過去國內之抵押貸款提前清償與逾期還款之相關研究，在實證研究上最主要利用邏輯斯迴歸或是比例轉機模型( Proportional hazard model )分析影響一般住宅抵押貸款人提前清償與逾期還款之因素，並估計一般住宅抵押貸款人提前清償之機率。本文選擇採用研究抵押貸款時，國內未曾使用之卜瓦松迴歸( Poisson regression model )來估計比例轉機模型假設下影響提前清償與違約變數之參數，以研究影響抵押貸款借款人之提前償還與違約因素。 本研究結合比例轉機模型與卜瓦松迴歸模型，目的在結合兩模型之優點，在處理時間相依之共變數效率提高，並且在處理多重時間尺度的方程式較偏最大概似估計法直接，以得到較佳的研究成果。另外，過去國內提前清償與違約之文獻中並未加入利率走勢之變數，本研究加入再融資利率對31∼90天期商業本票利率之比率與再融資利率波動性兩變數，以考慮利率走勢對貸款者提前清償及違約行為之影響。 模型中的解釋變數包括地區、季節、抵押貸款年齡、貸款成數、貸款人年齡、性別、婚姻狀況、教育程度、職業、屋齡、房屋坪數、所得、貸款金額、月付額對薪資比、再融資利率/31∼90天期商業本票利率、再融資利率波動性等十六項。實證結果在提前清償部份，顯著正向之變數有貸款年齡、屋齡、房屋坪數、所得、月付額與薪資比，顯著負向之變數包括季節、再融資利率對31∼90天期商業本票利率之比率、貸款金額。在違約部份，顯著正向之變數包括貸款年齡、貸款成數、年齡、所得、月付額與薪資比、再融資利率對31∼90天期商業本票利率之比率；顯著負向之變數包括季節、教育程度及貸款金額。

本研究利用離散時間涉險模型，分析台灣上市公司之多角化程度、公司治理與財務危機之關係。本研究分為三階段逐步加入多角化程度變數、公司治理與多角化程度之交叉相乘項及控制變數。首先探討相關或非相關多角化程度是否與公司發生財務危機之可能性具有關聯性。接著納入公司治理之考量，探究公司治理、相關或非相關多角化程度與公司發生財務危機可能性間之關係。 實證結果顯示，無論是相關多角化或是非相關多角化均可顯著降低公司發生財務危機之可能性。當納入公司治理之考量後，實證結果顯示，當公司的董監質押比率、控制股東持股比率、關係人進貨比率、關係人融資比率、席次控制比率、董事席次等6項公司治理指標愈差時，公司的相關多角化程度愈高，發生財務危機的可能性也會提高；而當公司的控制股東持股比率、關係人進貨比率、關係人融資比率、席次控制比率、董事席次等5項公司治理指標愈差時，公司的非相關多角化程度愈高，發生財務危機的可能性也會愈高。 / This study employs discrete-time hazard model to investigate how the distress-diversification sensitivity is moderated depending on the level of corporate governance in nested models which sequentially incorporate diversification and then corporate governance as a moderator. The findings show that diversification reduces the possibility of financial distress while corporate governance moderates the diversification effect on financial distress.

Who can survive longer and what factors could prolong the trading life of individual investors in the market? This is the questions we ask in the dissertation. Based on our knowledge, there is not any research about the issue of survival analysis on analyzing individual investors in stock market. The paper classifies three possibilities could affect the trading life of investors: personal characteristics, trading behavior, and market condition. In the dissertation, we use tick-by-tick transaction data from the Taiwan Stock Exchange to profile survivors versus non-survivors, to investigate how the traders’ characteristics (such as, gender), trading behaviors (such as the degree of diversification, trading amount and trading frequency) and market condition affect the trading life of investors. We borrow the proportional hazard models proposed by Cox (1972) who used in bio-statistics to analyze the survival rate. Using the Kaplan-Meier curves for male and female, we find that survival functions and hazard rates of female investors have better survival prognosis than the male investors. Different timing of entering results in distinct patterns of survival curves and hazard rates. Investors entering that market in the bull and bear market have a larger survival rate than those who enter the market in normal time during the trading life from 1 to 7 years. Moreover, as the trading life increases larger 7 year, the three curves of bull, bear and normal market conditions, respectively, appear to get closer, suggesting that if trading life is shorter than 7 years, the investors entering in the bull and bear markets seemly have lower hazard ratio than that in the normal market to leave the market. Finally, the results of Cox’s proportional hazard model show that female investors stay in the market 74 days longer than the male. Trading cycle increasing by one day will prolong the traders in the market by 4.8 days. Average volume per trade measured in ten thousands does not have economic effect on the trading duration, although its estimate is statistically significant. A one percentage increase of portfolio return will reduce about 151 days of the trading life. One more stock in the portfolio will prolong about 133 days in the trading life. The effect on the trading duration of trading performance of those who enter in the bull market is positive. / Who can survive longer and what factors could prolong the trading life of individual investors in the market? This is the questions we ask in the dissertation. Based on our knowledge, there is not any research about the issue of survival analysis on analyzing individual investors in stock market. The paper classifies three possibilities could affect the trading life of investors: personal characteristics, trading behavior, and market condition. In the dissertation, we use tick-by-tick transaction data from the Taiwan Stock Exchange to profile survivors versus non-survivors, to investigate how the traders’ characteristics (such as, gender), trading behaviors (such as the degree of diversification, trading amount and trading frequency) and market condition affect the trading life of investors. We borrow the proportional hazard models proposed by Cox (1972) who used in bio-statistics to analyze the survival rate. Using the Kaplan-Meier curves for male and female, we find that survival functions and hazard rates of female investors have better survival prognosis than the male investors. Different timing of entering results in distinct patterns of survival curves and hazard rates. Investors entering that market in the bull and bear market have a larger survival rate than those who enter the market in normal time during the trading life from 1 to 7 years. Moreover, as the trading life increases larger 7 year, the three curves of bull, bear and normal market conditions, respectively, appear to get closer, suggesting that if trading life is shorter than 7 years, the investors entering in the bull and bear markets seemly have lower hazard ratio than that in the normal market to leave the market. Finally, the results of Cox’s proportional hazard model show that female investors stay in the market 74 days longer than the male. Trading cycle increasing by one day will prolong the traders in the market by 4.8 days. Average volume per trade measured in ten thousands does not have economic effect on the trading duration, although its estimate is statistically significant. A one percentage increase of portfolio return will reduce about 151 days of the trading life. One more stock in the portfolio will prolong about 133 days in the trading life. The effect on the trading duration of trading performance of those who enter in the bull market is positive.

As researchers increasingly use web-based surveys, the ease of dropping out in the online setting is a growing issue in ensuring data quality. One theory is that dropout or attrition occurs in phases that can be generalized to phases of high dropout and phases of stable use. In order to detect these phases, several methods are explored. First, existing methods and user-specified thresholds are applied to survey data where significant changes in the dropout rate between two questions is interpreted as the start or end of a high dropout phase. Next, survey dropout is considered as a time-to-event outcome and tests within change-point hazard models are introduced. Performance of these change-point hazard models is compared. Finally, all methods are applied to survey data on patient cancer screening preferences, testing the null hypothesis of no phases of attrition (no change-points) against the alternative hypothesis that distinct attrition phases exist (at least one change-point).

Selection of signi?cant genes via expression patterns is important in a microarray problem. Owing to small sample size and large number of variables (genes), the selection process can be unstable. This research proposes a hierarchical Bayesian model for gene (variable) selection. We employ latent variables in a regression setting and use a Bayesian mixture prior to perform the variable selection. Due to the binary nature of the data, the posterior distributions of the parameters are not in explicit form, and we need to use a combination of truncated sampling and Markov Chain Monte Carlo (MCMC) based computation techniques to simulate the posterior distributions. The Bayesian model is ?exible enough to identify the signi?cant genes as well as to perform future predictions. The method is applied to cancer classi?cation via cDNA microarrays. In particular, the genes BRCA1 and BRCA2 are associated with a hereditary disposition to breast cancer, and the method is used to identify the set of signi?cant genes to classify BRCA1 and others. Microarray data can also be applied to survival models. We address the issue of how to reduce the dimension in building model by selecting signi?cant genes as well as assessing the estimated survival curves. Additionally, we consider the wellknown Weibull regression and semiparametric proportional hazards (PH) models for survival analysis. With microarray data, we need to consider the case where the number of covariates p exceeds the number of samples n. Speci?cally, for a given vector of response values, which are times to event (death or censored times) and p gene expressions (covariates), we address the issue of how to reduce the dimension by selecting the responsible genes, which are controlling the survival time. This approach enables us to estimate the survival curve when n << p. In our approach, rather than ?xing the number of selected genes, we will assign a prior distribution to this number. The approach creates additional ?exibility by allowing the imposition of constraints, such as bounding the dimension via a prior, which in e?ect works as a penalty. To implement our methodology, we use a Markov Chain Monte Carlo (MCMC) method. We demonstrate the use of the methodology with (a) di?use large B??cell lymphoma (DLBCL) complementary DNA (cDNA) data and (b) Breast Carcinoma data. Lastly, we propose a mixture of Dirichlet process models using discrete wavelet transform for a curve clustering. In order to characterize these time??course gene expresssions, we consider them as trajectory functions of time and gene??speci?c parameters and obtain their wavelet coe?cients by a discrete wavelet transform. We then build cluster curves using a mixture of Dirichlet process priors.

Selection of signi?cant genes via expression patterns is important in a microarray problem. Owing to small sample size and large number of variables (genes), the selection process can be unstable. This research proposes a hierarchical Bayesian model for gene (variable) selection. We employ latent variables in a regression setting and use a Bayesian mixture prior to perform the variable selection. Due to the binary nature of the data, the posterior distributions of the parameters are not in explicit form, and we need to use a combination of truncated sampling and Markov Chain Monte Carlo (MCMC) based computation techniques to simulate the posterior distributions. The Bayesian model is ?exible enough to identify the signi?cant genes as well as to perform future predictions. The method is applied to cancer classi?cation via cDNA microarrays. In particular, the genes BRCA1 and BRCA2 are associated with a hereditary disposition to breast cancer, and the method is used to identify the set of signi?cant genes to classify BRCA1 and others. Microarray data can also be applied to survival models. We address the issue of how to reduce the dimension in building model by selecting signi?cant genes as well as assessing the estimated survival curves. Additionally, we consider the wellknown Weibull regression and semiparametric proportional hazards (PH) models for survival analysis. With microarray data, we need to consider the case where the number of covariates p exceeds the number of samples n. Speci?cally, for a given vector of response values, which are times to event (death or censored times) and p gene expressions (covariates), we address the issue of how to reduce the dimension by selecting the responsible genes, which are controlling the survival time. This approach enables us to estimate the survival curve when n << p. In our approach, rather than ?xing the number of selected genes, we will assign a prior distribution to this number. The approach creates additional ?exibility by allowing the imposition of constraints, such as bounding the dimension via a prior, which in e?ect works as a penalty. To implement our methodology, we use a Markov Chain Monte Carlo (MCMC) method. We demonstrate the use of the methodology with (a) di?use large B??cell lymphoma (DLBCL) complementary DNA (cDNA) data and (b) Breast Carcinoma data. Lastly, we propose a mixture of Dirichlet process models using discrete wavelet transform for a curve clustering. In order to characterize these time??course gene expresssions, we consider them as trajectory functions of time and gene??speci?c parameters and obtain their wavelet coe?cients by a discrete wavelet transform. We then build cluster curves using a mixture of Dirichlet process priors.

Since 1997, fully noncontributory minimum pensions have been established in many Latin American countries, and have more recently been encouraged as a "zero pillar" of social security by the World Bank and other IFIs. These policies came into being under diverse political regimes and display a range of levels of generosity and universality. Becuase these policies are generally part of a modern bureaucratic welfare state project, they require identity documents, something that many low-income citizens do not possess. States have lowered barriers to the supply of identity documents, and new social policies, like noncontributory pensions and conditional or unconditional cash transfers, have stimulated demand for identity documents among those who do not currently have them. Brazils noncontributory pension, the BPC, has a means test and a large benefit (equivalent to the minimum wage), but requires providing identity documents for all household members. This report discusses the propagation of noncontributory pensions, then examines Brazilian government records to determine the size of the incentive to demand documents in Brazil using a logit model and a more novel survival time regression discontinuity design, raising questions of the relationships between benefit size, universality, document requirements, and poverty. / text

The input collected from warranty claims data links customer feedback with product quality. Results from warranty claim analysis can potentially improve product quality, customer relationships and positively affect business. However working on warranty claims data holds many challenges that requires a significant share of time devoted to data cleaning and data processing. The purpose of warranty claims analysis is to get the comprehensive overview of the reliability, costs and quality of household appliances produced by ASKO. While there are different ways to approach this problem, we will focus on non-parametric and semi-parametric methods, by using Kaplan-Meier estimators and Cox proportional hazard model respectively. These kinds of models are time dependent and therefore used for prediction of household appliance reliability. Even though non-parametric models are quite informative they cannot handle additional characteristics about observable product hence the semi-parametric Cox proportional hazard model was proposed. Apart from the reliability analysis, we will also predict warranty costs with probit model and observe inequality in household appliances part failures as a part of quality control analysis. Described methods were selected due to the fact that the warranty claims analysis will be practiced in future by ASKO’s quality department and therefore straight forward methods with very informative results are needed.

MSc (Statistics) / Department of Statistics / Selection of variables is vital in high dimensional statistical modelling as it aims to identify the right subset model. However, variable selection for discrete survival analysis poses many challenges due to a complicated data structure. Survival data might have unobserved heterogeneity leading to biased estimates when not taken into account. Conventional variable selection methods have stability problems. A simulation approach was used to assess and compare the performance of Least Absolute Shrinkage and Selection Operator (Lasso) and gradient boosting on discrete survival data. Parameter related mean squared errors (MSEs) and false positive rates suggest Lasso performs better than gradient boosting. Frailty models outperform discrete survival models that do not account for unobserved heterogeneity. The two methods were also applied on Zimbabwe Demographic Health Survey (ZDHS) 2016 data on age at first marriage and did not select exactly the same variables. Gradient boosting retained more variables into the model. Place of residence, highest educational level attained and age cohort are the major influential factors of age at first marriage in Zimbabwe based on Lasso. / NRF

The Eurasian wood wasp, Sirex noctilio, is considered a secondary pest in its native range; however, it has caused significant economic damage when introduced to pine plantations in the Southern Hemisphere. Sirex noctilio was recently introduced to the northeastern U.S., which has raised concerns about its potential impact on Southeastern pine plantations. This research was conducted to understand how silvicultural management affects populations of a native wood wasp, Sirex nigricornis, a wood wasp with similar ecosystem functions as S. noctilio. Sirex nigricornis abundance was higher in un-managed pine plantations than in managed plantations, mixed, and old growth forests. Additionally, geospatial models were built displaying S. noctilio hazard for the Southeastern U.S. based on oviposition host preference assays and historical outbreak information. Sirex noctilio hazard models will inform land managers about areas of greatest concern under various scenarios and should be used to decrease susceptibility of pine forests to this pest.