Computational approaches to scaling up experimental science
Abstract/Contents
- Abstract
- Low statistical power reduces the likelihood of detecting true effects and produces unreliable research with low reproducibility of results, but resource constraints limit sample sizes when resource requirements scale linearly with sample size. This work applies computational methods to scaling up experimental science, affecting experimental design, data collection and analysis. In the domain of gene expression measurements, costs are reduced by selecting reduced probe sets and imputing the remaining probes. Evaluation of the methods developed here in a wide variety of experimental settings shows that linking selection and imputation in a unified objective allows for considerable cost reductions with small information loss, and the approach is further validated in a large-scale study of immune system variation. Two additional applications of computational methods scale up cognitive testing and modeling of human learning dynamics.
Description
Type of resource | text |
---|---|
Form | electronic; electronic resource; remote |
Extent | 1 online resource. |
Publication date | 2015 |
Issuance | monographic |
Language | English |
Creators/Contributors
Associated with | Donner, Yonatan |
---|---|
Associated with | Stanford University, Department of Computer Science. |
Primary advisor | Shoham, Yoav |
Thesis advisor | Shoham, Yoav |
Thesis advisor | Batzoglou, Serafim |
Thesis advisor | Kosslyn, Stephen Michael, 1948- |
Advisor | Batzoglou, Serafim |
Advisor | Kosslyn, Stephen Michael, 1948- |
Subjects
Genre | Theses |
---|
Bibliographic information
Statement of responsibility | Yoni Donner. |
---|---|
Note | Submitted to the Department of Computer Science. |
Thesis | Thesis (Ph.D.)--Stanford University, 2015. |
Location | electronic resource |
Access conditions
- Copyright
- © 2015 by Yonatan Nissan Donner
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...