Despite considerable advances in missing data imputation techniques over the last three decades, the problem of missing data remains largely unsolved. Many techniques have emerged in the literature as candidate solutions, including the Expectation Maximisation (EM), and the combination of autoassociative neural networks and genetic algorithms (NN-GA). The merits of both these techniques have been discussed at length in the literature, but have never been compared to each other. This thesis contributes to knowledge by firstly, conducting a comparative study of these two techniques.. The significance of the difference in performance of the methods is presented. Secondly, predictive analysis methods suitable for the missing data problem are presented. The predictive analysis in this problem is aimed at determining if data in question are predictable and hence, to help in choosing the estimation techniques accordingly. Thirdly, a novel treatment of missing data for online condition monitoring problems is presented. An ensemble of three autoencoders together with hybrid Genetic Algorithms (GA) and fast simulated annealing was used to approximate missing data. Several significant insights were deduced from the simulation results. It was deduced that for the problem of missing data using computational intelligence approaches, the choice of optimisation methods plays a significant role in prediction. Although, it was observed that hybrid GA and Fast Simulated Annealing (FSA) can converge to the same search space and to almost the same values they differ significantly in duration. This unique contribution has demonstrated that a particular interest has to be paid to the choice of optimisation techniques and their decision boundaries. iii Another unique contribution of this work was not only to demonstrate that a dynamic programming is applicable in the problem of missing data, but to also show that it is efficient in addressing the problem of missing data. An NN-GA model was built to impute missing data, using the principle of dynamic programing. This approach makes it possible to modularise the problem of missing data, for maximum efficiency. With the advancements in parallel computing, various modules of the problem could be solved by different processors, working together in parallel. Furthermore, a method for imputing missing data in non-stationary time series data that learns incrementally even when there is a concept drift is proposed. This method works by measuring the heteroskedasticity to detect concept drift and explores an online learning technique. New direction for research, where missing data can be estimated for nonstationary applications are opened by the introduction of this novel method. Thus, this thesis has uniquely opened the doors of research to this area. Many other methods need to be developed so that they can be compared to the unique existing approach proposed in this thesis. Another novel technique for dealing with missing data for on-line condition monitoring problem was also presented and studied. The problem of classifying in the presence of missing data was addressed, where no attempts are made to recover the missing values. The problem domain was then extended to regression. The proposed technique performs better than the NN-GA approach, both in accuracy and time efficiency during testing. The advantage of the proposed technique is that it eliminates the need for finding the best estimate of the data, and hence, saves time. Lastly, instead of using complicated techniques to estimate missing values, an imputation approach based on rough sets is explored. Empirical results obtained using both real and synthetic data are given and they provide a valuable and promising insight to the problem of missing data. The work, has significantly confirmed that rough sets can be reliable for missing data estimation in larger and real databases.

No description available.

Who lies in negotiations—and when and why? While research has considered many factors, an important and understudied determinant is people’s expectancies about others. I argue that negotiators’ expectations about other people can help predict their own deceptive behavior. Chapter I explores how projection and pessimism shape deceptive behavior. Studies 1a-1d investigated negotiators’ expectancies and found evidence of projection and of rampant pessimism; negotiators consistently overestimated the percentage of other people who shared their own beliefs and the percentage of people who thought deception was appropriate in negotiations. Study 2 found that expectancies about others’ ethical standards predicted the degree to which negotiators were misleading or dishonest in negotiations. Study 3 manipulated expectancies and found that a higher perceived prevalence of gamers led to more misleading or dishonest behavior. Negotiators’ decisions to engage in deception were heavily influenced by an exaggerated pessimism about others’ ethical standards. In supplementary analyses, Chapter I also briefly addresses how expectancies about a specific counterpart’s level of deception shape deceptive behavior. Finally, Chapter II investigates how stereotypes shape deceptive behavior in negotiations, using the stereotype content model, which suggests that social groups are judged on two primary dimensions of warmth and competence. Study 1 provided evidence that deceptive negotiators are perceived to possess less warmth and greater competence than truthful negotiators. Study 2 showed that people from cold competent groups are perceived as more deceptive than people from warm incompetent groups. Study 3 tested actual behavior and demonstrated that manipulating the social category membership of a counterpart affected deception in a negotiation situation. Expectancies play a critical and understudied role in influencing a negotiator’s decision to be deceptive.

The Bernoulli distribution is a basic, well-studied distribution in probability. In this thesis, we will consider repeated Bernoulli trials in order to study runs of identical outcomes. More formally, for t ∈ N, we let Xt ∼ Bernoulli(p), where p is the probability of success, q = 1 − p is the probability of failure, and all Xt are independent. Then Xt gives the outcome of the tth trial, which is 1 for success or 0 for failure. For n, m ∈ N, we define Tn to be the number of trials needed to first observe n consecutive successes (where the nth success occurs on trial XTn ). Likewise, we define Tn,m to be the number of trials needed to first observe either n consecutive successes or m consecutive failures. We shall primarily focus our attention on calculating E[Tn] and E[Tn,m]. Starting with the simple cases of E[T2] and E[T2,2], we will use a variety of techniques, such as counting arguments and Markov chains, in order to derive the expectations. When possible, we shall also provide closed-form expressions for the probability mass function, cumulative distribution function, variance, and other values of interest. Eventually we will work our way to general formulas for E[Tn] and E[Tn,m]. We will also derive formulas for conditional averages, and discuss how famous results from probability such as Wald’s Identity apply to our problem. Numerical examples will also be given in order to supplement the discussion and clarify the results.

The purpose of this study was to examine the relationships of communication variables and parent marital variables with the fulfillment of marital expectations among newlyweds. Little research has been done on newlywed expectations and communication. This is an exploratory study conducted to determine how newlyweds' exposure to parents' marital interactions and communication styles correlated with newlyweds' fulfillment of marital expectations. Fifty newlywed couples (married 3-6 months) filled out the Marital Comparison Level Index (MCLI) questionnaire about their level of fulfillment of expectations. Couples were then videotaped talking to one another about the strengths of their marriage followed by a discussion of the potential weaknesses of their relationship. Those videotapes were then coded using the Marital Interaction Coding System--Global. The results indicate that parental marital variables had no significant association with newlywed children's level of fulfillment of expectations. The that was correlated with fulfillment of expectations was the wife's "withdrawal" behavior during the conversation about dissimilarities and weaknesses. The lack of relation with the other variables may have been masked by high levels of satisfaction in the first year of marriage and the homogeneous sample (age and religion).

在本文中使用七種不同的抽樣方法估計對稱分配的位置參數，目的是為了縮減估計值的變異數。我們考慮的方法是四種逐次估計量、Trimmed Mean、修正隨機估計量和加權隨機估計量。本文利用電腦模擬的方式，比較在觀察值為標準常態分配之下這幾種估計量與簡單隨機抽樣的樣本平均數估計值的變異數大小。 / In this paper seven sampling methods are used to estimate the mean of symmetric distributions. Our goal is reduce the variance of the estimate. The methods we consider include four sequential estimators, trimmed mean, adjusted random estimator, and weighted random estimator. This paper uses the method of computer simulation to compare variance of these estimators with sample mean using simple random sampling method under standard normal distribution.

本文主要是探討在股票單日漲跌幅限制下市場非恆久性失衡體系的一些經 濟現象，以及管制是否真正具有穩定價格之功能，將以實證之方式佐以稍 簡化之理論模型來驗證所要探討的命題。由於以往之研究有 (1) 以真實 資料而未以模型預測； 或 (2) 以模型預測而以電腦模擬資料。 所以本 文將以真實資料佐以理論與實證模型預測未限制下之股價分析比較， 希 望能提供一些較新的訊息，或給未來後續研究此命題的學者一些參考。另 外將與鄧鍇 ( 民國八十年 ) 之以電腦亂數模擬之研究結果比較，分析 單日漲跌幅度限制究竟有無短期穩定股價之功能。本文共分五章， 分別 為緒論、文獻回顧、理性預期基礎下之價格管制理論模型、理性預期基礎 下之價格管制模型之實證分析、結論。 第一章緒論中， 第一節研究背景 ，說明臺灣股票市場漲跌幅限制之由來，以及由此背景延伸出之研究動機 ， 第二節研究動機與目的，說明本研究與以往研究不同的部份，以及所 要驗證之主題。 第二章文獻回顧中，第一節國內相關文獻， 探討國內相 關文獻，依據文獻探討發展出本研究之命題，第二節國外相關文獻，敘述 本研究理論與實證模型之由來。 第三章理性預期基礎下之價格管制模型 中， 第一節理論模型架構，為理論模型之推導，說明漲跌幅限制幅度大 小對預期價格之影響， 第二節比較靜態分析，以經濟理論分析漲跌幅限 制與平均工資、 汽油價格、利率、貨幣供給對股票價格之影響，第三節 實證模型與估計方法，說明實證模型之架構與估計之步驟。 第四章理性 預期基礎下之價格管制模型之實證分析中， 第一節資料來源與限制， 說 明本研究資料來源，以及研究之時間區間，第二節估計參數分析，說明各 參數估計之結果， 並分析其與現實狀況之關係，第三節估計值變動差分 析，分析漲跌幅限制有無短期穩定股價之功能。 第五章結論中，第一節 經濟涵義及政策性建議， 將所得之結果歸納並做政策性建議，第二節本 文之限制、缺失及未來研究方向， 敘述本文因人力、時間之不足所遭遇 到之限制，產生之缺失，以及未來所要努力之方向。

Residual maximum likelihood (REML) estimation is a popular method of estimation for variance parameters in linear mixed models, which typically requires an iterative scheme. The aim of this thesis is to review several popular iterative schemes and to develop an improved iterative strategy that will work for a wide class of models. The average information (AI) algorithm is a computationally convenient and efficient algorithm to use when starting values are in the neighbourhood of the REML solution. However when reasonable starting values are not available, the algorithm can fail to converge. The expectation-maximisation (EM) algorithm and the parameter expanded EM (PXEM) algorithm are good alternatives in these situations but they can be very slow to converge. The formulation of these algorithms for a general linear mixed model is presented, along with their convergence properties. A series of hybrid algorithms are presented. EM or PXEM iterations are used initially to obtain variance parameter estimates that are in the neighbourhood of the REML solution, and then AI iterations are used to ensure rapid convergence. Composite local EM/AI and local PXEM/AI schemes are also developed; the local EM and local PXEM algorithms update only the random effect variance parameters, with the estimates of the residual error variance parameters held fixed. Techniques for determining when to use EM-type iterations and when to switch to AI iterations are investigated. Methods for obtaining starting values for the iterative schemes are also presented. The performance of these various schemes is investigated for several different linear mixed models. A number of data sets are used, including published data sets and simulated data. The performance of the basic algorithms is compared to that of the various hybrid algorithms, using both uninformed and informed starting values. The theoretical and empirical convergence rates are calculated and compared for the basic algorithms. The direct comparison of the AI and PXEM algorithms shows that the PXEM algorithm, although an improvement over the EM algorithm, still falls well short of the AI algorithm in terms of speed of convergence. However, when the starting values are too far from the REML solution, the AI algorithm can be unstable. Instability is most likely to arise in models with a more complex variance structure. The hybrid schemes use EM-type iterations to move close enough to the REML solution to enable the AI algorithm to successfully converge. They are shown to be robust to choice of starting values like the EM and PXEM algorithms, while demonstrating fast convergence like the AI algorithm. / Thesis (Ph.D.) - University of Adelaide, School of Agriculture, Food and Wine, 2008

<p>Bakgrund</p><p>Förväntningsgap inom revision har använts som begrepp inom företagsekonomin sedan början av 1970-talet. Den första definitionen av begreppet var gapet som uppstår mellan förväntningarna som användarna av finansiella rapporter har på revisorn och vad denne de facto gör. Under senare år har revisorns roll hamnat i rampljuset, detta främst på grund av ett antal spektakulära företagskollapser såsom Enron och WorldCom. I dessa skandaler riktades mångas blickar mot revisorerna i jakten på en syndabock. Anledningen till det är troligtvis att många har en felaktig bild om vad en revisors arbetsuppgifter egentligen är. De teorier som finns angående förväntningsgapet inom revision utgår alla från allmänhetens förväntningar på revisorn. I denna uppsats undersöks om det föreligger samma förväntningsgap mellan företag och revisorn.</p><p>Syfte</p><p>Syftet med denna uppsats är att genom intervjuer med företag och revisorer undersöka om det finns ett förväntningsgap mellan företags förväntningar på revisorn och vad revisorn de facto gör, och i så fall beskriva hur det gapet ser ut, och vad det beror på.</p><p>Avgränsningar</p><p>Uppsatsen är avgränsad till att endast undersöka det förväntningsgap som finns mellan små och medelstora ägarledda företag och revisorn. Det medför att uppsatsen inte undersöker och tar ställning till det eventuella förväntningsgap som finns mellan revisorn och andra intressenter i samhället. Vidare har undersökningen avgränsats till att endast undersöka förhållanden mellan utvalda företag och revisorer i Linköpings Kommun.</p><p>Genomförandet</p><p>För att undersöka om det finns ett förväntningsgap mellan företag och revisorer har vi genomfört fem stycken kvalitativa intervjuer. Tre intervjuer med revisorer och två intervjuer med företagare har genomförts. Dessa intervjuer utgör uppsatsens empiri. Empirin behandlas vidare i uppsatsens analys, först ställs de svar vi fått från revisorsrespondenterna mot den teori beträffande revisorns regelverks som tas upp i uppsats teoriavsnitt. Vidare ställs företagsrespondenternas svar mot revisorsrespondenternas dito, men även mot teorierna om revisorns regler och de teorier om förväntningsgap som återfinns i teoriavsnittet.</p><p>Resultat</p><p>Resultatet i denna uppsats kan inte ses som generaliserbart då underlaget för studien inte varit av den omfattning som skulle krävas för att dra sådana slutsatser. Uppsatsen påvisar dock att det finns ett förväntningsgap mellan företag och revisorn i de fall som vi har undersökt. Förväntningsgapet beror till största delen på en kunskapsbrist från företagens sida beträffande revisorernas ansvars- och uppgiftsområde. Den största identifierade kunskapsbristen är att företagen inte förstår gränsdragningen mellan revision och revisionsnära rådgivning. Detta förväntningsgap kan enligt denna uppsats överbyggas med kunskap hos revisorns klienter. Denna kunskap skulle enklast kunna förmedlas genom en klar definition av revisorns roll innan revisionsuppdraget påbörjas och genom specificerade fakturor från revisorerna.</p> / <p>Background</p><p>The auditing expectation gap has been used as a concept in business administration since the early 1970’s. The first definition of the notion was the gap that occur between the financial report users expectations on the auditor, and what the auditor actually is doing. In recent years the role of the auditor has been in the spotlight because of the big corporate scandals and colapses such as the Enron and the Wolrdcom. A lot of people has focused on the auditors role, when they wanted a scapegoat in the scandals. The publics lack of knowledge about the auditors task is said to be the reason for that phenomena. The theories about the gap within the auditing bransch, is most often based on the publics expectations, while this paper is focused on the gap between the auditor and their clients.</p><p>The purpose of this paper</p><p>The purpose of this paper is to explore whether a gap exists between the companies expectations and what the auditor actually do by interviews with auditors and companies. We hope to describe the gap, and find out why it exists.</p><p>Delimitation</p><p>This paper is limited to explore the gap between small and medium sized companies and the auditors. The purpose is not to investigate the gap between the public interest and the auditors. Further this paper is limited to reasearch the conditions within the municipal of Linköping.</p><p>Method</p><p>To explore the gap between companies and auditors we have carried out five qualitative interviews. Three with auditors, and two with companies. These interviews are forming the papers empirical part. A part which will later on be analyzed in different ways. First, the auditor interviews will be compared with the acts and standards regulating the auditors work. Then the companies answers will be compared with the auditors dito, and also against the standards and acts mentioned earlier.</p><p>Result</p><p>The conclusions in this report can not be generalized because of the brief extent of the study. Although this paper proves that there is an expectation gap between the auditors and companies examined in this study. The underlaying reason for the gap is the companies lack of knowledge regarding the auditors assigment. The main identified lack of knowledge is that the companies don not know where the line between statutory audit and advisory is. To be able to narrow the gap information is necessary. The companies needs information about the extend of the auditors assigment. That could be done by carefully explaining the assigment for the comapines before the assignment starts and specefied invoices from the auditors.</p>

Semiparametric maximum likelihood analysis allows inference in errors-invariables models with small loss of efficiency relative to full likelihood analysis but with significantly weakened assumptions. In addition, since no distributional assumptions are made for the nuisance parameters, the analysis more nearly parallels that for usual regression. These highly desirable features and the high degree of modelling flexibility permitted warrant the development of the approach for routine use. This thesis does so for the special cases of linear and nonlinear regression with measurement errors in one explanatory variable. A transparent and flexible computational approach is developed, the analysis is exhibited on some examples, and finite sample properties of estimates, approximate standard errors, and likelihood ratio inference are clarified with simulation. / Graduation date: 2001