# Ravi Varadhan

#### 18 packages on CRAN

Derivative-Free optimization algorithms. These algorithms do not require gradient information. More importantly, they can be used to solve non-smooth optimization problems.

Performs forward and backwards stepwise regression for the Proportional subdistribution hazards model in competing risks (Fine & Gray 1999). Procedure uses AIC, BIC and BICcr as selection criteria. BICcr has a penalty of k = log(n*), where n* is the number of primary events.

Augmented Lagrangian Adaptive Barrier Minimization Algorithm for optimizing smooth nonlinear objective functions with constraints. Linear or nonlinear equality and inequality constraints are allowed.

Algorithms for accelerating the convergence of slow, monotone sequences from smooth, contraction mapping such as the EM algorithm. It can be used to accelerate any smooth, linearly convergent acceleration scheme. A tutorial style introduction to this package is available in a vignette on the CRAN download page or, when the package is loaded in an R session, with vignette("SQUAREM").

Computes conditional multivariate normal probabilities, random deviates and densities.

Discretely-sampled function is first smoothed. Features of the smoothed function are then extracted. Some of the key features include mean value, first and second derivatives, critical points (i.e. local maxima and minima), curvature of cunction at critical points, wiggliness of the function, noise in data, and outliers in data.

Solves the ``inverse eigenvalue problem'' which is to generate a real-valued matrix that has the specified real eigenvalue spectrum. It can generate infinitely many dense matrices, symmetric or asymmetric, with the given set of eigenvalues. Algorithm can also generate stochastic and doubly stochastic matrices.

Algorithms for accelerating the convergence of slow, monotone sequences from smooth, contraction mapping such as the EM and MM algorithms. It can be used to accelerate any smooth, linearly convergent acceleration scheme. A tutorial style introduction to this package is available in a vignette on the CRAN download page or, when the package is loaded in an R session, with vignette("turboEM").

Derivative-free optimization by quadratic approximation based on an interface to Fortran implementations by M. J. D. Powell.

Methods for calculating (usually) accurate numerical first and second order derivatives. Accurate calculations are done using 'Richardson''s' extrapolation or, when applicable, a complex step derivative is available. A simple difference method is also provided. Simple difference is (usually) less accurate but is much quicker than 'Richardson''s' extrapolation and provides a useful cross-check. Methods are provided for real scalar and vector valued functions.

Provides a replacement and extension of the optim() function to unify and streamline optimization capabilities in R for smooth, possibly box constrained functions of several or many parameters. This is the CRAN version of the package.

Barzilai-Borwein spectral methods for solving nonlinear system of equations, and for optimizing nonlinear objective functions subject to simple constraints. A tutorial style introduction to this package is available in a vignette on the CRAN download page or, when the package is loaded in an R session, with vignette("BB").

The tools in this package are intended to help researchers assess multiple treatment-covariate interactions with data from a parallel-group randomized controlled clinical trial.

Implements a semi-parametric GEE estimator accounting for missing data with Inverse-probability weighting (IPW) and for imbalance in covariates with augmentation (AUG). The estimator IPW-AUG-GEE is Doubly robust (DR).

Provides a test of replacement and extension of the optim() function to unify and streamline optimization capabilities in R for smooth, possibly box constrained functions of several or many parameters. This version has a reduced set of methods and is intended to be on CRAN.

It is vital to assess the heterogeneity of treatment effects (HTE) when making health care decisions for an individual patient or a group of patients. Nevertheless, it remains challenging to evaluate HTE based on information collected from clinical studies that are often designed and conducted to evaluate the efficacy of a treatment for the overall population. The Bayesian framework offers a principled and flexible approach to estimate and compare treatment effects across subgroups of patients defined by their characteristics. This package allows users to explore a wide range of Bayesian HTE analysis models, and produce posterior inferences about HTE.

Calculate posterior modes and credible intervals of parameters of the Dixon-Simon model for subgroup analysis (with binary covariates) in clinical trials.

Package for optimizing regular numeric problems in optically stimulated luminescence dating, such as: equivalent dose calculation, dose rate determination, growth curve fitting, decay curve decomposition, statistical age model optimization, and statistical plot visualization.