Science Score: 23.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
✓Committers with academic emails
10 of 21 committers (47.6%) from academic institutions -
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.6%) to scientific vocabulary
Repository
An R package for adaptive shrinkage
Basic Info
Statistics
- Stars: 84
- Watchers: 9
- Forks: 37
- Open Issues: 47
- Releases: 10
Metadata Files
README.md
This repository contains an R package for performing "Adaptive Shrinkage."
To install the ashr package first you need to install devtools:
R
install.packages("devtools")
library(devtools)
install_github("stephens999/ashr")
Running Adaptive Shrinkage
The main function in the ashr package is ash. To get minimal help:
R
library(ashr)
?ash
More background
The ashr ("Adaptive SHrinkage") package aims to provide simple, generic, and flexible methods to derive "shrinkage-based" estimates and credible intervals for unknown quantities $\beta=(\beta1,\dots,\betaJ)$, given only estimates of those quantities ($\hat\beta=(\hat\beta1,\dots, \hat\betaJ)$) and their corresponding estimated standard errors ($s=(s1,\dots,sJ)$).
The "adaptive" nature of the shrinkage is two-fold. First, the appropriate amount of shrinkage is determined from the data, rather than being pre-specified. Second, the amount of shrinkage undergone by each $\hat\betaj$ will depend on the standard error $sj$: measurements with high standard error will undergo more shrinkage than measurements with low standard error.
Methods Outline
The methods are based on treating the vectors $\hat\beta$ and $s$ as "observed data", and then performing inference for $\beta$ from these observed data, using a standard hierarchical modelling framework to combine information across $j=1,\dots,J$.
Specifically, we assume that the true $\beta_j$ values are independent
and identically distributed from some unimodal distribution $g$. By
default we assume $g$ is unimodal about zero and symmetric. You can
specify or estimate a different mode using the mode parameter. You
can allow for asymmetric $g$ by specifying
mixcompdist="halfuniform".
Then, we assume that the observations $\hat\betaj \sim
N(\betaj,sj)$, or alternatively the normal assumption can be
replaced by a $t$ distribution by specifying df, the number of
degrees of freedom used to estimate $sj$. Actually this is
important: do be sure to specify df if you can.
Owner
- Name: Matthew Stephens
- Login: stephens999
- Kind: user
- Repositories: 28
- Profile: https://github.com/stephens999
GitHub Events
Total
- Issues event: 3
- Watch event: 4
- Issue comment event: 8
- Pull request event: 1
- Fork event: 1
Last Year
- Issues event: 3
- Watch event: 4
- Issue comment event: 8
- Pull request event: 1
- Fork event: 1
Committers
Last synced: about 1 year ago
Top Committers
| Name | Commits | |
|---|---|---|
| stephens999 | s****9@g****m | 282 |
| Peter Carbonetto | p****o@g****m | 144 |
| Jason Willwerscheid | w****d@u****u | 45 |
| daichaoxing | d****g@g****m | 44 |
| David Gerard | g****7@g****m | 22 |
| MuzheZeng | m****e@u****u | 17 |
| Mengyin | m****8@g****m | 17 |
| esterpantaleo | e****o@g****m | 10 |
| LSun | s****l@u****u | 9 |
| Zhengrong | z****g@u****u | 5 |
| Xiao Nan | r****t@g****m | 3 |
| Wei Wang | w****g@W****l | 3 |
| Zhengrong | z****g@g****u | 3 |
| Abhishek Sarkar | a****r@a****u | 2 |
| zouyuxin | y****t@g****m | 2 |
| Eric | e****5@g****m | 1 |
| chaoxing | c****g@w****u | 1 |
| Wei Wang | w****g@w****u | 1 |
| Wei Wang | w****g@w****u | 1 |
| Evan M. Koch | e****h@b****u | 1 |
| heejungshim | h****m@g****m | 1 |
Committer Domains (Top 20 + Academic)
Issues and Pull Requests
Last synced: 11 months ago
All Time
- Total issues: 72
- Total pull requests: 36
- Average time to close issues: 5 months
- Average time to close pull requests: 18 days
- Total issue authors: 25
- Total pull request authors: 9
- Average comments per issue: 3.35
- Average comments per pull request: 1.89
- Merged pull requests: 27
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 2
- Pull requests: 2
- Average time to close issues: about 18 hours
- Average time to close pull requests: N/A
- Issue authors: 2
- Pull request authors: 1
- Average comments per issue: 2.0
- Average comments per pull request: 1.5
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- pcarbo (14)
- willwerscheid (13)
- stephens999 (12)
- aksarkar (6)
- william-denault (4)
- frederikziebell (3)
- mengyin (2)
- eacton (1)
- tamigj (1)
- jhsiao999 (1)
- agombolay (1)
- DongyueXie (1)
- suzannastep (1)
- eweine (1)
- msarguru (1)
Pull Request Authors
- willwerscheid (17)
- mengyin (9)
- LSun (3)
- aksarkar (2)
- nikhilmilind (2)
- eweine (1)
- zouyuxin (1)
- suzannastep (1)
- emkoch (1)
Top Labels
Issue Labels
Pull Request Labels
Packages
- Total packages: 2
-
Total downloads:
- cran 4,482 last-month
- Total docker downloads: 192,352
-
Total dependent packages: 8
(may contain duplicates) -
Total dependent repositories: 35
(may contain duplicates) - Total versions: 14
- Total maintainers: 1
cran.r-project.org: ashr
Methods for Adaptive Shrinkage, using Empirical Bayes
- Homepage: https://github.com/stephens999/ashr
- Documentation: http://cran.r-project.org/web/packages/ashr/ashr.pdf
- License: GPL (≥ 3)
-
Latest release: 2.0.5
published over 9 years ago
Rankings
Maintainers (1)
conda-forge.org: r-ashr
- Homepage: https://github.com/stephens999/ashr
- License: GPL-3.0-or-later
-
Latest release: 2.0.5
published almost 4 years ago
Rankings
Dependencies
- R >= 3.1.0 depends
- Matrix * imports
- Rcpp >= 0.10.5 imports
- SQUAREM * imports
- etrunct * imports
- graphics * imports
- invgamma * imports
- mixsqp * imports
- stats * imports
- truncnorm * imports
- REBayes * suggests
- ggplot2 * suggests
- knitr * suggests
- rmarkdown * suggests
- testthat * suggests