Esta dissertação aborda a caracterização mecânica de um robô manipulador paralelo de 3 graus de liberdade. A topologia do manipulador corresponde a um mecanismo de estrutura cinemática paralela, cujo efetuador é capaz de realizar 3 deslocamentos lineares no espaço tridimensional. A tecnologia associada ao controle de robôs de estrutura cinemática serial encontra-se bastante madura. No entanto, o mesmo não se dá nos robôs paralelos. Para que se avance no domínio do controle de trajetória destes robôs é necessária a sua caracterização mecânica, a qual fornecerá os subsídios para identificação paramétrica, calibração de modelos, ajuste de ganhos dos controladores, etc. Especificamente, a caracterização mecânica neste trabalho teve por objetivo o levantamento experimental dos erros de posicionamento do efetuador com relação a exatidão e repetibilidade, sua rigidez sob a ação de cargas externas, bem como das frequências naturais do sistema. Os ensaios realizados foram executados no robô Laila, que é um protótipo físico de um robô manipulador, desenvolvido pelo Departamento de Engenharia Mecatrônica e Sistemas Mecânicos da Escola Politécnica da Universidade de São Paulo. A dissertação apresenta como resultados os mapeamentos dos erros de posicionamento do efetuador, a rigidez sob a ação de cargas externas, bem como suas frequências naturais, ao longo do espaço de medição. A seguir, apresenta-se uma discussão da consistência dos valores obtidos para estas propriedades. Por fim, é feita uma análise sobre a influência das folgas mecânicas sobre os índices de desempenho do robô. / This dissertation deals with the mechanical characterization of a parallel manipulator robot of 3 degrees of freedom. The topology of the manipulator corresponds to a mechanism of parallel kinematic structure, whose effector is capable of performing 3 linear displacements in the three-dimensional space. The technology associated with the control of robots of serial kinematic structure is quite mature. However, the same is not true of parallel robots. In order to advance in the field of control of trajectory of these robots it is necessary to characterize them mechanically, which will provide the subsidies for parametric identification, calibration of models, adjustment of gains of the controllers, etc. Specifically, the mechanical characterization in this work had as objective the experimental study of the positioning errors of the effector in relation to the accuracy and repeatability, its rigidity under the action of external loads, as well as the natural frequencies of the system. The tests were performed in the Laila robot, which is a physical prototype of a manipulator robot, developed by the Department of Mechatronics Engineering and Mechanical Systems of the Polytechnic School of the University of São Paulo. The dissertation presents as results the mappings of the positioning errors of the effector, the rigidity under the action of external loads, as well as their natural frequencies, along the measurement space. The following is a discussion of the consistency of the values obtained for these properties. Finally, an analysis is made on the influence of the mechanical gaps on the performance indexes of the robot.

Dada a importância de um sistema de prescrição, a possibilidade de ocorrências de erros no referido sistema e as conseqüências de tais erros nos resultados da terapia medicamentosa oferecida aos pacientes de uma Instituição, resolvemos desenvolver o presente trabalho. Os objetivos deste trabalho foram analisar o registro de erros relacionados à prescrição de medicamentos à pacientes internos, preparados e dispensados pela Divisão de Assistência Farmacêutica do Hospital das Clínicas da FMRP-USP, bem como contribuir para a melhoria e aprimora mento do sistema de prescrição de medicamentos e consequentemente para o uso seguro e racional dos mesmos no Hospital das Clínicas da FMRP-USP. Foi efetuado um estudo descritivo, inquérito prospectivo. Teve como população de referência prescri ções médicas e como população de estudo as prescrições médicas elabo radas pelos médicos no Hospital das Clínicas da Faculdade de Medicina de Ribeirão Preto da Universidade de São Paulo. Os participantes foram as prescrições que satisfizeram os critérios de inclusão, quais sejam: prescrições médicas do Hospital das Clínicas da FMRP-USP a partir do mês de outubro de 2006, até atingir o tamanho amostral. Foi utilizada uma amostragem de conveniência até completar o número (n) de 3.456 prescrições. Depois de analisadas 3.456 prescrições concluímos que 9,05% das mesmas 17 apresentaram erros (IC entre 9% e 11%); 61,3% apresentaram erro administrativo, 20,8% erro de prescrição e 17,9% erros administrativos e erros de prescrição concomitantemente. Os erros administrativos e de prescrição foram mais freqüentes entre os médicos residentes e docentes e os erros administrativos concomitantes com os de prescrição foram entre os docentes; a versão II da prescrição eletrônica apresentou 79,8% de erros seguida da prescrição liberada pela enfermagem, que apresentou 15,4%; as clínicas que apresentaram maior quantidade de erros, por ordem decrescente, foram a Dermatologia, com 9,6%, a Urologia e Cardiologia com 8%, a Neurocirurgia com 7,0%, o Centro de Terapia Intensiva com 6,7% e a Proctologia e Gastrocirurgia, com 6,4%; o erro de leito do paciente foi o mais freqüente e cometido pelo médico residente 65,8%, seguido pelo médico contratado 25,6%; o erro de medicamento foi o erro de prescrição de maior freqüência, seguido pelo erro de dose e posteriormente pelo nome comercial; a maior freqüência de erros administrativos foi detectada na Dermatologia, seguida pela Cardiologia, Neurocirurgia e Gastrocirurgia; a maior freqüência de erros de prescrição foi observada na Ortopedia, Hematologia e Imunologia; a maior freqüência de erros de dose foi detectada na Ortopedia. / Owing to the importance of a prescription system, the possibility of error occurrences in such system, and the consequences of such errors in the results of the medicine therapy offered to the patients from an Institution, we decided to develop the current work. called . This study aims to analyze the records of errors related to the prescription of medicines to internal patients, which were prepared and issued by the Divisão de Assistência Farmacêutica do Hospital das Clínicas da FMRP-USP. It also intends to contribute to the improvement of medicine prescription systems and consequent development of sensible and safe uses of such medicines in the Hospital das Clínicas da FMRP-USP. An inquiring prospective and descriptive study was carried out, which had as referential population some medical prescriptions, and as study population the medical prescriptions elaborated by physicians in Hospital das Clínicas da FMRPUSP. The prescriptions complying with the inclusion criteria were chosen as participants; such criteria being: medical prescriptions from the Hospital das Clínicas of the FMRP-USP from October, 2006, until achieving the sample amount. A convenient sample was used until completing the number (n) of 3.456 prescriptions. After analyzing 3,456 prescriptions it was mainly concluded that: 10% of the studied prescriptions presented errors (IC between 9% and 11%); 61,3% of the prescriptions presented administrative errors, 20.8% presented prescription errors and 17.9% presented adminis trative and prescription errors concomitantly. The administrative and prescription errors occurred more frequently between resident physicians and professors, while concomitant administrative and prescription errors were more common among professors. The version II of the electronic pres cription presented 79.8% of errors, followed by prescriptions issued by the nursing which were 15,4%. The clinics presenting greater amount of errors, in decreasing order, were the Dermatology Department, with 9,6%, the Urology and Cardiology Department with 8%, the Neurosurgery Department with 7,0%, the Intensive Therapy Center, with 6,7% and the Proctology and Gastrosurgery Departments, with 6,4%. The most frequent error made by resident doctors was in reference to the patient bed, 65.8%, followed by hired doctors: 25.6%. The medicine error was the most common prescription error, followed by dosage and trade mark. The most usual administrative errors were found in the Dermatology Department, followed by the Cardiology Department, Neurosurgery and Gastrosurgery Departments; the most common prescription errors were observed in the Orthopedic, Hematology and Imunology Departments. Finally, the most frequent dosage errors were found in the Orthopedic Department.

O presente trabalho é uma formulação teórica que permite estudar num modelo estocástico, a influência dos erros de classificação na mensuração da prevalência da esquistossomose mansônica. Os erros de classificação são desagregados e identificados como: falhas de leitura por parte do examinador ou preparo inadequado da lâmina; contingências biológicas que possibilitam o aparecimento de ovos não viáveis e a eliminação de ovos contínua por parte dos indivíduos. É apresentada uma solução geral para o problema, bem como soluções para os casos em que se conhece a distribuição de probabilidades do número de ovos de S.mansoni. Uma solução aproximada e independente da forma e dependente dos dois primeiros momentos da distribuição do número de ovos é sugerida. A influência dos erros de classificação pode quantitativamente ser apreciada, através de um conjunto de tabelas elaboradas com diversos valores dos parâmetros intervenientes no problema. / The present paper is a theoretical approach which will, allow studying the influence - in a stochastic model - of errors in classifying the measurement of the prevalence of Schistosomiasis mansoni. The misclassification errors considered are due to: (A) failure of the examiner in either (1) reading or (2) poor technique. (B) biological contingences which will allow for the appearence of (1) sterile eggs, or (2) discontinuity in the elimination of eggs by the carriers. An exact general solution of the problem is presented, as well as solutions for the particular cases in which the probability distribution of S.mansoni eggs counts in known. An approximate solution is suggested, which is independent from the way in which the number of eggs is distributed, but depends upon the first two moments of the probability distribution of the eggs counts. The influence of misclassification errors can be judged in a quantitative way, by means of a set of tables mande up for the different parametric values of the problem.

by Guo Sujuan. / Bibliography: leaves 145-151 / Thesis (M.Ph.)--Chinese University of Hong Kong, 1986

呂淑貞 = A study of lexical errors of secondary school students in Hogn Kong / Lui Suk Ching. / 據手稿本影印. / Thesis (M.A.)--香港中文大學硏究院敎育學部. / Ju shou gao ben ying yin. / Includes bibliographical references (leaves 278-284). / Lü Shuzhen = A study of lexical errors of secondary school students in Hong Kong / Lui Suk Ching. / Thesis (M.A.)--Xianggang Zhong wen da xue yan jiu yuan jiao yu xue bu. / 論文摘要 / Chapter 第一章 --- 引言 --- p.1 / Chapter (I) --- 香港寫作教學的現狀 --- p.4 / Chapter (II) --- 研究動機與目的 --- p.6 / Chapter (III) --- 研究意義 / Chapter 第二章 --- 文獻回顧 / Chapter 甲 --- 詞是什麼 / Chapter (I) --- 詞的定義 --- p.8 / Chapter (II) --- 詞和詞組 --- p.11 / Chapter (III) --- 詞和詞素 --- p.14 / Chapter (IV) --- 詞的詞匯意義和語法意義 --- p.16 / Chapter (V) --- 漢語的造詞法體系 --- p.25 / Chapter 乙 --- 現代漢語詞匯現範化的標準和內容 --- p.27 / Chapter (I) --- 方言詞的規範 --- p.28 / Chapter (II) --- 外來詞的規範 --- p.29 / Chapter 丙 --- 語誤分析 --- p.31 / Chapter (I) --- 語誤分析與語誤分類 --- p.31 / Chapter (II) --- 語誤分析的理論依据 --- p.31 / Chapter (III) --- 錯誤的來源 --- p.33 / Chapter (IV) --- 語誤分析的應用 --- p.34 / Chapter 丁 --- 謬詞分準則的釐訂 --- p.35 / Chapter (I) --- 謬詞的主要類型舉隅 --- p.35 / Chapter (II) --- 謬詞分類依據 --- p.37 / Chapter (III) --- 謬詞分類模式 --- p.38 / Chapter 第三章 --- 研究設計 --- p.41 / Chapter (I) --- 研究問題 --- p.41 / Chapter (II) --- 研究方法 --- p.42 / Chapter (III) --- 研究對象與取樣 --- p.43 / Chapter (IV) --- 研究工具 --- p.46 / Chapter (V) --- 實驗程序 --- p.47 / Chapter (VI) --- 資料分析及整理 --- p.49 / Chapter (VII) --- 研究局限 --- p.51 / Chapter 第四章 --- 研究結果及計論 / Chapter (I) --- 香港一般中學生作文中謬詞類型的分佈情況 --- p.52 / Chapter (II) --- 不同年級、不同語文程度及中、英文中學學生作文中謬詞類型分佈情況的差異 --- p.58 / Chapter (III) --- 各類型謬詞錯誤的原因 --- p.65 / Chapter 第五章 --- 建議 --- p.78 / Chapter 第六章 --- 結論 --- p.81 / 表（二）至表（五十五） --- p.84 / 註釋 / Chapter 附錄(一) --- 謬詞的主要類型舉隅 --- p.116 / Chapter (二) --- 謬詞的主要類型舉隅 --- p.117 / Chapter (三) --- 謬詞的主要類型舉隅 --- p.121 / Chapter (四) --- 各類型謬詞實錄 --- p.123 / 中文參考書目 --- p.278 / 英文參考書目 --- p.283

姜貝玲. / 據手稿本影印. / Thesis (M.A.)--香港中文大學硏究院敎育學部. / Ju shou gao ben ying yin. / Includes bibliographical references (leaves 142-146). / Jiang Beiling. / Thesis (M.A.)--Xianggang Zhong wen da xue yan jiu yuan jiao yu xue bu. / Chapter 第一章 --- 導言 --- p.1 / 研究緣起與目的 --- p.1 / 理論根據 --- p.4 / 假設 --- p.25 / 術語說明 --- p.26 / Chapter 第二章 --- 研究方法 --- p.30 / 研究設計 --- p.30 / 研究對象 --- p.34 / 研究工具 --- p.36 / 實驗程序 --- p.44 / 資料分析 --- p.47 / Chapter 第三章 --- 結果與討論 --- p.51 / 結果 --- p.51 / 討論 --- p.98 / Chapter 第四章 --- 摘要、結論與建議 --- p.128 / 摘要 --- p.128 / 結論 --- p.133 / 建議 --- p.138 / 參考文獻 --- p.142 / 附錄 --- p.153 / Chapter 一 --- 按提示在語段中填詞測驗卷 --- p.153 / Chapter 二 --- 按提示選詞在語段中填空測驗卷 --- p.157 / Chapter 三 --- 按提示在句子中填詞測驗卷 --- p.162 / Chapter 四 --- 按提示選詞在句子中填空測驗卷 --- p.166 / Chapter 五 --- 遣詞能力測驗評分參考 --- p.171

Lai Ching Ha. / Thesis (Ph.D.)--Chinese University of Hong Kong, 1995. / Includes bibliographical references (leaves 225-243). / Title --- p.1 / Abstract --- p.2 / Acknowledgments --- p.4 / Contents --- p.5 / Abbreviations --- p.10 / List of Figures --- p.12 / List of Tables --- p.15 / Chapter Chapter 1 --- Review on Inherited Metabolic Diseases --- p.18 / Chapter 1.1 --- Development of the concept of inherited metabolic diseases (IMD) --- p.18 / Chapter 1.2 --- Frequency of inherited metabolic diseases --- p.20 / Chapter 1.3 --- Molecular basis of mutations in inherited metabolic diseases --- p.22 / Chapter 1.3.1 --- Point mutations --- p.22 / Chapter 1.3.2 --- Small deletions and insertions --- p.25 / Chapter 1.3.3 --- large deletions or duplications --- p.26 / Chapter 1.4 --- Pathological consequences of protein defect resultingin IMD --- p.27 / Chapter 1.4.1 --- End product --- p.28 / Chapter 1.4.2 --- Precursor accumulation --- p.28 / Chapter 1.4.3 --- Unusual metabolites --- p.29 / Chapter 1.5 --- Heterogeneity of inherited metabolic diseases --- p.29 / Chapter 1.5.1 --- Genetic heterogeneity --- p.29 / Chapter 1.5.2 --- Variations of expression in different cells --- p.31 / Chapter 1.6 --- Diagnosis of inherited metabolic diseases --- p.32 / Chapter 1.6.1. --- Biochemical investigations --- p.32 / Chapter 1.6.2 --- Identification of accumulated or missing metabolites --- p.33 / Chapter 1.6.3 --- Direct analysis of enzymes and proteins --- p.34 / Chapter 1.6.4 --- Molecular investigations --- p.34 / Chapter 1.7 --- Treatment of inherited metabolic diseases --- p.40 / Chapter 1.7.1 --- Treatment at the clinical phenotype level --- p.41 / Chapter 1.7.2 --- Treatment at the metabolite level --- p.41 / Chapter 1.7.3 --- Treatment at the dysfunctional protein level --- p.43 / Chapter 1.7.4 --- Transplantation --- p.44 / Chapter 1.7.5 --- Gene therapy --- p.45 / Chapter 1.8 --- Inherited metabolic diseases in Hong Kong --- p.47 / Chapter 1.9 --- General Aim --- p.48 / Chapter Chapter 2 --- Study of Inherited Metabolic Diseases in Mentally Retarded Patients --- p.49 / Chapter 2.1 --- Introduction --- p.49 / Chapter 2.2 --- Aim --- p.52 / Chapter 2.3 --- Materials --- p.53 / Chapter 2.3.1 --- Standards --- p.53 / Chapter 2.3.2 --- Chemical reagents --- p.53 / Chapter 2.3.3 --- Derivatization reagents --- p.54 / Chapter 2.3.4 --- Major equipment --- p.54 / Chapter 2.4 --- Clinical materials --- p.56 / Chapter 2.4.1 --- Subjects --- p.55 / Chapter 2.4.2 --- Blood and urine samples --- p.56 / Chapter 2.5 --- Methods --- p.57 / Chapter 2.5.1 --- General biochemistry tests --- p.57 / Chapter 2.5.2 --- Metabolic screening tests --- p.57 / Chapter 2.5.3 --- Two-dimensional thin layer chromatography --- p.53 / Chapter 2.5.4 --- Identification of urinary organic acids by gas chromatography mass spectroscopy --- p.59 / Chapter 2.5.5 --- Amino acid analysis by high performance liquid chromatography --- p.66 / Chapter 2.6 --- Results --- p.71 / Chapter (A) --- Methodological Aspects / Chapter 2.6.1 --- Identification of urinary organic acids by gas chromatography-mass spectroscopy (GC-MS) --- p.71 / Chapter 2.6.2 --- Amino acid analysis by high performance liquid chromatography (HPLC) --- p.86 / Chapter (B) --- Patient Investigations / Chapter 2.6.3 --- General biochemistry tests --- p.107 / Chapter 2.6.4 --- Serum amino acid profiles --- p.113 / Chapter 2.6.5 --- Urinary organic acid analysis --- p.115 / Chapter 2.6.6 --- Case reports --- p.119 / Chapter 2.7 --- Discussion --- p.123 / Chapter 2.7.1 --- Identification of urinary organic acids by gas chromatography-mass spectroscopy (GC-MS) --- p.123 / Chapter 2.7.2. --- Amino acid analysis by high performance liquid chromatography (HPLC) --- p.130 / Chapter 2.7.3 --- Identification of inherited metabolic diseases (IMD)in an institutionalized mentally retarded patients --- p.136 / Chapter Chapter 3 --- Molecular Investigation of Maple Syrup Urine Disease --- p.140 / Chapter 3.1 --- Introduction --- p.140 / Chapter 3.1.1 --- Branched chain amino acids (BCAA) --- p.140 / Chapter 3.1.2 --- Metabolism of branched chain amino acids --- p.142 / Chapter 3.1.3 --- Maple syrup urine disease (MSUD) --- p.144 / Chapter 3.1.4 --- Classification of maple syrup urine disease --- p.146 / Chapter 3.1.5 --- Screening and diagnosis of maple syrup urine disease --- p.148 / Chapter 3.1.6 --- Treatment of maple syrup urine disease --- p.150 / Chapter 3.1.7. --- Branched chain a-ketoacid dehydrogenase complex (BCKDH) --- p.151 / Chapter 3.1.8 --- "Gene features of human E1α,E1β and E2 subunitsin branched chain α-ketoacid dehydrogenase complex" --- p.153 / Chapter 3.1.9 --- Molecular defects of the BCKDH gene complex --- p.156 / Chapter 3.1.10 --- MSUD in Hong Kong --- p.161 / Chapter 3.2 --- Aim --- p.163 / Chapter 3.3 --- Materials --- p.164 / Chapter 3.3.1 --- Source of skin fibroblasts --- p.164 / Chapter 3.3.2 --- Enzymes --- p.164 / Chapter 3.3.3 --- DNA markers --- p.164 / Chapter 3.3.4 --- Reagent Kits --- p.165 / Chapter 3.3.5 --- Primers --- p.165 / Chapter 3.3.6 --- Chemical reagents --- p.165 / Chapter 3.3.7 --- Nitrocellulose membrane --- p.166 / Chapter 3.3.8 --- Antiserum for Western blotting --- p.166 / Chapter 3.3.9 --- Radioisotopes --- p.166 / Chapter 3.4 --- Methods --- p.168 / Chapter 3.4.1 --- Preparation of buffers and solutions --- p.168 / Chapter 3.4.2 --- Agarose gel electrophoresis --- p.170 / Chapter 3.4.3 --- Preparation of native polyacrylamide gel --- p.171 / Chapter 3.4.4 --- Preparation of sodium dodecyl sulfate (SDS) polyacrylamide gel --- p.172 / Chapter 3.4.5 --- Preparation of denaturing polyacrylamide gel --- p.173 / Chapter 3.4.6 --- Branched chain α-ketoacid dehydrogenase complex enzyme assay --- p.173 / Chapter 3.4.7. --- Identification of the affected subunits in BCKDH complex of MSUD patient and her family members --- p.176 / Chapter 3.4.8 --- Screening of mutation in the BCKDH subunits by RT-PCR-SSCP --- p.178 / Chapter 3.4.9 --- Mutation analysis of whole cDNA fragments of Elα， Elβ and E2 subunits by ds DNA cycle sequencing --- p.184 / Chapter 3.5 --- Results --- p.188 / Chapter 3.5.1 --- Branched chain α-ketoacid dehydrogenase complex enzyme assay --- p.188 / Chapter 3.5.2 --- Identification of the affected subunits in BCKDH complex ofMSUD patient and her family members --- p.188 / Chapter 3.5.3 --- Screening of mutation in the BCKDH subunits by RT-PCR-SSCP --- p.192 / Chapter 3.5.4 --- "Mutation analysis of whole cDNA fragments of Ela, Elβ and E2 subunits by ds DNA cycle sequencing" --- p.204 / Chapter 3.6 --- Discussion --- p.210 / Chapter 3.6.1 --- BCKDH activity in the MSUD patient and her family members --- p.210 / Chapter 3.6.2 --- Investigation of the mutation sites --- p.212 / General Conclusion --- p.222 / Appendix --- p.224 / References --- p.225

The current classroom environment is filled with expectations for both teacher and student but is often lacking in time. Skolverket (2011) outlines ambitious goals such as developing students’ critical thinking abilities, adapting teaching to each student’s individual needs, and encouraging students to actively take part in the development of their own educational process, to name just a few. It is crucial to develop and use techniques that aid in attaining these objectives. Peer response could be such a tool. There is an abundance of research which demonstrates how effective it is, but there is also a great reluctance on the part of teachers and students alike to employ it in the classroom. This could be due in part to the idea that learners lack the necessary knowledge to correct and give feedback. However, this and other criticisms directed against peer feedback could be alleviated through deliberate formal peerresponse training. Most of today’s research on this topic seems to focus on English as a Second or Foreign Language (ESL/EFL) classrooms in the U.S.A and Asia, with little work having been done in the Swedish context. Also lacking are investigations regarding peer response in grammar testing, since most of the research emphasizes essay writing. This paper aims to add to the body of existing research on prompted peer response by examining its application in English classrooms in Sweden. To do so, two secondary school English classes in Sweden are tested by means of an abbreviated version of Gan’s (2011) prompted peer response model. More specifically, this paper’s objective is to explore if prompted peer response leads to improvements in grammar (operationalized in this case as reducing grammatical errors in a grammar test) when compared to unprompted peer response. In addition, this paper intends to explore whether peer response can possibly produce any additional rewards and what those could be. The results for this study seem promising. The primary results of this paper support the existing research in this area that prompted peer response leads to a reduction in student’s grammatical errors. Perhaps more importantly, the results suggest that it also aids students in developing a progressive approach to peer response which ultimately can lead to students developing learning strategies and self-reflection over their own learning process.

This thesis consists of three papers in applied statistics, specifically in cluster sampling, causal inference, and measurement error. The first paper studies the problem of estimating the finite population mean from a two-stage sample with unequal selection probabilies in a Bayesian framework. Cluster sampling is common in survey practice, and the corresponding inference has been predominantly design-based. We develop a Bayesian framework for cluster sampling and account for the design effect in the outcome modeling. In a two-stage cluster sampling design, clusters are first selected with probability proportional to cluster size, and units are then randomly sampled within selected clusters. Methodological challenges arise when the sizes of nonsampled cluster are unknown. We propose both nonparametric and parametric Bayesian approaches for predicting the cluster size, and we implement inference for the unknown cluster sizes simultaneously with inference for survey outcome. We implement this method in Stan and use simulation studies to compare the performance of an integrated Bayesian approach to classical methods on their frequentist properties. We then apply our propsed method to the Fragile Families and Child Wellbeing study as an illustration of complex survey inference. The second paper focuses on the problem of weak instrumental variables, motivated by estimating the causal effect of incarceration on recidivism. An instrument is weak when it is only weakly predictive of the treatment of interest. Given the well-known pitfalls of weak instrumental variables, we propose a method for strengthening a weak instrument. We use a matching strategy that pairs observations to be close on observed covariates but far on the instrument. This strategy strengthens the instrument, but with the tradeoff of reduced sample size. To help guide the applied researcher in selecting a match, we propose simulating the power of a sensitivity analysis and design sensitivity and using graphical methods to examine the results. We also demonstrate the use of recently developed methods for identifying effect modification, which is an interaction between a pretreatment covariate and the treatment. Larger and less variable treatment effects are less sensitive to unobserved bias, so identifying when effect modification is present and which covariates may be the source is important. We undertake our study in the context of studying the causal effect of incarceration on recividism via a natural experiment in the state of Pennsylvania, a motivating example that illustrates each component of our analysis. The third paper considers the issue of measurement error in the context of survey sampling and hierarchical models. Researchers are often interested in studying the relationship between community-levels variables and individual outcomes. This approach often requires estimating the neighborhood-level variable of interest from the sampled households, which induces measurement error in the neighborhood-level covariate since not all households are sampled. Other times, neighborhood-level variables are not observed directly, and only a noisy proxy is available. In both cases, the observed variables may contain measurement error. Measurement error is known to attenuate the coefficient of the mismeasured variable, but it can also affect other coefficients in the model, and ignoring measurement error can lead to misleading inference. We propose a Bayesian hierarchical model that integrates an explicit model for the measurement error process along with a model for the outcome of interest for both sampling-induced measurement error and classical measurement error. Advances in Bayesian computation, specifically the development of the Stan probabilistic programming language, make the implementation of such models easy and straightforward.

The fabrication of Bit Patterned Media has become highly developed, with samples fabricated of over 1.5 Tb/in2. However, writing BPM presents significant challenges and for a system to be developed studies must be made into writing. This work has investigated a number of effects on the writing of Bit Pattterned Media (BPM). Magnetostatic interactions between islands have been used to investigate the effect of patterns of magnetisation on the write-window of a BPM system. A method of acquiring a distribution of patterns was determined and used to vary the probability of a target island switching. This showed that magnetostatic interactions between islands could be modelled as a variation in the anisotropy field. The relationship between island parameter distributions, the write-window and error rates was also explored. The effect of non-Gaussian distributions on the error in a BPM system was studied. It was concluded that tails of island parameter distributions have a significant effect on errors occurring in the write process of a BPM system. Therefore an accurate distribution of island parameters must be known and the necessary accuracy of such a distribution was established. Furthermore a model of BPM writing where the shape of the head field is approximated from the value at the maximum head field gradient will not account for switching in the tail of a real head field. This led onto a study of the ideal write point in BPM. In conventional recording theory the medium is designed to switch when the applied head field is at the position of its maximum gradient, which produces sharp transitions between magnetisation regions. A natural assumption in BPM is that the system could be optimised by setting the island switching field in a similar manner. This strategy of optimisation was investigated to see what gives the minimum error, or maximum write-window. It was concluded that optimisation could not be solely based on the maximum head field gradient, furthermore assuming the shape of the head field from this point will not produce an accurate estimation of the error in a BPM system.