to examine whether level of written emotional expression (EE) and emotional/cognitive processing (ECP) for traumatic events predict health status (CD4 and VL), Category B symptoms, depression and anxiety in an HIV+ population over four years. Specifically, two different scoring methods of two variables within ECP (cognitive appraisal and self-esteem) will be compared to see if a change score (SMCHANGE) or a final score (SMFINAL) better predict outcomes. The possible mediating role of ECP in the relationship between EE and outcomes will also be explored. Methods: This longitudinal study assessed 169 HIV+ and diverse men and women in the midrange of illness as indicated by a CD4 number between 150 and 200 and no previous AIDS-defining symptom. EE/ECP data was gathered during baseline assessment and participants attended follow-up assessments every 6 months for a period of 4 years. Hierarchical Linear Modeling was used to examine change over time in CD4, VL log, Category B symptoms, depression and anxiety controlling for age, gender, ethnicity, education, anti-HIV medication and baseline values for each outcome. In addition, analyses for CD4 and VL log were rerun controlling for medication adherence. Results: Positive EE was found to be significantly related to only CD4 and Category B symptoms slopes. Negative EE was not related to any outcome. ECP was found to be related to CD4, VL log and Category B symptoms slope. No relationships were found between EE/ECP and depression and anxiety. SMFINAL scores on ECP subscales were found to predict CD4 and VL log slope better than SMCHANGE, but SMCHANGE scores predicted Category B symptoms slope better than SMFINAL. Within meditational analyses, ECP was found to mediate the relationship between positive EE and CD4 slope controlling for adherence. Positive EE mediated the relationship between ECP and Category B symptoms slope. Conclusions: Higher engagement in positive EE and ECP within emotional writing about a trauma contributes to beneficial changes in health outcomes over time within HIV+ individuals. SMFINAL seems to be more related to CD4 and VL log slope while SMCHANGE seems to be more related to Category B symptoms slope, indicating that both scoring methods within ECP seem to be valuable. Findings support the meditational role of ECP between EE and CD4, and provide new evidence that positive EE plays a meditational role between ECP and Category B symptoms. These findings can be used to help improve health for patients in future studies or in CBT therapies.

This study examined the relationship of holistic scoring with handwriting legibility, spelling accuracy and number of T-units within compositions written by children in grades 3 through 6 using path analysis. A sample of 223 compositions was rated for handwriting legibility and composition quality, and coded for number of T-units and percentage of accurately spelled words. Number of T-units was consistently the strongest predictor of holistic scoring across the four grade levels. Handwriting legibility and spelling accuracy yielded varying results in different grade levels.

This study examined the relationship of holistic scoring with handwriting legibility, spelling accuracy and number of T-units within compositions written by children in grades 3 through 6 using path analysis. A sample of 223 compositions was rated for handwriting legibility and composition quality, and coded for number of T-units and percentage of accurately spelled words. Number of T-units was consistently the strongest predictor of holistic scoring across the four grade levels. Handwriting legibility and spelling accuracy yielded varying results in different grade levels.

Abstract According to the latest statistical data from Ministry of Finance, it is found that domestic consuming loan is growing up continuously these years. Up to the end of September in 2000 the sum of this business is 3984.9 billion. It is equal to 34.1% among loan of native banks. Personal small-scale consumer credit is increasing at 18% rate per year from 148.6 billion in 1994 to 365.1 billion in the end of September in 2000. It is developed vigorously, and even to be the main profit for banks. This is because consumers have slowly changed their concepts about how to use their money. Another reason is that the banks are actively to provide small-scale consumer credit with easy formality. But its potential risk is becoming higher since depression in economy and unemployment are getting higher. ¡§How to do the credit estimation for your consumers; how to make the lost of breaking an appointment lower¡¨ is the most urgent for the banks who would like to have good performance in the field of consuming finance. This research takes 1764 consumers who have small-scale consumer credit from a specific bank as samples for analysis. We found 29 elements that will affect the payment from literature and credit estimation from other branches. After concluding 6 types of credit risk, 25 influent elements offered by sample bank are listed for the purpose of analysis. ¡§K-W independent check¡¨ and ¡§Spearman¡¦s rho related analysis¡¨ are used to gain 17 variables. They are interactive and remarkable for credit. The summarized introduction of this research is as follows. 1. Age is notable for payment. The risk between ages of 41 ~45 is higher than the average. Seniority around 7 ~10 years is also dangerous. The above appearance is figured out to be concerned about transition of economical environment such as depression in economy and unemployment. The thought ¡§ higher ages or seniority means lower risk¡¨ should be done some amendment. 2. Actual net income should be considered while estimating the credit. Higher income is not necessarily equal to lower risk. People with high income were easily to obtain more loans since they would have better payment capacity. It is observed from credit estimation of each bank. In fact income is unable to reflect payment capacity. Debt will be important reason to influence payment capacity. 3. Having real property doesn¡¦t mean having no risk. We could find that consumer¡¦s property usually took large percentage in credit estimation. Sometimes consumers would become dangerous since they had debt for real property. The banks had better to correct their illusion ¡¨land is wealth¡¨ as soon as possible. 4. More or less guarantees are not essential for credit risk. Simple and fast formality appeals to the popular while the banks are promoting small-scale consumer credit. In the past the banks believed that more guarantees could lower the risk. It is wrong and will be the block in developing business. The banks should focus on payment capacity as main accordance for credit estimation. Key words: Consumers loan; Credit risk management, Credit scoring system.

Purpose: This study examined the effects of conceptual scoring on vocabulary performance of bilingual children with and without language impairment and the classification accuracy of an expressive vocabulary test across four scoring methods, single language and conceptual scoring, for bilingual (English-Spanish) children with and without language impairment. Method: Participants included English speaking monolingual children (n=14) and Spanish-English bilingual children (n=116) ages 5-11. Children completed the English and bilingual versions of the Expressive One-Word Picture Vocabulary Test. Four different scores were derived representing monolingual scores in English and Spanish, and three conceptual scores. Within-test conceptual scores credited children’s other language responses during the test; and across-test conceptual scores compiled a conceptual score across Spanish and English administrations of the test. Results: Across-test conceptual scoring resulted in better overall classification, sensitivity, and specificity than within-test conceptual scoring, which resulted in better overall classification, sensitivity, and specificity than monolingual scoring; however, neither method achieved minimum standards of 80% accuracy in sensitivity and specificity. Conclusions: Results suggest that bilingual children are not always able to readily access their second language in confrontation naming tasks. Priming or inhibition may play a role in test performance. Cross-test conceptual scoring yielded the highest classification accuracy and is the recommended method for clinical practice. / text

国立情報学研究所で電子化したコンテンツを使用している。