Bergherr, Elisabeth

[["dc.bibliographiccitation.firstpage","317"],["dc.bibliographiccitation.issue","2"],["dc.bibliographiccitation.journal","The International Journal of Biostatistics"],["dc.bibliographiccitation.lastpage","329"],["dc.bibliographiccitation.volume","17"],["dc.contributor.author","Griesbach, Colin"],["dc.contributor.author","Säfken, Benjamin"],["dc.contributor.author","Waldmann, Elisabeth"],["dc.date.accessioned","2022-03-23T09:52:10Z"],["dc.date.available","2022-03-23T09:52:10Z"],["dc.date.issued","2021"],["dc.description.abstract","Gradient boosting from the field of statistical learning is widely known as a powerful framework for estimation and selection of predictor effects in various regression models by adapting concepts from classification theory. Current boosting approaches also offer methods accounting for random effects and thus enable prediction of mixed models for longitudinal and clustered data. However, these approaches include several flaws resulting in unbalanced effect selection with falsely induced shrinkage and a low convergence rate on the one hand and biased estimates of the random effects on the other hand. We therefore propose a new boosting algorithm which explicitly accounts for the random structure by excluding it from the selection procedure, properly correcting the random effects estimates and in addition providing likelihood-based estimation of the random effects variance structure. The new algorithm offers an organic and unbiased fitting approach, which is shown via simulations and data examples."],["dc.identifier.doi","10.1515/ijb-2020-0136"],["dc.identifier.pmid","34826371"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/105070"],["dc.language.iso","en"],["dc.relation.eissn","1557-4679"],["dc.relation.orgunit","Professur für Raumbezogene Datenanalyse und Statistische Lernverfahren"],["dc.title","Gradient boosting for linear mixed models"],["dc.type","journal_article"],["dc.type.internalPublication","no"],["dc.type.subtype","original_ja"],["dspace.entity.type","Publication"]]

[["dc.contributor.author","Griesbach, Colin"],["dc.contributor.author","Groll, Andreas"],["dc.contributor.author","Waldmann, Elisabeth"],["dc.date.accessioned","2022-04-20T14:13:29Z"],["dc.date.available","2022-04-20T14:13:29Z"],["dc.date.issued","2020-07"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/106586"],["dc.language.iso","en"],["dc.relation.conference","35th International Workshop on Statistical Modelling, IWSM2020"],["dc.relation.eventend","2020-07-24"],["dc.relation.eventlocation","Bilbao, Spain"],["dc.relation.eventstart","2020-07-20"],["dc.relation.ispartof","Proceedings of the 35th International Workshop on Statistical Modelling"],["dc.relation.orgunit","Professur für Raumbezogene Datenanalyse und Statistische Lernverfahren"],["dc.title","Addressing cluster-constant covariates in mixed effects models via likelihood-based boosting techniques"],["dc.type","conference_paper"],["dc.type.internalPublication","no"],["dspace.entity.type","Publication"]]

[["dc.bibliographiccitation.artnumber","e0254178"],["dc.bibliographiccitation.issue","7"],["dc.bibliographiccitation.journal","PLoS One"],["dc.bibliographiccitation.volume","16"],["dc.contributor.author","Griesbach, Colin"],["dc.contributor.author","Groll, Andreas"],["dc.contributor.author","Bergherr, Elisabeth"],["dc.date.accessioned","2022-03-23T09:51:58Z"],["dc.date.available","2022-03-23T09:51:58Z"],["dc.date.issued","2021"],["dc.description.abstract","Boosting techniques from the field of statistical learning have grown to be a popular tool for estimating and selecting predictor effects in various regression models and can roughly be separated in two general approaches, namely gradient boosting and likelihood-based boosting. An extensive framework has been proposed in order to fit generalized mixed models based on boosting, however for the case of cluster-constant covariates likelihood-based boosting approaches tend to mischoose variables in the selection step leading to wrong estimates. We propose an improved boosting algorithm for linear mixed models, where the random effects are properly weighted, disentangled from the fixed effects updating scheme and corrected for correlations with cluster-constant covariates in order to improve quality of estimates and in addition reduce the computational effort. The method outperforms current state-of-the-art approaches from boosting and maximum likelihood inference which is shown via simulations and various data examples."],["dc.identifier.doi","10.1371/journal.pone.0254178"],["dc.identifier.pmid","34242316"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/105069"],["dc.language.iso","en"],["dc.relation.eissn","1932-6203"],["dc.relation.orgunit","Professur für Raumbezogene Datenanalyse und Statistische Lernverfahren"],["dc.title","Addressing cluster-constant covariates in mixed effects models via likelihood-based boosting techniques"],["dc.type","journal_article"],["dc.type.internalPublication","no"],["dc.type.subtype","original_ja"],["dspace.entity.type","Publication"]]

[["dc.bibliographiccitation.journal","Computational and Mathematical Methods in Medicine"],["dc.bibliographiccitation.volume","2021"],["dc.contributor.author","Griesbach, Colin"],["dc.contributor.author","Groll, Andreas"],["dc.contributor.author","Bergherr, Elisabeth"],["dc.date.accessioned","2022-03-23T09:51:44Z"],["dc.date.available","2022-03-23T09:51:44Z"],["dc.date.issued","2021"],["dc.description.abstract","Joint models are a powerful class of statistical models which apply to any data where event times are recorded alongside a longitudinal outcome by connecting longitudinal and time-to-event data within a joint likelihood allowing for quantification of the association between the two outcomes without possible bias. In order to make joint models feasible for regularization and variable selection, a statistical boosting algorithm has been proposed, which fits joint models using component-wise gradient boosting techniques. However, these methods have well-known limitations, i.e., they provide no balanced updating procedure for random effects in longitudinal analysis and tend to return biased effect estimation for time-dependent covariates in survival analysis. In this manuscript, we adapt likelihood-based boosting techniques to the framework of joint models and propose a novel algorithm in order to improve inference where gradient boosting has said limitations. The algorithm represents a novel boosting approach allowing for time-dependent covariates in survival analysis and in addition offers variable selection for joint models, which is evaluated via simulations and real world application modelling CD4 cell counts of patients infected with human immunodeficiency virus (HIV). Overall, the method stands out with respect to variable selection properties and represents an accessible way to boosting for time-dependent covariates in survival analysis, which lays a foundation for all kinds of possible extensions."],["dc.identifier.doi","10.1155/2021/4384035"],["dc.identifier.pmid","34819988"],["dc.identifier.uri","https://resolver.sub.uni-goettingen.de/purl?gro-2/105068"],["dc.language.iso","en"],["dc.relation.eissn","1748-6718"],["dc.relation.issn","1748-670X"],["dc.relation.orgunit","Professur für Raumbezogene Datenanalyse und Statistische Lernverfahren"],["dc.title","Joint Modelling Approaches to Survival Analysis via Likelihood-Based Boosting Techniques"],["dc.type","journal_article"],["dc.type.internalPublication","yes"],["dc.type.subtype","original_ja"],["dspace.entity.type","Publication"]]