Learning, inference, and prediction in the presence of missing data are pervasive problems in machine learning and statistical data analysis. This thesis focuses on the problems of collaborative prediction with non-random missing data and classification with missing features. We begin by presenting and elaborating on the theory of missing data due to Little and Rubin. We place a particular emphasis on the missing at random assumption in the multivariate setting with arbitrary patterns of missing data. We derive inference and prediction methods in the presence of random missing data for a variety of probabilistic models including finite mixture models, Dirichlet process mixture models, and factor analysis. Based on this foundation, we develop several novel models and inference procedures for both the collaborative prediction problem and the problem of classification with missing features. We develop models and methods for collaborative prediction with non-random missing data by combining standard models for complete data with models of the missing data process. Using a novel recommender system data set and experimental protocol, we show that each proposed method achieves a substantial increase in rating prediction performance compared to models that assume missing ratings are missing at random. We describe several strategies for classification with missing features including the use of generative classifiers, and the combination of standard discriminative classifiers with single imputation, multiple imputation, classification in subspaces, and an approach based on modifying the classifier input representation to include response indicators. Results on real and synthetic data sets show that in some cases performance gains over baseline methods can be achieved by methods that do not learn a detailed model of the feature space.

Šiame darbe išnagrinėjome kelis praleistų reikšmių įrašymo metodus, kuriuos taikėme išvykstamojo turizmo statistinio tyrimo 2.6. klausimo pirmiems dviem punktams: paslaugų paketo ir transporto išlaidoms. Įrašymo metodų efektyvumo analizę atlikome su pilnais duomenimis, juose fiktyviai padarydamos praleistas reikšmes ir į jas įrašydamos reikšmes keliais praleistų reikšmių įrašymo metodais. Tuomet turėdamos tikras ir įrašytas reikšmes galėjome palyginti parametrų įverčius. Kadangi praleistos reikšmės gali atsirasti atsitiktinai ir neatsitiktinai, todėl mes praleistų reikšmių įrašymo metodus taikėme trims atvejams: kai praleistos reikšmės atsiranda atsitiktinai, kai praleistos reikšmės atsiranda tada, kai neatsako respondentai turėję didžiausias ar mažiausias išlaidas kelionėje. Praleistų reikšmių įrašymui taikėme skirstiniu pagrįstą, vidurkio, atsitiktinio pakartojimo, santykiu pagrįstą ir daugiareikšmio įrašymo metodus, nesudarydamos įrašymo klasių ir sudarydamos įrašymo klases. Taigi, siūlome tokį pat praleistų reikšmių įrašymo metodų efektyvumo tyrimą atlikti ir likusiems 2.6. klausimo punktams, nusistatyti tinkamiausią įrašymo metodą ir tada jį taikyti jau tikroms praleistoms reikšmėms įrašyti. Be to, reikėtų atsižvelgti ir į dėl įrašymo atsirandančios dispersijos įvertinį, nes jos indėlis į bendrą dispersijos įvertinį yra nemažas. Atlikus praleistų reikšmių įrašymą, bus galima taikyti kompiuterinius įverčių skaičiavimo metodus ir nebus prarasta kita informacija, kurią... [toliau žr. visą tekstą] / In this work, we examined some missing data imputation methods in the survey on outbound tourism for the package tour and transport expenses. We performed an analysis of the efficiency of missing data imputation methods using full data sets with fictitious missing data applying various missing data imputation methods to fill in the missing data. Thus, we had real values and imputed values and could compare the estimated parameters. The missing data can appear randomly and non-randomly, so we applied missing data imputation methods in three cases: when missing data appear randomly and when missing data appear in case of non-response of respondents who had the highest or the lowest travel expenses. We applied distribution, average, random, ratio and multiple imputation methods for missing data imputation without using imputation classes and using imputation classes. We propose to perform the same efficiency survey of missing data imputation methods for the remaining items of expenses in the outbound tourism questionnaire in order to find out a convenient missing data imputation method and apply it for the real missing data (the current analysis was performed applying fictitious missing data). After the missing data imputation, we can apply the procedures of parameter estimation and we will not lose other information as it would be the case with the elimination of questionnaires having missing data.

Šiame darbe išnagrinėjome kelis praleistų reikšmių įrašymo metodus, kuriuos taikėme išvykstamojo turizmo statistinio tyrimo 2.6. klausimo pirmiems dviem punktams: paslaugų paketo ir transporto išlaidoms. Įrašymo metodų efektyvumo analizę atlikome su pilnais duomenimis, juose fiktyviai padarydamos praleistas reikšmes ir į jas įrašydamos reikšmes keliais praleistų reikšmių įrašymo metodais. Tuomet turėdamos tikras ir įrašytas reikšmes galėjome palyginti parametrų įverčius. Kadangi praleistos reikšmės gali atsirasti atsitiktinai ir neatsitiktinai, todėl mes praleistų reikšmių įrašymo metodus taikėme trims atvejams: kai praleistos reikšmės atsiranda atsitiktinai, kai praleistos reikšmės atsiranda tada, kai neatsako respondentai turėję didžiausias ar mažiausias išlaidas kelionėje. Praleistų reikšmių įrašymui taikėme skirstiniu pagrįstą, vidurkio, atsitiktinio pakartojimo, santykiu pagrįstą ir daugiareikšmio įrašymo metodus, nesudarydamos įrašymo klasių ir sudarydamos įrašymo klases. Taigi, siūlome tokį pat praleistų reikšmių įrašymo metodų efektyvumo tyrimą atlikti ir likusiems 2.6. klausimo punktams, nusistatyti tinkamiausią įrašymo metodą ir tada jį taikyti jau tikroms praleistoms reikšmėms įrašyti. Be to, reikėtų atsižvelgti ir į dėl įrašymo atsirandančios dispersijos įvertinį, nes jos indėlis į bendrą dispersijos įvertinį yra nemažas. Atlikus praleistų reikšmių įrašymą, bus galima taikyti kompiuterinius įverčių skaičiavimo metodus ir nebus prarasta kita informacija, kurią... [toliau žr. visą tekstą] / In this work, we examined some missing data imputation methods in the survey on outbound tourism for the package tour and transport expenses. We performed an analysis of the efficiency of missing data imputation methods using full data sets with fictitious missing data applying various missing data imputation methods to fill in the missing data. Thus, we had real values and imputed values and could compare the estimated parameters. The missing data can appear randomly and non-randomly, so we applied missing data imputation methods in three cases: when missing data appear randomly and when missing data appear in case of non-response of respondents who had the highest or the lowest travel expenses. We applied distribution, average, random, ratio and multiple imputation methods for missing data imputation without using imputation classes and using imputation classes. We propose to perform the same efficiency survey of missing data imputation methods for the remaining items of expenses in the outbound tourism questionnaire in order to find out a convenient missing data imputation method and apply it for the real missing data (the current analysis was performed applying fictitious missing data). After the missing data imputation, we can apply the procedures of parameter estimation and we will not lose other information as it would be the case with the elimination of questionnaires having missing data.

Association rules are a useful concept in data mining with the goal of summa- rizing the strong patterns that exist in data. We have identified several issues in mining association rules and addressed them in three main areas. The first area we explore is standardized interestingness measures. Different interestingness measures exist on different ranges, and interpreting them can be subtly problematic. We standardize several interestingness measures and show how these are useful to consider in association rule mining in three examples. A second area we address is incomplete transactions. By applying statistical methods in new ways to association rules, we provide a more comprehensive means of analyzing incomplete transactions. We also describe how to find families of distributions for interestingness measure values when transactions are incomplete. Finally, we address the common result of mining: a plethora of association rules. Unlike methods which attempt to reduce the number of resulting rules, we harness this large quantity to find a higher-level set of patterns. / NSERC Discovery Grant and OMRI Early Researcher Award

No description available.

A search for diphoton events with large missing transverse energy is conducted using 3.1 pb^{-1} of integrated luminosity of proton-proton collisions at center of mass energy \sqrt{s}=7 TeV. The data were collected with the ATLAS detector at the CERN Large Hadron Collider during the period from March 30, 2010 until August 30, 2010. No excess of such events is observed above the Standard Model background prediction. This result is interpreted in the context of a gravity mediated One Universal Extra Dimension model with \Lambda R=20, N=6 and M_{D}=5 TeV, where \Lambda is the cutoff scale, N is the number of large extra dimensions and M_{D} is the Planck scale in the higher dimensional theory. The compactification radius of the Universal Extra Dimension, R, is excluded for values of 1/R < 728 GeV at 95\% CL, providing the most stringent limit on this model at the time of publication.

A search for diphoton events with large missing transverse energy is conducted using 3.1 pb^{-1} of integrated luminosity of proton-proton collisions at center of mass energy \sqrt{s}=7 TeV. The data were collected with the ATLAS detector at the CERN Large Hadron Collider during the period from March 30, 2010 until August 30, 2010. No excess of such events is observed above the Standard Model background prediction. This result is interpreted in the context of a gravity mediated One Universal Extra Dimension model with \Lambda R=20, N=6 and M_{D}=5 TeV, where \Lambda is the cutoff scale, N is the number of large extra dimensions and M_{D} is the Planck scale in the higher dimensional theory. The compactification radius of the Universal Extra Dimension, R, is excluded for values of 1/R < 728 GeV at 95\% CL, providing the most stringent limit on this model at the time of publication.

In this dissertation I examine representations of the events surrounding the disappearance and murder of women from Vancouver’s Downtown Eastside, in the interests of animating a sense of implication in these events among a wider public. To do so, I build on theoretical concepts developed in the work of Avery Gordon, Judith Butler, and Wendy Brown, namely the notions of hauntings, grievability, and inheritance. My approach to knowledge production builds upon Avery Gordon’s theorizing about the significance of hauntings in particular. Following Gordon, I argue that while the women disappeared from Vancouver are no longer physically “there” in the Downtown Eastside, they do indeed maintain what Gordon describes as a “seething presence” in Vancouver (and beyond), one that suggests matters of some urgency for contemporary social and political life, and so my research traces those presences as they have arisen through my engagement with a variety of cultural productions (including documentary film, photography, journalism, art, and poetry). Building on insights from each of the three theorists listed above, I argue that ethical encounters with the ghosts of the women who have been disappeared require rethinking conventional ways of understanding the relationships between self/other and past/present/future. Because the women disappeared from the Downtown Eastside are disproportionately Indigenous, I begin by investigating how histories of colonization, and in particular the frontier mythology so commonplace in western Canada, are implicated in these contemporary acts of violence. I argue that conventional understandings of space, temporality, and history are inadequate for understanding these events in all of their complexity. From there, I investigate how and why the women were initially cast, in a variety of representations, as living lives that many assumed could not be widely recognized through the framework of what Judith Butler has coined a “grievable life.” And finally, I ask after what kind of memorial practices might be most capable of hailing an “us” into relations of inheritance with the women who have been disappeared - such relations, I argue, are a necessary part of reckoning with our individual and collective implication in the disappearances of women from the Downtown Eastside. / English

Thesis (Ph.D.) - Carleton University, 2005. / Includes bibliographical references (p. 252-258). Also available in electronic format on the Internet.

Univ., Diss.--München, 2003. / Zsfassung in engl. Sprache.