Software packages
plotROC: Generate Useful ROC Curve Charts for Print and Interactive Use
Most ROC curve plots obscure the cutoff values and inhibit interpretation and comparison of multiple curves. This attempts to address those shortcomings by providing plotting and interactive tools. Functions are provided to generate an interactive ROC curve plot for web use, and print versions. A Shiny application implementing the functions is also included.
Package homepage CRAN link Shiny application Related publication
causaloptim: An Interface to Specify Causal Graphs and Compute Bounds on Causal Effects
When causal quantities are not identifiable from the observed data, it still may be possible to bound these quantities using the observed data. We outline a class of problems for which the derivation of tight bounds is always a linear programming problem and can therefore, at least theoretically, be solved using a symbolic linear optimizer. We extend and generalize the approach of Balke and Pearl (1994) doi:10.1016/B978-1-55860-332-5.50011-0 and we provide a user friendly graphical interface for setting up such problems via directed acyclic graphs (DAG), which only allow for problems within this class to be depicted. The user can then define linear constraints to further refine their assumptions to meet their specific problem, and then specify a causal query using a text interface. The program converts this user defined DAG, query, and constraints, and returns tight bounds. The bounds can be converted to R functions to evaluate them for specific datasets, and to latex code for publication. The methods and proofs of tightness and validity of the bounds are described in a paper by Sachs, Jonzon, Gabriel, and Sjölander (2022) doi:10.1080/10618600.2022.2071905.
Package homepage CRAN link Shiny application Related publication
eventglm: Regression Models for Event History Outcomes
A user friendly, easy to understand way of doing event history regression for marginal estimands of interest, including the cumulative incidence and the restricted mean survival, using the pseudo observation framework for estimation. For a review of the methodology, see Andersen and Pohar Perme (2010) doi:10.1177/0962280209105020 or Sachs and Gabriel (2022) doi:10.18637/jss.v102.i09. The interface uses the well known formulation of a generalized linear model and allows for features including plotting of residuals, the use of sampling weights, and corrected variance estimation.
Package homepage CRAN link Related publication
xactonomial: Exact Inference for Real-Valued Functionals of k-Sample Multinomial Parameters
We consider the k sample multinomial problem where we observe k vectors (possibly of different lengths), each representing an independent sample from a multinomial. For a given function psi which takes in the concatenated vector of multinomial probabilities and outputs a real number, we are interested in constructing a confidence interval for psi. We use an exact (but computational and stochastic) method to compute a confidence interval and a function for calculation of p values. The details of the method will be in a forthcoming preprint.
Package homepage
stdReg2: Regression Standardization for Causal Inference
Contains more modern tools for causal inference using regression standardization. Four general classes of models are allowed; generalized linear models, conditional generalized estimating equation models, Cox proportional hazards models and shared frailty gamma-Weibull models. Sjolander, A. (2016) doi:10.1007/s10654-016-0157-3. Also includes functionality for doubly robust estimation for these model classes in some special cases.
Package homepage Related publication
drsurv: Doubly Robust Estimation of Survival Differences with Censored Data
An implementation of several doubly robust estimators for the survival difference at a given time point and one more complex doubly robust estimator for the survival curve process. The estimators are doubly robust in the sense that they are consistent if the censoring model is correctly specified for censoring and either the outcome model is correctly specified for confounding or the exposure model is correctly specified for confounding. See doi:10.48550/arXiv.2310.16207 for more details and examples.
Package homepage Related publication
cosinor: Tools for Estimating and Predicting the Cosinor Model
A set of simple functions that transforms longitudinal data to estimate the cosinor linear model as described in Tong (1976). Methods are given to summarize the mean, amplitude and acrophase, to predict the mean annual outcome value, and to test the coefficients.
Package homepage CRAN link Shiny application Related publication
testassay: A Hypothesis Testing Framework for Validating an Assay for Precision
A common way of validating a biological assay for is through a procedure, where m levels of an analyte are measured with n replicates at each level, and if all m estimates of the coefficient of variation (CV) are less than some prespecified level, then the assay is declared validated for precision within the range of the m analyte levels. Two limitations of this procedure are: there is no clear statistical statement of precision upon passing, and it is unclear how to modify the procedure for assays with constant standard deviation. We provide tools to convert such a procedure into a set of m hypothesis tests. This reframing motivates the m:n:q procedure, which upon completion delivers a 100q% upper confidence limit on the CV. Additionally, for a post-validation assay output of y, the method gives an “effective standard deviation interval” of log(y) plus or minus r, which is a 68% confidence interval on log(mu), where mu is the expected value of the assay output for that sample. Further, the m:n:q procedure can be straightforwardly applied to constant standard deviation assays. We illustrate these tools by applying them to a growth inhibition assay. This is an implementation of the methods described in Fay, Sachs, and Miura (2018) doi:10.1002/sim.7528.
Package homepage CRAN link Related publication
pseval: Methods for Evaluating Principal Surrogates of Treatment Response
Contains the core methods for the evaluation of principal surrogates in a single clinical trial. Provides a flexible interface for defining models for the risk given treatment and the surrogate, the models for integration over the missing counterfactual surrogate responses, and the estimation methods. Estimated maximum likelihood and pseudo-score can be used for estimation, and the bootstrap for inference. A variety of post-estimation summary methods are provided, including print, summary, plot, and testing.
Package homepage CRAN link Related publication
tufterhandout: Tufte-style html document format for rmarkdown
Custom template and output formats for use with rmarkdown. Produce Edward Tufte-style handouts in html formats with full support for rmarkdown features
Package homepage CRAN link