Strategies for Model Mixing in Generalized Linear Models

Merlise Clyde
Proceedings of the Sixth International Workshop on Artificial Intelligence and Statistics, PMLR R1:103-114, 1997.

Abstract

In linear regression models and generalized linear regression models (GLMs), there is often substantial uncertainty about the choice of covariates to include in the model. Both classical and Bayesian approaches that involve selecting a subset of covariates and making inferences conditional on that model choice ignore a major component of uncertainty in the problem. One approach for incorporating this form of model uncertainty into the analysis is by directly building into the model a vector of indicator variables $Y$ that reflects which covariates are included in the model ...

Cite this Paper

BibTeX
@InProceedings{pmlr-vR1-clyde97a, title = {Strategies for Model Mixing in Generalized Linear Models}, author = {Clyde, Merlise}, booktitle = {Proceedings of the Sixth International Workshop on Artificial Intelligence and Statistics}, pages = {103--114}, year = {1997}, editor = {Madigan, David and Smyth, Padhraic}, volume = {R1}, series = {Proceedings of Machine Learning Research}, month = {04--07 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r1/clyde97a/clyde97a.pdf}, url = {https://proceedings.mlr.press/r1/clyde97a.html}, abstract = {In linear regression models and generalized linear regression models (GLMs), there is often substantial uncertainty about the choice of covariates to include in the model. Both classical and Bayesian approaches that involve selecting a subset of covariates and making inferences conditional on that model choice ignore a major component of uncertainty in the problem. One approach for incorporating this form of model uncertainty into the analysis is by directly building into the model a vector of indicator variables $Y$ that reflects which covariates are included in the model ...}, note = {Reissued by PMLR on 30 March 2021.} }
Endnote
%0 Conference Paper %T Strategies for Model Mixing in Generalized Linear Models %A Merlise Clyde %B Proceedings of the Sixth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 1997 %E David Madigan %E Padhraic Smyth %F pmlr-vR1-clyde97a %I PMLR %P 103--114 %U https://proceedings.mlr.press/r1/clyde97a.html %V R1 %X In linear regression models and generalized linear regression models (GLMs), there is often substantial uncertainty about the choice of covariates to include in the model. Both classical and Bayesian approaches that involve selecting a subset of covariates and making inferences conditional on that model choice ignore a major component of uncertainty in the problem. One approach for incorporating this form of model uncertainty into the analysis is by directly building into the model a vector of indicator variables $Y$ that reflects which covariates are included in the model ... %Z Reissued by PMLR on 30 March 2021.
APA
Clyde, M.. (1997). Strategies for Model Mixing in Generalized Linear Models. Proceedings of the Sixth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R1:103-114 Available from https://proceedings.mlr.press/r1/clyde97a.html. Reissued by PMLR on 30 March 2021.

Related Material