Strimenopoulou, F. and Brown, P.J. (2008) Empirical Bayes logistic regression. Statistical Applications in Genetics and Molecular Biology, 7 (2). ISSN 1544-6115 .
| The full text of this publication is not available from this repository. (Contact us about this Publication) | |
| Official URL http://dx.doi.org/10.2202/1544-6115.1359 |
Abstract
We construct a diagnostic predictor for patient disease status based on a single data set of mass spectra of serum samples together with the binary case-control response. The model is logistic regression with Bernoulli log-likelihood augmented either by quadratic ridge or absolute $L_1$ penalties. For ridge penalization using the singular value decomposition we reduce the the number of variables for maximization to the rank of the design matrix. With log-likelihood loss, 10-fold cross-validatory choice is employed to specify the penalization hyperparameter. Predictive ability is judged on a set-aside subset of the data.
| Item Type: | Article |
|---|---|
| Additional information: | Article No 9 |
| Subjects: | Q Science > QA Mathematics (inc Computing science) > QA276 Mathematical statistics |
| Divisions: | Faculties > Science Technology and Medical Studies > School of Mathematics Statistics and Actuarial Science > Statistics |
| Depositing User: | Philip J Brown |
| Date Deposited: | 07 Mar 2009 13:00 |
| Last Modified: | 14 Jan 2010 14:30 |
| Resource URI: | http://kar.kent.ac.uk/id/eprint/8191 (The current URI for this page, for reference purposes) |
- Depositors only (login required):
