A variable selection approach to monotonic regression with Bernstein polynomials

One of the standard problems in statistics consists of determining the relationship between a response variable and a single predictor variable through a regression function. Background scientific knowledge is often available that suggests that the regression function should have a certain shape (e.g. monotonically increasing or concave) but not necessarily a specific parametric form. Bernstein polynomials have been used to impose certain shape restrictions on regression functions. The Bernstein polynomials are known to provide a smooth estimate over equidistant knots. Bernstein polynomials are used in this paper due to their ease of implementation, continuous differentiability, and theoretical properties. In this work, we demonstrate a connection between the monotonic regression problem and the variable selection problem in the linear model. We develop a Bayesian procedure for fitting the monotonic regression model by adapting currently available variable selection procedures. We demonstrate the effectiveness of our method through simulations and the analysis of real data.     

Developing a new BIC for detecting change-points

Usual derivation of BIC for the marginal likelihood of a model or hypothesis via Laplace approximation does not hold for a change-point which is a discrete parameter. We provide an analogue l BIC, which is a lower bound to the marginal likelihood of a model with change points and has an approximation error up to O_p(1) like standard Schwartz BIC. Several applications are provided covering simulated r.v.'s and real financial figures on short-term interest rate.     

Bayesian and likelihood-based inference for the bivariate normal correlation coefficient

The paper develops some objective priors for correlation coefficient of the bivariate normal distribution. The criterion used is the asymptotic matching of coverage probabilities of Bayesian credible intervals with the corresponding frequentist coverage probabilities. The paper uses various matching criteria, namely, quantile matching, highest posterior density matching, and matching via inversion of test statistics. Each matching criterion leads to a different prior for the parameter of interest. We evaluate their performance by comparing credible intervals through simulation studies. In addition, inference through several likelihood-based methods have been discussed.     

The Competitive Impact of Targeted Television Advertisements Using DVR Technology

Digital video recorders (DVRs) are an emerging technology that is fundamentally changing the competitive landscape in industries that advertise on television. Perhaps the most familiar impact of DVR technology is that it enables consumers to avoid advertisements (ads) by fast forwarding through them. However, this “zipping” of ads is only one aspect of the impact of DVR technology. DVRs also collect a wealth of information at the consumer level that can be used by firms to target their ads more effectively. We examine how this targeting capability moderates the impact of ad avoidance in a competitive setting. Insights are provided on how best to manage this emerging technology in terms of the key managerial decisions of product pricing and advertising efforts, as well as its impact on profits in a competitive (duopoly) marketplace.     

Estimating the distribution function using k-tuple ranked set samples

The basic assumption underlying the concept of ranked set sampling is that actual measurement of units is expensive, whereas ranking is cheap. This may not be true in reality in certain cases where ranking may be moderately expensive. In such situations, based on total cost considerations, k-tuple ranked set sampling is known to be a viable alternative, where one selects k units (instead of one) from each ranked set. In this article, we consider estimation of the distribution function based on k-tuple ranked set samples when the cost of selecting and ranking units is not ignorable. We investigate estimation both in the balanced and unbalanced data case. Properties of the estimation procedure in the presence of ranking error are also investigated. Results of simulation studies as well as an application to a real data set are presented to illustrate some of the theoretical findings.     

Constrained Bayes and empirical Bayes estimation under random effects normal ANOVA model with balanced loss function

The paper develops constrained Bayes and empirical Bayes estimators in the random effects ANOVA model under balanced loss functions. In the balanced normal–normal model, estimators of the Bayes risks of the constrained Bayes and constrained empirical Bayes estimators are provided which are correct asymptotically up to O(m^-1)$\mathrm{O}(m^{-1})$, that is the remainder term is o(m^-1)$\mathrm{o}(m^{-1})$, m$m$ denoting the number of strata.     

Some new factor screening designs using the search linear model

Factor screening designs for searching two and three effective factors using the search linear model are discussed. The construction of such factor screening designs involved finding a fraction with small number of treatments of a 2^m factorial experiment having the property P_2t (no 2t columns are linearly dependent) for t=2 and 3. A ‘Packing Problem’ is introduced in this connection. A complete solution of the problem in one case and partial solutions for the other cases are presented. Many practically useful new designs are listed.     

LGBTQ Activist Organizations as ‘Respectably Queer’ in India: Contesting a Western View

This study contests the distinction of LGBTQ (lesbian, gay, bisexual, transgender and queer) organizations suggested by earlier scholars as ‘respectable’ — i.e. normalizing, professionalizing and conforming to the dominant cultural and institutional patterns — and ‘queer’, meaning challenging the cultural and institutional forces that ‘normalize and commodify differences’. Using Bernstein's model of identity deployment, it is found problematic to distinguish LGBTQ organizations this way because when the actions of LGBTQ organizations are more complex to describe, it is not warranted to conflate identity goals with identity strategies — whether normalizing (respectable) or differentiating (queer). To examine these concerns, a qualitative inquiry was used to study five LGBTQ organizations in India where the intersections of post‐colonial ethnicity, gender, social class and sexuality offer an intriguing context through which to study queer activism. Based on the findings, it is argued from a post‐colonial perspective that when the socio‐cultural and historical existence of non‐homonormative queer communities and practices is strong, LGBTQ organizations challenge the heteronormative and/or other forms of domination to become ‘queer’. But they may simultaneously become ‘respectable′ by conforming to the diversity politics of non‐profit business, donors, and social movement organizations they seek support from, and turn out as ‘respectably queer’.