Here are various open source R packages developed from members of the van der Laan research group. |
More help on R can be found at: R project |
If you would like to receive email updates about new releases of the DSA please email: Romain.S.Neugebauer [at] nsmtp.kp.org or bullard [at] berkeley.edu to subscribe to the mailing list. |
Computationally Efficient Confidence Intervals for Cross-validated Area Under the ROC Curve Estimates
The "cvAUC" R package computes influence curve based confidence intervals for cross-validated Area Under the ROC curve (AUC) estimates. Influence curve based variance estimation serves as a computationally efficient alternative to bootstrapping. See the corresponding tech report for more information.
download | platform | release date | status | maintainer | release notes |
cvAUC_1.0-0.tar.gz | unix/src | 12/06/2012 | stable | ledell [at] berkeley.edu | |
cvAUC_1.0-0.zip | windows binary | 12/06/2012 | stable | ledell [at] berkeley.edu |
Targeted Minimum Loss Based Estimation of an Intervention Specific Mean Outcome
R source code for TMLE, IPTW, and parametric MLE estimation of the treatment specific mean outcome. Examples are provided in a separate file. |
download | platform | release date | status | maintainer | release notes |
tmle_ISM.R | R src | 01/16/2012 | stable | sgruber [at] berkeley.edu | |
tmle_ISM_simulations.R | R src | 01/16/2012 | stable | sgruber [at] berkeley.edu |
Targeted Maximum Likelihood Estimation with Point Treatment Data
Targeted maximum likelihood estimation (TMLE) of marginal treatment effect of a binary point treatment on a continuous or binary outcome, adjusting for baseline covariates. Missingness in the outcome is accounted for in the estimation procedure. The tmle package provides estimation of the additive treatment effect for a continuous outcome, and risk difference, risk ratio, and odds ratio estimates for binary outcomes. Super learning for data-adaptive estimation is recommended (see http://www.stat.berkeley.edu/~ecpolley/SL/).
download | platform | release date | status | maintainer | release notes |
tmle_1.1.tar.gz | unix/src | 02/04/2011 | stable | sgruber [at] berkeley.edu | |
tmle_1.1.zip | windows binary | 02/04/2011 | stable | sgruber [at] berkeley.edu | |
tmle_1.0.tar.gz | unix/src | 10/18/2010 | stable | sgruber [at] berkeley.edu |
Collaborative targeted maximum likelihood estimation of an additive treatment effect. Super learning for data-adaptive estimation is recommended (see http://www.stat.berkeley.edu/~ecpolley/SL/). |
download | platform | release date | status | maintainer | release notes |
ctmle_0.5.3.R | R src | 01/16/2012 | stable | sgruber [at] berkeley.edu | Minor bug fixes. |
ctmle_0.5.R | R src | 10/15/2010 | stable | sgruber [at] berkeley.edu |
Collaborative targeted maximum likelihood estimation of a population mean outcome under missingness. |
download | platform | release date | status | maintainer | release notes |
ctmle_EY1.0.5.4.R | R src | 01/16/2012 | stable | sgruber [at] berkeley.edu |
"tmleLite" implements a simplified TMLE approach to estimating the additive treatment effect using the DSA algorithm for data-adaptive estimation of the Q and g portions of the likelihood, and is restricted to a linear fluctuation when targeting the effect on a continuous outcome. |
download | platform | release date | status | maintainer | release notes |
tmleLite_1.0-2.tar.gz | unix/src | 02/11/2010 | stable | sgruber [at] berkeley.edu | |
tmleLite_1.0-2.zip | windows binary | 02/11/2010 | stable | sgruber [at] berkeley.edu | Release Notes |
tmleLite_1.0-1.tar.gz | unix/src | 12/16/2009 | stable | sgruber [at] berkeley.edu | |
tmleLite_1.0-1.zip | windows binary | 12/16/2009 | stable | sgruber [at] berkeley.edu |
Demo of Longitudinal TMLE package for fitting marginal structural working models that model the effect of multiple time point dynamic or static interventions on time to event outcomes. |
download | platform | release date | status | maintainer | release notes |
ltmle_0.8.tar.gz | unix/src | 03/07/2013 | stable | joshuaschwab [at] yahoo.com | readme.txt |
simsLtmleCroi.R | R src | 03/07/2013 | stable | joshuaschwab [at] yahoo.com | |
iedea methods public.pdf | 03/07/2013 | stable | joshuaschwab [at] yahoo.com |
Data-Adaptive Estimation with Cross-Validation and the D/S/A Algorithm
The DSA performs data-adaptive estimation through estimator selection
based on cross-validation and the L2 loss function. Candidate
estimators are defined with polynomial generalized linear models
generated with the Deletion/Substitution/Addition (D/S/A) algorithm
under user-specified constraints.
download | platform | release date | status | maintainer | release notes |
modelUtils_3.1.4.tar.gz / DSA_3.1.4.tar.gz | unix/src | 06/30/2010 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
modelUtils_3.1.4.zip / DSA_3.1.4.zip | windows binary | 06/30/2010 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.1.3.tar.gz | unix/src | 09/01/2008 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.1.3.zip | windows binary | 09/01/2008 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.1.2.tar.gz | unix/src | 08/09/2008 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.1.2.zip | windows binary | 08/09/2008 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.1.1.tar.gz | unix/src | 08/20/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.1.1.zip | windows binary | 08/20/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.1.tar.gz | unix/src | 08/20/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.1.zip | windows binary | 08/20/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.0.2.tar.gz | unix/src | 07/06/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.0.2.zip | windows binary | 07/06/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.0.1.tar.gz | unix/src | 07/06/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.0.1.zip | windows binary | 07/06/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.0.tar.gz | unix/src | 06/21/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_3.0.zip | windows binary | 06/21/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.2.2.tar.gz | unix/src | 01/08/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.2.2.zip | windows binary | 01/08/2007 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.2.1.tar.gz | unix/src | 12/05/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.2.1.zip | windows binary | 12/05/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.1.4.tar.gz | unix/src | 10/10/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.1.4.zip | windows binary | 10/10/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.1.3.tar.gz | unix/src | 9/25/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.1.3.zip | windows binary | 9/25/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.1.2.tar.gz | unix/src | 9/12/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.1.2.zip | windows binary | 9/12/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.0.2.tar.gz | unix/src | 7/25/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_2.0.2.zip | windows binary | 7/25/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | Release Notes |
DSA_1.1.tar.gz | unix/src | 3/31/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | |
DSA_1.1.zip | windows binary | 3/31/2006 | stable | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | |
DSA_1.0.tar.gz | unix/src | 2/6/2006 | obsolete | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu | |
DSA_1.0.zip | windows binary | 2/6/2006 | obsolete | Romain.S.Neugebauer [at] nsmtp.kp.org,bullard [at] stat.berkeley.edu |
MSM-Based Causal Inference with Point Treatment Data
The cvDSA package groups several routines for causal inference with
point treatment data based on Marginal Structural Models (MSM). The
routines are entirely written in R and can be used for MSM estimation
with the Inverse Probability of Treatment Weighted, G-computation and
Double Robust estimators (data-adaptive estimation with
cross-validation and the D/S/A algorithm, check of the Experimental
Treatment Assignment (ETA) assumption, etc). A GUI interface is
available for easy use of the routines along with complete
documentation (library(help=cvDSA)). Version 0.5-3-1 was updated by Erin Hartman and Jasjeet Sekhon and can be installed on any R platform (i.e. Windows, Mac, *nix). Version 0.5-3-2 was updated by Susan Gruber.
download | platform | release date | status | maintainer | release notes |
cvDSA_0.5-3.2.tar.gz | unix/windows src | 10/15/2010 | stable | sgruber [at] berkeley.edu | Release Notes |
MSM_point_treatment.zip | unix/windows src | 2/1/2006 | stable | ywang [at] stat.berkeley.edu | |
cvDSA_0.5-3-1.tar.gz | unix/windows src | 6/12/2009 | stable | sekhon [at] berkeley.edu |
Supervised detection of conserved motifs in DNA sequences with cosmo
cosmo searches a set of unaligned DNA sequences for a common motif that might represent, for example, a shared transcription factor binding site. This search can be supervised by specifying a set of constraints that the position weight matrix of the unknown motif must satisfy. Such constraints may be formulated, for example, on the basis of prior knowledge about the structure of the transcription factor in question. More information on cosmo as well as an implementation in the form of a web-application are available at http://cosmoweb.berkeley.edu/intro.html. |
download | platform | release date | status | maintainer | release notes |
cosmo_1.0.tar.gz | unix/src | 9/5/2006 | stable | bembom [at] berkeley.edu |
Data-adaptively truncated IPTW estimators
This package implements IPTW estimators that data-adaptively select an appropriate truncation level for the treatment mechanism with the aim of minimizing the mean squared error of the resulting estimator. |
download | platform | release date | status | maintainer | release notes |
tIPTW_1.0.0.tar.gz | unix/src | 3/10/2008 | stable | bembom [at] berkeley.edu |
Diagnosing and Responding to Violations in the Positivity Assumption
R source code to diagnose estimator bias due to positivity violations for the following estimation procedures: G-computation, Inverse Probability of Treatment Weighted estimation (IPTW), augmented IPTW, and Targeted Maximum Likelihood Estimation, using a parametric bootstrap approach (bias.pboot.R). Examples are provides in a separate file. |
download | platform | release date | status | maintainer | release notes |
bias.pboot.R | R src | 10/15/2010 | stable | kristinporter [at] berkeley.edu sgruber [at] berkeley.edu |
|
positivity_simulations.R | R src | 10/15/2010 | stable | kristinporter [at] berkeley.edu sgruber [at] berkeley.edu |