@article{Thaden2017General,
 abstract = {Modeling complex relationships and interactions between variables is an

ongoing statistical challenge. In particular, the joint modeling of multiple

response variables has recently gained interest among methodological and

applied researchers. In this article, we contribute to this development by

incorporating semiparametric predictors into recursive simultaneous equation

models. In particular, we extend the existing framework by imposing effect

priors that account for correlation of the effects across equations. This idea

can be seen as a generalization of multivariate conditional autoregressive

priors used for the analysis of multivariate spatial data.

We implement a Gibbs sampler for the estimation and evaluate the model in

an elaborate simulation study. Finally, we illustrate the applicability of our

approach with real data examples on malnutrition in Asia and Africa as well

as the analysis of plant and species richness with respect to environmental

diversity.},
 author = {Thaden, Hauke and Klein, Nadja and Kneib, Thomas},
 year = {2019},
 title = {Multivariate effect priors in bivariate semiparametric recursive Gaussian models},
 url = {https://www.uni-goettingen.de/de/13_Thaden_02_2017/558175.html},
 keywords = {econ;phd},
 pages = {51--66},
 volume = {137},
 issn = {01679473},
 journal = {Computational Statistics {\&} Data Analysis},
 doi = {10.1016/j.csda.2018.12.004},
 howpublished = {refereed}
}

{"_id":"wg5qjaNXbzZKjAc8q","bibbaseid":"thaden-klein-kneib-multivariateeffectpriorsinbivariatesemiparametricrecursivegaussianmodels-2019","authorIDs":[],"author_short":["Thaden, H.","Klein, N.","Kneib, T."],"bibdata":{"bibtype":"article","type":"article","abstract":"Modeling complex relationships and interactions between variables is an ongoing statistical challenge. In particular, the joint modeling of multiple response variables has recently gained interest among methodological and applied researchers. In this article, we contribute to this development by incorporating semiparametric predictors into recursive simultaneous equation models. In particular, we extend the existing framework by imposing effect priors that account for correlation of the effects across equations. This idea can be seen as a generalization of multivariate conditional autoregressive priors used for the analysis of multivariate spatial data. We implement a Gibbs sampler for the estimation and evaluate the model in an elaborate simulation study. Finally, we illustrate the applicability of our approach with real data examples on malnutrition in Asia and Africa as well as the analysis of plant and species richness with respect to environmental diversity.","author":[{"propositions":[],"lastnames":["Thaden"],"firstnames":["Hauke"],"suffixes":[]},{"propositions":[],"lastnames":["Klein"],"firstnames":["Nadja"],"suffixes":[]},{"propositions":[],"lastnames":["Kneib"],"firstnames":["Thomas"],"suffixes":[]}],"year":"2019","title":"Multivariate effect priors in bivariate semiparametric recursive Gaussian models","url":"https://www.uni-goettingen.de/de/13_Thaden_02_2017/558175.html","keywords":"econ;phd","pages":"51–66","volume":"137","issn":"01679473","journal":"Computational Statistics & Data Analysis","doi":"10.1016/j.csda.2018.12.004","howpublished":"refereed","bibtex":"@article{Thaden2017General,\r\n abstract = {Modeling complex relationships and interactions between variables is an\r\n\r\nongoing statistical challenge. In particular, the joint modeling of multiple\r\n\r\nresponse variables has recently gained interest among methodological and\r\n\r\napplied researchers. In this article, we contribute to this development by\r\n\r\nincorporating semiparametric predictors into recursive simultaneous equation\r\n\r\nmodels. In particular, we extend the existing framework by imposing effect\r\n\r\npriors that account for correlation of the effects across equations. This idea\r\n\r\ncan be seen as a generalization of multivariate conditional autoregressive\r\n\r\npriors used for the analysis of multivariate spatial data.\r\n\r\nWe implement a Gibbs sampler for the estimation and evaluate the model in\r\n\r\nan elaborate simulation study. Finally, we illustrate the applicability of our\r\n\r\napproach with real data examples on malnutrition in Asia and Africa as well\r\n\r\nas the analysis of plant and species richness with respect to environmental\r\n\r\ndiversity.},\r\n author = {Thaden, Hauke and Klein, Nadja and Kneib, Thomas},\r\n year = {2019},\r\n title = {Multivariate effect priors in bivariate semiparametric recursive Gaussian models},\r\n url = {https://www.uni-goettingen.de/de/13_Thaden_02_2017/558175.html},\r\n keywords = {econ;phd},\r\n pages = {51--66},\r\n volume = {137},\r\n issn = {01679473},\r\n journal = {Computational Statistics {\\&} Data Analysis},\r\n doi = {10.1016/j.csda.2018.12.004},\r\n howpublished = {refereed}\r\n}\r\n\r\n\r\n","author_short":["Thaden, H.","Klein, N.","Kneib, T."],"key":"Thaden2017General","id":"Thaden2017General","bibbaseid":"thaden-klein-kneib-multivariateeffectpriorsinbivariatesemiparametricrecursivegaussianmodels-2019","role":"author","urls":{"Paper":"https://www.uni-goettingen.de/de/13_Thaden_02_2017/558175.html"},"keyword":["econ;phd"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"http://www.uni-goettingen.de/de/document/download/9d7c40531010bf5be953ccd9446e47ae.bib/GRK1644BibHomepage.bib","creationDate":"2020-04-06T15:49:00.968Z","downloads":0,"keywords":["econ;phd"],"search_terms":["multivariate","effect","priors","bivariate","semiparametric","recursive","gaussian","models","thaden","klein","kneib"],"title":"Multivariate effect priors in bivariate semiparametric recursive Gaussian models","year":2019,"dataSources":["psxr4mFyE5JDwFLuZ","2w3D54bmLuhpt4TNv","t8S6Y6RWEwDAQHiSQ","cLGdYAfLyvQDgrYmh"]}