Thomas Kneib

Statistical Modelling and Regression Structures: Festschrift in Honour of Ludwig Fahrmeir Thomas Kneib 2010 edition

Marc Notes: Title from content provider.; Access is restricted to subscribing institutions. Table of Contents: The Smooth Complex Logarithm and Quasi-Periodic Models.- P-spline Varying Coefficient Models for Complex Data.- Penalized Splines, Mixed Models and Bayesian Ideas.- Bayesian Linear Regression Different Conjugate Models and Their (In) Sensitivity to Prior-Data Conflict.- An Efficient Model Averaging Procedure for Logistic Regression Models Using a Bayesian Estimator with Laplace Prior.- Posterior and Cross-validatory Predictive Checks: A Comparison of MCMC and INLA.- Data Augmentation and MCMC for Binary and Multinomial Logit Models.- Generalized Semiparametric Regression with Covariates Measured with Error.- Determinants of the Socioeconomic and Spatial Pattern of Undernutrition by Sex in India: A Geoadditive Semi-parametric Regression Approach.- Boosting for Estimating Spatially Structured Additive Models.- Generalized Linear Mixed Models Based on Boosting.- Measurement and Predictors of a Negative Attitude towards Statistics among LMU Students.- Graphical Chain Models and their Application.- Indirect Comparison of Interaction Graphs.- Modelling, Estimation and Visualization of Multivariate Dependence for High-frequency Data.- Ordinal- and Continuous-Response Stochastic Volatility Models for Price Changes: An Empirical Comparison.- Copula Choice with Factor Credit Portfolio Models.- Penalized Estimation for Integer Autoregressive Models.- Bayesian Inference for a Periodic Stochastic Volatility Model of Intraday Electricity Prices.- Online Change-Point Detection in Categorical Time Series.- Multiple Linear Panel Regression with Multiplicative Random Noise.- A Note on Using Multiple Singular Value Decompositions to Cluster Complex Intracellular Calcium Ion Signals.- On the self-regularization property of the EM algorithm for Poisson inverse problems.- Sequential Design of Computer Experiments for Constrained Optimization."Review Quotes: From the reviews: The festschrift is a collection of 24 contributions stemming from a wide area of statistical models ranging from semiparametric and geoadditive regression to Bayesian inference, time series modeling, statistical regularization, and others. The topics are of current interest. The format of the volume is uniform and nicely presented . will be a useful resource for graduate students, researchers, and practitioners with an interest in these topics. I think the festschrift deserves a broad readership. (Technometrics, Vol. 52 (3), August, 2010)"Publisher Marketing: Thecollectedcontributionscontainedwithinthisbookhavebeenwrittenbyfriends andcolleaguestoacknowledgeLudwigFahrmeir swidespreadandimportantimpact onStatisticsasascience, whilecelebratinghis65thBirthday. Asayoungstudent, LudwigstartedhiscareerasaMathematician, buthequickly turnedintoarisingandshiningstarwithintheGermanandinternationalStatistics community. HesoonobtainedbothhisPhDandhisHabilitationattheTechnical UniversityofMunich. AfterashortperiodasavisitingprofessorattheUniversity ofDortmund, hereturnedtohishomelandBavariaandwasappointedFullProfessor ofStatisticsattheUniversityofRegensburg, attheageof32. Someyearslater, hemovedtothecapitalofBavariaandbecameProfessoratthe DepartmentofStatisticsattheUniversityofMunich. Hisappointmenthadsigni?cant impactontheDepartmentsince, soonafterhisarrival, Ludwigstartedaninitiative toestablishacollaborativeresearchcenteronthe StatisticalAnalysisofDiscrete Structures. Afterasuccessfulapplicationforinitialfunding, furtherfundingwas extendedseveraltimes, untiltheresearchcenterreachedthemaximumperiodfor fundingin2006. Duringthecompleteduration, Ludwigservedasaspeakerofthe researchcenterand tociteoneofthe?nalreferees manageditinaneasyand ef?cientwayandcontributedseveralimportantresults. Duringthelastfortyyears, Ludwig sworkhashadtremendousimpactontheS- tisticscommunity. Hewasamongthe?rstresearcherstorecognizetheimportance ofgeneralizedlinearmodelsandcontributedinaseriesofpaperstothetheoretical backgroundofthatmodelclass. Hisinterestinstatisticalmodellingledtothe- ganizationofaworkshopon StatisticalModellingandGeneralizedLinearModels (GLIM) inMunichin1992andculminatedinthehighlycitedmonographon M- tivariateStatisticalModellingBasedonGeneralizedLinearModels thatsawtwo printingsandremainstobeakeyreferenceonappliedstatisticalmodellingutilizing generalizedlinearmodels. Ludwigalsohadgreatin?uenceonthecreationofthe StatisticalModellingSociety, andiscurrentlyontheadvisoryboardofthecor- spondingjournalon StatisticalModelling. Boththesocietyandjournalemerged outoftheearlyGLIMworkshopsandproceedings. v vi Foreword Ofcourse, Ludwig sworkisde?nitelynotrestrictedtogeneralizedlinearmodels but onthecontrary spansawiderangeofmodernStatistics. Heco-authoredor co-editedseveralmonographs, e. g. onMultivariateStatistics, StochasticProcesses, MeasurementofCreditRisks, aswellaspopulartextbooksonRegressionandan IntroductiontoStatistics. Hisrecentresearchcontributionsaremostlyconcentrated insemiparametricregressionandspatialstatisticswithinaBayesianframework. When?rstcirculatingtheideaofaFestschriftforthecelebrationofLudwig s 65thbirthday, allpotentialcontributorswereextremelypositive, manyimmediately agreeingtocontribute. ThesereactionsatesttoLudwig shighpersonalandp- fessionalappreciationinthestatisticalcommunity. Thefarreachingandvarietyof subjectscoveredwithinthesecontributionsalsorepresentsLudwig sbroadinterest andimpactinmanybranchesofmodernStatistics. BotheditorsofthisFestschriftwereluckyenoughtoworkwithLudwigatseveral occasionsandinparticularearlyintheircareersasPhDstudentsandPostDocs. His personalandprofessionalmentorshipandhisstrongcommitmentmadehimaperfect supervisorandhispatient, con?dentandencouragingworkingstylewillalwaysbe rememberedbyallofhisstudentsandcolleagues. Ludwigalwaysprovidedafriendly workingenvironmentthatmadeitapleasureandanhonortobeapartofhisworking group. WeareproudtobeabletosaythatLudwigismuchmorethanacolleague butturnedintoafriendforbothofus. OldenburgandMunich, January2010 ThomasKneib, GerhardTutz Acknowledgements Theeditorswouldliketoexpresstheirgratitudeto allauthorsofthisvolumefortheiragreementtocontributeandtheireasyco- erationatseveralstagesofputtingtogetherthe?nalversionoftheFestschrift. JohannaBrandt, JanGertheiss, AndreasGroll, FelixHeinzl, SebastianPetry, Jan UlbrichtandStephanieRubenbauerfortheirinvaluablecontributionsinproof- A readingandcorrectionofthepapers, aswellasinsolvingseveralLTX-related E problems. theSpringerVerlagforagreeingtopublishthisFestschriftandinparticularNils- PeterThomas, AliceBlanck and FrankHolzwarthfor the smooth collabo- tion in preparing th emanuscript. vii Contents ListofContributors. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xix TheSmoothComplexLogarithmandQuasi-PeriodicModels . . . . . . . . . . 1 PaulH. C. Eilers 1 Foreword. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 2 Introduction. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 3 DataandModels. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 3. 1 TheBasicModel. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 3. 2 SplinesandPenalties. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 3. 3 StartingValues. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 3. 4 SimpleTrendCorrectionandPriorTransformation. . . . . 8 3. 5 AComplexSignal. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3. 6 Non-normalDataandCascadedLinks. . . . . . . . . . . . . . . . 10 3. 7 AddingHarmonics. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 4 MoretoExplore. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 5 Discussion. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 References. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 P-splineVaryingCoef?cientModelsforComplexData. . . . . . . . . . . . . . . . 19 BrianD. Marx 1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 2 LargeScale VCM, withoutBack?tting. . . . . . . . . . . . . . . . . . . . . . 22 3 NotationandSnapshotofaSmoothingTool: B-splines. . . . . . . . . . 24 3. 1 GeneralKnotPlacement. . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 3. 2 SmoothingtheKTBData. . . . . . . . . . . . . . . . . . . . . . . . . . . 25 4 UsingB-splinesforVaryingCoef?cientModels. . . . . . . . . . . . . . . . 26 5 P-splineSnapshot: Equally-SpacedKnots&Penalization. . . . . . . . 28 5. 1 P-splinesforAdditiveVCMs. . . . . . . . . . . . . . . . . . . . . . . . 30 5. 2 StandardErrorBands. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 6 OptimallyTuningP-splines . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 7 MoreKTBResults. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 8 ExtendingP-VCMintotheGeneralizedLinearModel. . . . . . . . . . 33 9 Two-dimensionalVaryingCoef?cientModels. . . . . . . . . . . . . . . . . 36 ix x Contents 9. 1 Mechanicsof2D-VCMthroughExample . . . . . . . . . . . . . 37 9. 2 VCMsandPenaltiesasArrays. . . . . . . . . . . . . . . . . . . . . . . 39 9. 3 Ef?cientComputationUsingArrayRegression. . . . . . . . . 40 10 DiscussionTowardMoreComplexVCMs. . . . . . . . . . . . . . . . . . . . . 41 References. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 PenalizedSplines, MixedModelsandBayesianIdeas. . . . . . . . . . . . . . . . . . 45 ] GoranKauermann 1 Introduction. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45 2 NotationandPenalizedSplinesasLinearMixedModels. . . . . . . . 46 3 Classi?cationwithMixedModels. . . . . . . . . . . . . . . . . . . . . . . . . . . 48 4 VariableSelectionwithSimplePriors. . . . . . . . . . . . . . . . . . . . . . . . 50 4. 1 MarginalAkaikeInformationCriterion. . . . . . . . . . . . . . . 50 4. 2 ComparisoninLinearModels. . . . . . . . . . . . . . . . . . . . . . ." Contributor Bio:  Tutz, Gerhard Dr Gerhard Tutz is a Professor of Mathematics in the Department of Statistics at Ludwig-Maximilians University, Munich. He is formerly a Professor at the Technical University Berlin. He is the author or co-author of nine books and more than 100 papers.