For my senior thesis, I am planning to blend my mathematical studies with my second field of study, psychology. In particular, to develop and test various scoring methods for a multidimensional, psychometric measure of social skills/competence. I would work with the Social Skills Inventory (see below) and an existing data set, using statistical modelling to design a more representative total score measure. The current total score measure does not appear to take into account balances and value weights of the six inventory items.

This thesis takes up the issue of consumer loans credit risk. It aims to identify factors that influence the likelihood of default during the repayment of bank retail products. Theoretical part is focused on the theory of bank loans, credit risk together with its regulation within the Basel guidelines and a description of the most commonly used statistical methods for the creation of scoring models. In the practical part, logistic regression parameter estimates are used on real set, the main features linking loans in default are examined and their impact on the proportion of bad loans in the portfolio is measured.

The purpose of this study was to examine the accuracy of English-speakers in determining the word recognition score of native Taiwan Mandarin-speakers. Digitally recorded Mandarin word lists were presented to 10 native Mandarin-speakers from Taiwan (five male, five female), from whom oral and written responses were collected. Oral responses were scored by 30 native English-speakers, 15 of which had no experience with Mandarin and 15 with two to three years of college-level Mandarin courses or equivalent knowledge of Mandarin. The judges who had experience with Mandarin were able to score the WRS tests with 97% accuracy (with scores ranging from 10% below to 4% above the actual score of the test). The judges without experience with Mandarin scored the WRS tests with 88.8% accuracy (with scores ranging from 34% below to 26% above the actual score of the test). An analysis of variance found that there was a significant difference between a judge's knowledge of Mandarin and his or her ability to accurately score the oral responses. An inspection of the performance of the judges in respect to the five different Mandarin tones indicated that there are some tone combinations that are more difficult to score correctly than others. While it is apparent that tone combination may play a role in the ability to accurately score WRS words in Mandarin, the implications of this for a clinical setting are uncertain because words with these tone combinations were not heard often. Tone perception training for the judges or simply making clinicians aware of this difficulty in tone identification may be of benefit in overcoming this obstacle.

Background: Scoring models are widely established in the intensive care unit (ICU). However, the importance in patients with ruptured abdominal aortic aneurysm (RAAA) remains unclear. Our aim was to analyze scoring systems as predictors of survival in patients undergoing open surgical repair (OSR) for RAAA. Methods: This is a retrospective study in critically ill patients in a surgical ICU at a university hospital. Sixty-eight patients with RAAA were treated between February 2005 and June 2013. Serial measurements of Sequential Organ Failure Assessment score (SOFA), Simplified Acute Physiology Score II (SAPS II) and Simplified Therapeutic Intervention Scoring System-28 (TISS-28) were evaluated with respect to in-hospital mortality. Eleven patients had to be excluded from this study because 6 underwent endovascular repair and 5 died before they could be admitted to the ICU. Results: All patients underwent OSR. The initial, highest, and mean of SOFA and SAPS II scores correlated significant with in-hospital mortality. In contrast, TISS-28 was inferior and showed a smaller area under the receiver operating curve. The cut-off point for SOFA showed the best performance in terms of sensitivity and specificity. An initial SOFA score below 9 predicted an in-hospital mortality of 16.2% (95% CI, 4.3–28.1) and a score above 9 predicted an in-hospital mortality of 73.7% (95% CI, 53.8–93.5, p < 0.01). Trend analysis showed the largest effect on SAPS II. When the score increased or was unchanged within the first 48 h (score >45), the in-hospital mortality rate was 85.7% (95% CI, 67.4–100, p < 0.01) versus 31.6% (95% CI, 10.7–52.5, p = 0.01) when it decreased. On multiple regression analysis, only the mean of the SOFA score showed a significant predictive capacity with regards to mortality (odds ratio 1.77; 95% CI, 1.19–2.64; p < 0.01). Conclusion: SOFA and SAPS II scores were able to predict in-hospital mortality in RAAA within 48 h after OSR. According to cut-off points, an increase or decrease in SOFA and SAPS II scores improved sensitivity and specificity.

<p>The present dissertation investigated the impact of scales / scoring methods and prompt linguistic features on the meausrement quality of L2 English elicited imitation (EI). Scales / scoring methods are an important feature for the validity and reliabilty of L2 EI test, but less is known (Yan et al., 2016). Prompt linguistic features are also known to influence EI test quaity, particularly item difficulty, but item discrimination or corpus-based, fine-grained meausres have rarely been incorporated into examining the contribution of prompt linguistic features. The current study addressed the research needs, using item response theory (IRT) and random forest modeling.</p><p>Data consisted of 9,348 oral responses to forty-eight items, including EI prompts, item scores, and rater comments, which were collected from 779 examinees of an L2 English EI test at Purdue Universtiy. First, the study explored the current and alternative EI scales / scoring methods that measure grammatical / semantic accuracy, focusing on optimal IRT-based measurement qualities (RQ1 through RQ4 in Phase Ⅰ). Next, the project identified important prompt linguistic features that predict EI item difficulty and discrimination across different scales / scoring methods and proficiency, using multi-level modeling and random forest regression (RQ5 and RQ6 in Phase Ⅱ).</p><p>The main findings were (although not limited to): 1) collapsing exact repetition and paraphrase categories led to more optimal measurement (i.e., adequacy of item parameter values, category functioning, and model / item / person fit) (RQ1); there were fewer misfitting persons with lower proficiency and higher frequency of unexpected responses in the extreme categories (RQ2); the inconsistency of qualitatively distinguishing semantic errors and the wide range of grammatical accuracy in the minor error category contributed to misfit (RQ3); a quantity-based, 4-category ordinal scale outperformed quality-based or binary scales (RQ4); sentence length significantly explained item difficulty only, with small variance explained (RQ5); Corpus-based lexical measures and phrase-level syntactic complexity were important to predicting item difficulty, particularly for the higher ability level. The findings made implications for EI scale / item development in human and automatic scoring settings and L2 English proficiency development.</p>

Background: Scoring models are widely established in the intensive care unit (ICU). However, the importance in patients with ruptured abdominal aortic aneurysm (RAAA) remains unclear. Our aim was to analyze scoring systems as predictors of survival in patients undergoing open surgical repair (OSR) for RAAA. Methods: This is a retrospective study in critically ill patients in a surgical ICU at a university hospital. Sixty-eight patients with RAAA were treated between February 2005 and June 2013. Serial measurements of Sequential Organ Failure Assessment score (SOFA), Simplified Acute Physiology Score II (SAPS II) and Simplified Therapeutic Intervention Scoring System-28 (TISS-28) were evaluated with respect to in-hospital mortality. Eleven patients had to be excluded from this study because 6 underwent endovascular repair and 5 died before they could be admitted to the ICU. Results: All patients underwent OSR. The initial, highest, and mean of SOFA and SAPS II scores correlated significant with in-hospital mortality. In contrast, TISS-28 was inferior and showed a smaller area under the receiver operating curve. The cut-off point for SOFA showed the best performance in terms of sensitivity and specificity. An initial SOFA score below 9 predicted an in-hospital mortality of 16.2% (95% CI, 4.3–28.1) and a score above 9 predicted an in-hospital mortality of 73.7% (95% CI, 53.8–93.5, p < 0.01). Trend analysis showed the largest effect on SAPS II. When the score increased or was unchanged within the first 48 h (score >45), the in-hospital mortality rate was 85.7% (95% CI, 67.4–100, p < 0.01) versus 31.6% (95% CI, 10.7–52.5, p = 0.01) when it decreased. On multiple regression analysis, only the mean of the SOFA score showed a significant predictive capacity with regards to mortality (odds ratio 1.77; 95% CI, 1.19–2.64; p < 0.01). Conclusion: SOFA and SAPS II scores were able to predict in-hospital mortality in RAAA within 48 h after OSR. According to cut-off points, an increase or decrease in SOFA and SAPS II scores improved sensitivity and specificity.