%0 Conference Paper %1 camargo_estimation_2012 %A Camargo, André P. %A Stern, Julio M. %A Lauretto, Marcelo S. %B AIP Conference Proceedings %C Waterloo, Ontario, Canada %D 2012 %I American Institute of Physics %K Bayesian compositional data, dirichlet dirichlet, inference, model regression, selection %P 206--213 %R doi:10.1063/1.3703637 %T Estimation and model selection in Dirichlet regression %U http://proceedings.aip.org/resource/2/apcpcs/1443/1/206_1 %V 1443 %X We study Compositional Models based on Dirichlet Regression where, given a (vector) covariate x, one considers the response variable y = (y1,...,yD) to be a positive vector with a conditional Dirichlet distribution, y\textbarx ̃ D(α1(x)...αD(x)). We introduce a new method for estimating the parameters of the Dirichlet Covariate Model when αj(x) is a linear model on x, and also propose a Bayesian model selection approach. We present some numerical results which suggest that our proposals are more stable and robust than traditional approaches.

@inproceedings{camargo_estimation_2012, abstract = {We study Compositional Models based on Dirichlet Regression where, given a (vector) covariate x, one considers the response variable y = (y1,...,yD) to be a positive vector with a conditional Dirichlet distribution, y{\textbar}x ̃ D(α1(x)...αD(x)). We introduce a new method for estimating the parameters of the Dirichlet Covariate Model when αj(x) is a linear model on x, and also propose a Bayesian model selection approach. We present some numerical results which suggest that our proposals are more stable and robust than traditional approaches.}, added-at = {2017-01-09T13:57:26.000+0100}, address = {Waterloo, Ontario, Canada}, author = {Camargo, André P. and Stern, Julio M. and Lauretto, Marcelo S.}, biburl = {https://www.bibsonomy.org/bibtex/2d2acba2d7bd5c5cde6846448d1e70658/yourwelcome}, booktitle = {{AIP} {Conference} {Proceedings}}, doi = {doi:10.1063/1.3703637}, interhash = {10490c284eb42d3d8c059ee75772856a}, intrahash = {d2acba2d7bd5c5cde6846448d1e70658}, keywords = {Bayesian compositional data, dirichlet dirichlet, inference, model regression, selection}, month = may, pages = {206--213}, publisher = {American Institute of Physics}, timestamp = {2017-01-09T14:01:11.000+0100}, title = {Estimation and model selection in {Dirichlet} regression}, url = {http://proceedings.aip.org/resource/2/apcpcs/1443/1/206_1}, urldate = {2012-07-21}, volume = 1443, year = 2012 }