R
Ramani S. Pilla
Researcher at National Institutes of Health
Publications - 6
Citations - 107
Ramani S. Pilla is an academic researcher from National Institutes of Health. The author has contributed to research in topics: Estimator & Generalized method of moments. The author has an hindex of 5, co-authored 6 publications receiving 95 citations.
Papers
More filters
Journal ArticleDOI
Moment-Based Approximations of Distributions Using Mixtures: Theory and Applications
TL;DR: The authors used moment methods to approximate a theoretical univariate distribution with mixtures of known distributions, such as normal and gamma mixtures, and showed that the new approximation is generally superior to these alternatives.
Journal ArticleDOI
Iteratively Reweighted Generalized Least Squares for Estimation and Testing With Correlated Data: An Inference Function Framework
Catherine Loader,Ramani S. Pilla +1 more
TL;DR: This article derives an iteratively reweighted generalized least squares or IRGLS algorithm for finding the QIF estimator and establishes its convergence properties.
Posted Content
Inference Under Convex Cone Alternatives for Correlated Data
TL;DR: In this paper, an inferential theory for hypothesis testing under general convex cone alternatives for correlated data is developed, and an asymptotic lower bound is constructed for the power of the generalized quasi-score test under a sequence of local alternatives in the convex manifold in the unit sphere.
Posted Content
On large-sample estimation and testing via quadratic inference functions for correlated data
Ramani S. Pilla,Catherine Loader +1 more
TL;DR: In this paper, a generalized estimating equation framework is proposed to estimate the underlying correlation structure of correlated data. But, the framework is restricted to a set of score functions and does not address the problem of estimating the underlying covariance matrix.
Posted Content
Model Building for Semiparametric Mixtures
TL;DR: In this article, a unified framework for finding the nonparametric maximum likelihood estimator of a multivariate mixing distribution and consequently estimating the mixture complexity is developed, which casts the mixture maximization problem in the concave optimization framework with finitely many linear inequality constraints and turns it into an unconstrained problem using a "penalty function".