No description available.

No description available.

Background: Using a nude rat model of site-specific metastatic bone disease (MBD), we developed a semiquantitative histological score for rapid assessment of lytic lesions in bone. This provides additional information to conventional histological measurement by clarifying the extent and location of metastatic infiltration and the tumor growth pattern. The score can also be used to assess the action of bisphosphonates on bone metastases. Materials and Methods: Male nude rats (n = 12 per group) were inoculated with the human breast cancer cell line MDA-MB-231 via the femoral artery. Following appearance of radiographically visible osteolytic lesions on day 18, the animals received phosphate-buffered saline (PBS; controls) or ibandronate (IBN, 10 µg P/kg) daily until day 30. Whole body radiographs were obtained on days 18 and 30, and osteolytic areas (OA) were determined by radiographic computer-based analysis (CBA). On day 30, MBD was assessed in both tibias using conventional histological CBA and the new scoring system. Results: Metastatic tumor area correlated with the total sum of the new score in both PBS- (r = 0.762) and IBN-treated animals (r = 0.951; p < 0.001). OA correlated well with the total sum in both groups (r = 0.845 and 0.854, respectively; p < 0.001). Conclusion: Significant reduction of bone marrow and cortical infiltration of tumor cells with IBN suggested local control of metastases. / Hintergrund: Mit Hilfe eines etablierten Tiermodells zur Erzeugung lokalisationsspezifischer Knochenmetastasen in der Nacktratte wurde ein semiquantitatives histologisches Graduierungssystem zur schnellen Bewertung osteolytischer Knochenmetastasen entwickelt. Das Graduierungssystem liefert hinsichtlich der Metastasenlokalisation, deren Ausmaß und Infiltrationsmuster wertvolle Zusatzinformationen zu den konventionellen histologischen Untersuchungsmethoden. Damit kann beispielsweise auch die pharmakologische Wirkung von Bisphosphonaten auf die Knochenmetastasierung beurteilt werden. Material und Methoden: Männlichen Nacktratten (n = 12 pro Gruppe) wurden Zellen der humanen Brustkrebszellinie MDA-MB-231 in die Oberschenkelarterie inokuliert. Ab dem Auftreten radiologisch erkennbarer Osteolysen 18 Tage nach Inokulation erhielten die Tiere bis zum Studienende (Tag 30) täglich entweder eine subkutane Applikation einer Phosphat-Puffer-Lösung (Kontrollgruppe) oder Ibandronat (IBN, 10 µg P/kg; Behandlungsgruppe). Konventionelle Röntgenaufnahmen wurden an den Tagen 18 und 30 nach Tumorinokulation angefertigt und die Osteolysenflächen mittels Computerauswertung bestimmt. Nach Studienende wurde der Metastasenbefall in beiden Tibiae sowohl konventionell histologisch als auch mittels des neuen Graduierungssystems ausgewertet. Ergebnisse: Die Metastasenfläche korrelierte mit der kummulativen Punktsumme des Graduierungssystems sowohl in der Kontrollgruppe (r = 0,762; p < 0,001) als auch in der Ibandronat- Gruppe (r = 0,951; p < 0,001). Ebenso war die Osteolysenfläche eng mit der Punktesumme in beiden Gruppen korreliert (r = 0,845 und 0,854; p < 0,001). Schlussfolgerung: Die signifikante Reduktion von Knochenmark- und Kortikalisbefall durch IBN deuten auf eine gute lokale Kontrolle des Metastasenwachstums hin. / Dieser Beitrag ist mit Zustimmung des Rechteinhabers aufgrund einer (DFG-geförderten) Allianz- bzw. Nationallizenz frei zugänglich.

Introduction: The past decade has seen a significant shift in the demographics of childbearing in the United States. The average age of women at first birth has steadily increased over the last four decades, with the birth rate for women aged 40-44 more than doubling from 1990 to 2012. The aim of this study was to evaluate the risk of adverse pregnancy outcomes with increasing maternal age and paternal age using national health statistics data. Methods: The study population included 3 495 710 live births among women 15-54+ years of age from the 2012 Natality dataset. Outcomes were modeled for both maternal and paternal 5-year age groups using logistic regression analysis to calculate adjusted and unadjusted odds ratios (AORs, ORs) with 95% confidence intervals. Analysis was performed to examine the association between maternal and paternal age across seven different adverse outcomes, including low birthweight, low Apgar score, early term pregnancies, abnormal newborn conditions and presence of congenital anomalies. Results: The risks for most outcomes paralleled with advanced maternal age and paternal age. Logistic regression models demonstrated that maternal age groups 40-44, 45-49 and 50-54+ were at highest risk for an adverse pregnancy outcome compared to the 30-34 year old reference group. Abnormal newborn conditions including assisted ventilation, NICU admission and use of antibiotics were significant for all age groups 40 and older. Low Apgar score, low birthweight and early term pregnancies were significantly higher among mothers as well as fathers with advanced age. Conclusions: These findings suggest that advanced maternal age is a risk factor for a variety of adverse pregnancy outcomes. Women aged 35-39 have a similar risk of an adverse outcome as their younger counterparts. This suggests that perhaps we should begin assessing high-risk pregnancies as starting at an older age versus the de facto standard of 35.

觀察性研究資料中，透過傾向分數的使用，可以使基準變數在實驗與對照兩組間達到某種程度的平衡，並可視同為一隨機試驗，進而進行有效的統計推論。文獻中有關平衡與否的診斷，大多聚焦於平均數與變異數的比較。本文中我們提出使用KLIC(Kullback-Leibler Information Criterion)及KS(Kolmogorov and Simonov)兩種比較分配函數差異的統計量，作為另一種平衡診斷工具的構想，並針對其可行性進行探討與評比。此外，數據顯示KLIC及KS與透過傾向分數配對的成功比例呈現負相關。由於配對成功比例過低將導致後續統計推論結果的侷限性，因此本文也就KLIC及KS作為是否進行配對的一個先行指標之可行性作探討。模擬結果顯示，二者的答案均是肯定的。 / In observational studies, propensity scores are frequently used as tools to balance the distribution of baseline covariates between treated and untreated groups to some extent so that the data could be treated as if they were from a randomized controlled trial (RCT) and causal inferences could thus be made. In the past, balance or not was usually diagnosed in terms of the means and/or the variances. In this study, we proposed using either Kullback-Leibler Information Criterion (KLIC) or Kolmogorov and Simonov (KS) statistic as a diagnostic measure, and evaluated its feasibility. In addition, since low propensity score matching rate decreases the power of the statistical inference and a pilot study showed that the matching rate was negatively correlated with KLIC and KS; thus, we also discussed the possibilities of using KLIC and KS to be pre-indices before implementing propensity score matching. Both considerations appear to be positive through our simulation study.

Educators are increasingly being asked to interact with data to facilitate students’ learning in the classroom. However, as an educational measurement community, we have little understanding of the factors and/or contexts that facilitate educators’ successful use of data. Educators’ use of score reports and the relationship to the intended use is integral to the concept of validity. A conceptual model, “Data Habit of Mind,” is proposed to study educators’ understanding, interpretation and potential applications of results from large-scale assessments. The metaphor, “Habit of Mind,” was originally coined by Robert Sternberg and Dan Keating, and has been applied in the education sector to describe educators’ habits of inquiry when interacting with assessments. Based on an extensive review of the literature, Data Habit of Mind is defined as a combination of statistical literacy and score report interpretation. Statistical literacy is the extent to which an individual is able to describe, organize and reduce, represent, and analyze and interpret data. Score report interpretation is the extent to which an individual is able to describe, summarize, question, and propose an application for a given set of elements on a score report. The combination of these two makes up an individual’s Data Habit of Mind. Twenty educators were interviewed to assess their level of statistical literacy and their score report interpretation skills. A cognitive interview approach was used to capture the educators’ cognitive processes as they solved performance-based tasks, and protocol analysis procedures were used to encode the responses into the conceptual model. Descriptions of educators’ Data Habit of Mind were then generated through qualitative matrix analysis. Four groups of educators were identified based on the patterns of relationship between their statistical literacy and score report interpretation scores. Demographic factors, including teaching experience, gender and educational background were not meaningful predictors of educators’ Data Habit of Mind. These results add to our understanding of how educators interpret and use test results and have implications for test validation processes.

The purpose of this work was to study the ability of the Slacks-Based Model of Data Envelopment Analysis in the prediction of corporate failure of non-manufacturing companies as compared to Altman’s Z’’ score model. This research looks at non-manufacturing firms specifically and attempts to classify companies without looking at the asset size of the firm. A DEA model based on the Altman’s Z’’ score financial ratios was created as well as a revised DEA model. The overall accuracy of the models showed the revised DEA model to be more accurate than the original DEA model as well as the Altman Z’’ score. This indicated that bankruptcy could be predicted without the use of total assets or liabilities as variables. This also showed the ability of an SBM DEA model to predict bankruptcy.

Educators are increasingly being asked to interact with data to facilitate students’ learning in the classroom. However, as an educational measurement community, we have little understanding of the factors and/or contexts that facilitate educators’ successful use of data. Educators’ use of score reports and the relationship to the intended use is integral to the concept of validity. A conceptual model, “Data Habit of Mind,” is proposed to study educators’ understanding, interpretation and potential applications of results from large-scale assessments. The metaphor, “Habit of Mind,” was originally coined by Robert Sternberg and Dan Keating, and has been applied in the education sector to describe educators’ habits of inquiry when interacting with assessments. Based on an extensive review of the literature, Data Habit of Mind is defined as a combination of statistical literacy and score report interpretation. Statistical literacy is the extent to which an individual is able to describe, organize and reduce, represent, and analyze and interpret data. Score report interpretation is the extent to which an individual is able to describe, summarize, question, and propose an application for a given set of elements on a score report. The combination of these two makes up an individual’s Data Habit of Mind. Twenty educators were interviewed to assess their level of statistical literacy and their score report interpretation skills. A cognitive interview approach was used to capture the educators’ cognitive processes as they solved performance-based tasks, and protocol analysis procedures were used to encode the responses into the conceptual model. Descriptions of educators’ Data Habit of Mind were then generated through qualitative matrix analysis. Four groups of educators were identified based on the patterns of relationship between their statistical literacy and score report interpretation scores. Demographic factors, including teaching experience, gender and educational background were not meaningful predictors of educators’ Data Habit of Mind. These results add to our understanding of how educators interpret and use test results and have implications for test validation processes.

The purpose of this work was to study the ability of the Slacks-Based Model of Data Envelopment Analysis in the prediction of corporate failure of non-manufacturing companies as compared to Altman’s Z’’ score model. This research looks at non-manufacturing firms specifically and attempts to classify companies without looking at the asset size of the firm. A DEA model based on the Altman’s Z’’ score financial ratios was created as well as a revised DEA model. The overall accuracy of the models showed the revised DEA model to be more accurate than the original DEA model as well as the Altman Z’’ score. This indicated that bankruptcy could be predicted without the use of total assets or liabilities as variables. This also showed the ability of an SBM DEA model to predict bankruptcy.

Learning from data, especially ‘Big Data’, is becoming increasingly popular under names such as Data Mining, Data Science, Machine Learning, Statistical Learning and High Dimensional Data Analysis. In this dissertation we propose a new related field, which we call ‘United Nonparametric Data Science’ - applied statistics with “just in time” theory. It integrates the practice of traditional and novel statistical methods for nonparametric exploratory data modeling, and it is applicable to teaching introductory statistics courses that are closer to modern frontiers of scientific research. Our framework includes small data analysis (combining traditional and modern nonparametric statistical inference), big and high dimensional data analysis (by statistical modeling methods that extend our unified framework for small data analysis). The first part of the dissertation (Chapters 2 and 3) has been oriented by the goal of developing a new theoretical foundation to unify many cultures of statistical science and statistical learning methods using mid-distribution function, custom made orthonormal score function, comparison density, copula density, LP moments and comoments. It is also examined how this elegant theory yields solution to many important applied problems. In the second part (Chapter 4) we extend the traditional empirical likelihood (EL), a versatile tool for nonparametric inference, in the high dimensional context. We introduce a modified version of the EL method that is computationally simpler and applicable to a large class of “large p small n” problems, allowing p to grow faster than n. This is an important step in generalizing the EL in high dimensions beyond the p ≤ n threshold where the standard EL and its existing variants fail. We also present detailed theoretical study of the proposed method.