No description available.

Binary response data is often modeled using the logistic regression model, a well known nonlinear model. Designing an optimal experiment for this nonlinear situation poses some problems not encountered with a linear model. The application of several optimality design criteria to the logistic regression model is explored, and many resulting optimal designs are given. The implementation of these optimal designs requires the parameters of the model to be known. However, the model parameters are not known. If they were, there would be no need to design an experiment. Consequently the parameters must be estimated prior to implementing a design. Standard one-stage optimal designs are quite sensitive to parameter misspecification and are therefore unsatisfactory in practice. A two-stage Bayesian design procedure is developed which effectively deals with poor parameter knowledge while maintaining high efficiency. The first stage makes use of Bayesian design as well as Bayesian estimation in order to cope with parameter misspecification. Using the parameter estimates from the first stage, the second stage conditionally optimizes a chosen design optimality criterion. Asymptotically, the two-stage design procedure is considerably more efficient than the one-stage design when the parameters are misspecified and only slightly less efficient when the parameters are known. The superiority of the two-stage procedure over the one-stage is even more evident for small samples. / Ph. D.

In Victorian and Edwardian England, the grieving process involved numerous mortuary practices but the final and longest lasting of these is the stone monument placed over the grave or an engraving on an existing monument. However, comparison of burial records to monument records in rural Cambridgeshire, England would indicate that not all individuals received such a monument at their passing. This study explores the root of this variation through one of the most psychologically difficult deaths to navigate: that of a child. In this study, I compare those children who did not receive a stone monument to those that did as a function of the family’s socioeconomic class, the year of death, as well as the child’s age, gender, and place in the birth order at time of death. With a database of 11,578 individuals between the ages of 3 and 25 from 114 parishes in Cambridgeshire, this study is the largest of its kind and thus permits the exploration of interactions between these different factors. Using logistic regression modeling, I illustrate that the decision to erect a stone monument is demonstrably related to the child’s lived experience and the role they played in their household and community. Although rate of commemoration is not commonly explored in historical cemetery studies, this measurement offers valuable insight on the following themes: the emergence of adolescence and the ‘New Woman’, the drop in child fertility and mortality, the rise of the lower class over time, the role of girls within the household, the shift from conceptualizing children as economically useful to economically useless but emotionally priceless over time, the impact of major events like the agricultural depression and the First World War, and the impact that primogeniture had on the likelihood of commemoration. / Thesis / Doctor of Philosophy (PhD) / The death of a child evokes pain and loss that is, in part, reconciled through the grieving process. For Victorian and Edwardian parents in rural Cambridgeshire, England, this process involved burying their child in a local churchyard or cemetery and, in some cases, erecting a stone monument over the grave or having the child’s name carved on an existing monument. But comparison of burial and monument inscription records would indicate that only some children received this relatively expensive and permanent marker at their passing. This study explores differences in commemorative decision-making as a product of the child’s age at death, gender, the socioeconomic class of the family, the year they passed away, and the family structure. While the stone monument is unsurprisingly more common among children of the higher socioeconomic classes, I found that social change, such as shifts in gendered expectations, were also expressed in commemorative practice.

Thesis advisor: Zhushan Mandy Li / Differential item functioning (DIF) occurs when examinees of equal ability from different groups have different probabilities of correctly responding to certain items. DIF analysis aims to identify potentially biased items to ensure the fairness and equity of instruments, and has become a routine procedure in developing and improving assessments. This study proposed a DIF detection method using regularization techniques, which allows for simultaneous investigation of all items on a test for both uniform and nonuniform DIF. In order to evaluate the performance of the proposed DIF detection models and understand the factors that influence the performance, comprehensive simulation studies and empirical data analyses were conducted. Under various conditions including test length, sample size, sample size ratio, percentage of DIF items, DIF type, and DIF magnitude, the operating characteristics of three kinds of regularized logistic regression models: lasso, elastic net, and adaptive lasso, each characterized by their penalty functions, were examined and compared. Selection of optimal tuning parameter was investigated using two well-known information criteria AIC and BIC, and cross-validation. The results revealed that BIC outperformed other model selection criteria, which not only flagged high-impact DIF items precisely, but also prevented over-identification of DIF items with few false alarms. Among the regularization models, the adaptive lasso model achieved superior performance than the other two models in most conditions. The performance of the regularized DIF detection model using adaptive lasso was then compared to two commonly used DIF detection approaches including the logistic regression method and the likelihood ratio test. The proposed model was applied to analyzing empirical datasets to demonstrate the applicability of the method in real settings. / Thesis (PhD) — Boston College, 2019. / Submitted to: Boston College. Lynch School of Education. / Discipline: Educational Research, Measurement and Evaluation.

Fler konsumenter väljer att handla på internet. Vare sig det handlar om bekvämlighet eller priser har denna ökning en påverkan på hur detaljhandel sköts och distribueras. Kundkraven ändras och konsumenten har mer att säga till om. Rapporten syftar till att beskriva hur en ökad e-handel har påverkat och fortsatt kommer att påverka distributionen av detaljhandelsvaror nationellt. Den beskriver även hur ökningen påverkar distributionsföretagen och hur dessa i sin tur valt att agera för att bemöta förändringen som sker på marknaden. Vad som påverkar distributionsbolagen mest kommer också att beröras och rapporten ger en bild av e-handelns påverkan på distributionsföretagen. De slutsatser som kunnat dras av rapporten är att de ökande volymerna av gods från e-handel i dagsläget inte påverkat företagen nämnvärt, men att förändringar förmodligen kommer att behöva ske inom vissa områden i framtiden. Ökningen av e-handelsgods har gett distributionsföretagen en högre volym att hantera. De ökade volymerna för även med sig ytterligare kostnader i den mest kostsamma delen av distributionen, the last mile, genom att det blir fler leveranser till konsumentens hem. På grund av denna ökade kostnad ser distributionsföretagen ett behov av att öka sina vinstmarginaler genom att erbjuda konsumenten olika tilläggstjänster. Ytterligare ser företagen att det har blivit förändringar i de krav konsumenterna ställer. Krav på leveransservice blir allt högre och pressen på distributionsföretagen att ha kvalitet i sin produktion ökar. I dagens läge konstateras att volymerna alltjämt är för låga för att motivera en omfattande affärsutveckling med dyra investeringar för att möta den nivå av ökning som hittills skett. Detta kommer förmodligen vara nödvändigt i framtiden om ökningen fortsätter i samma takt som nu. Att utöka kunskapen och arbeta mer aktivt för att främja leveransservice är därför någonting som i rapporten framkommer som viktigt inför framtidens utmaningar. / More consumers choose to shop online. Whether it is because of convenience or prices this increase has an impact on how retailing is managed and distributed. Customer demands change and the consumer has more power. This report aims to describe how an increase in e-commerce has affected and will continue to influence the distribution of retail goods nationally and how it affects the companies providing transportation of e-commerce goods. The report also discuss how the distribution companies act in response to these changes in the market and which areas that have been affected the most. The conclusions drawn from the report is that the increasing volume of goods from e-commerce have not currently affected the distribution companies significantly, however in the future changes are believed to be necessary in certain areas. The increase of e-commerce goods has contributed to a higher volume of goods for distribution companies to manage. These increased volumes bring additional costs to the most expensive part of the distribution, the last mile, by bringing more deliveries to the consumer’s home. Because of this increase in costs, the distribution companies need to increase their margins by offering consumers additional services. Additionally, the companies see a change in the customer demands. Customer demands on delivery service are increasing and the pressure on the distribution companies to have a high quality in their production increases. Today the volume is still too low to justify a heavy business development with costly investments to counter the increasing volume. These changes will probably be necessary in the future if the increase continues at the same rate. To increase the knowledge and evolve the delivery service is something that this report indicates to be important in the future.

Made available in DSpace on 2015-03-05T18:39:03Z (GMT). No. of bitstreams: 0 Previous issue date: 28 / Nenhuma / Atualmente, o elevado grau de complexidade que caracteriza o ambiente empresarial, acompanhado de uma necessidade crescente de altos níveis de desempenho, exige a utilização de estratégias cada vez mais sofisticadas. Diante disso, a medição de desempenho surge como principal aliada no processo de gestão, com a percepção de que o desempenho é, em parte, resultado das decisões tomadas. Dentre os diversos modelos para mensuração do desempenho disponíveis na literatura, uma vulnerabilidade identificada é a relação linear entre seus componentes, que normalmente não reflete a interação com o ambiente mutável em que a organização está inserida. A utilização da lógica difusa foi considerada um mecanismo viável para compensar essa linearidade, revelando as prioridades que a organização precisa focar nos ambientes em que atua. Nesse contexto, o presente estudo se propôs a desenvolver um modelo de mensuração do desempenho logístico, apoiado pela lógica difusa, a fim de que sirva como suporte eficaz à tomada de decisão. / Nowadays, the raised complexity that characterizes the enterprise environment, followed by an increasing necessity of high levels of performance, demands the use of more sophisticated strategies. For this reason, the measurement of performance appears as main allied in the management process, with the perception that the performance is, in part, result of taken decisions. Among the different models for the performance measuring available in literature, an identified vulnerability is the linear relation between its components, which normally does not reflect the interaction with the changeable environment where the organization is inserted. The use of the fuzzy logic was considered a feasible mechanism to compensate this linearity, disclosing the priorities that organization needs to focus in the environments where it acts. In this context, the present study intended to develop a model of logistic performance measurement supported for the fuzzy logic, in order to work as an efficient support to decision taken.

För alpina skidåkare mäter man prestationer i så kallad FIS-ranking. Vi undersöker några metoder för hur man kan analysera data där responsen består av ranger som dessa. Vid situationer då responsdata utgörs av urval av ranger finns ingen självklar analysmetod. Det vi undersöker är skillnaderna vid användandet av olika regressionsanpassningar så som linjär, logistisk och ordinal logistisk regression för att analysera data av denna typ. Vidare används bootstrap för att bilda konfidensintervall. Det visar sig att för våra datamaterial ger metoderna liknande resultat när det gäller att hitta betydelsefulla förklarande variabler. Man kan därmed utgående från denna undersökning, inte se några skäl till varför man ska använda de mer avancerade modellerna. / Alpine skiers measure their performance in FIS ranking. We will investigate some methods on how to analyze data where response data is based on ranks like this. In situations where response data is based on ranks there is no obvious method of analysis. Here, we examine differences in the use of linear, logistic and ordinal logistic regression to analyze data of this type. Bootstrap is used to make confidence intervals. For our data these methods give similar results when it comes to finding important explanatory variables. Based on this survey we cannot see any reason why one should use the more advanced models.

If customers respond differently to a campaign, it is worthwhile to find those customers who respond most positively and direct the campaign towards them. This can be done by using so called incremental response analysis where respondents from a campaign are compared with respondents from a control group. Customers with the highest increased response from the campaign will be selected and thus may increase the company’s return. Incremental response analysis is applied to the mobile operator Tres historical data. The thesis intends to investigate which method that best explain the incremental response, namely to find those customers who give the highest incremental response of Tres customers, and what characteristics that are important.The analysis is based on various classification methods such as logistic regression, Lassoregression and decision trees. RMSE which is the root mean square error of the deviation between observed and predicted incremental response, is used to measure the incremental response prediction error. The classification methods are evaluated by Hosmer-Lemeshow test and AUC (Area Under the Curve). Bayesian logistic regression is also used to examine the uncertainty in the parameter estimates.The Lasso regression performs best compared to the decision tree, the ordinary logistic regression and the Bayesian logistic regression seen to the predicted incremental response. Variables that significantly affect the incremental response according to Lasso regression are age and how long the customer had their subscription.

Every day most people are using applications and services that are utilising machine learning, in some way, without even knowing it. Some of these applications and services could, for example, be Google’s search engine, Netflix’s recommendations, or Spotify’s music tips. For machine learning to work it needs data, and often a large amount of it. Roughly 2,5 quintillion bytes of data are created every day in the modern information society. This huge amount of data can be utilised to make applications and systems smarter and automated. Time logging systems today are usually not smart since users of these systems still must enter data manually. This bachelor thesis will explore the possibility of applying machine learning to task logging systems, to make it smarter and automated. The machine learning algorithm that is used to predict the user’s task, is called multiclass logistic regression, which is categorical. When a small amount of training data was used in the machine learning process the predictions of a task had a success rate of about 91%.

Diploma thesis is focused on a selection of a supplier with regard of total costs. In an introductory part of the thesis there is theoretical background about selection of the supplier, logistic costs and analysis of total costs. In practical part of the thesis, the problematic is applied on two concrete examples in Bosch concern.