ESTIMATING THE COMMON MEAN OF A BIVARIATE NORMAL POPULATION

For estimating the common mean of a bivariate normal distribution, Krishnamoorthy & Rohatgi (1989) proposed some estimators which dominate the maximum likelihood estimator in a large region of the parameter space. We consider some modifications of these estimators and study their risk performance.     

A stochastic Newton-Raphson method

A stochastic approximation procedure of the Robbins-Monro type is considered. The original idea behind the Newton-Raphson method is used as follows. Given n approximations X₁,…, X_n with observations Y₁,…, Y_n, a least squares line is fitted to the points (X_m, Y_m),…, (X_n, Y_n) where m<n may depend on n. The (n+1)st approximation is taken to be the intersection of the least squares line with y=0. A variation of the resulting process is studied. It is shown that this process yields a strongly consistent sequence of estimates which is asymptotically normal with minimal asymptotic variance.     

Efficient Use of Two Decks of Cards in Randomized Response Sampling

This paper extends the work of Russell (1976). Proof Is given that, for many parameter sets, all O:XB designs belonging to the set are connected. It is shown how an (M,S)-optinal design nay be selected from the M-optimal designs of a given parameter set. The efficiencies of these (M,S)-optimal designs are displayed, and it is concluded that the (M,S)-optimality criterion is useful for selecting designs of high efficiency.     

Confidence Bounds for Multiplicative Comparisons

Statements that are inherently multiplicative have historically been justified using ratios of random variables. Although recent work on ratios has extended the classical theory to produce confidence bounds conditioned on a positive denominator, this current article offers a novel perspective that eliminates the need for such a condition. Although seemingly trivial, this new perspective leads to improved lower confidence bounds to support multiplicative statements. This perspective is also more satisfying as it allows comparisons that are inherently multiplicative in nature to be properly analyzed as such.     

On Blest’s Measure of Kurtosis Adjusted for Skewness

We reconsider the derivation of Blest’s (2003) skewness adjusted version of the classical moment-based coefficient of kurtosis and propose an adaptation of it which generally eliminates the effects of asymmetry a little more successfully. Lower bounds are provided for the two skewness adjusted kurtosis moment measures as functions of the classical coefficient of skewness. The results from a Monte Carlo experiment designed to investigate the sampling properties of numerous moment-based estimators of the two skewness adjusted kurtosis measures are used to identify those estimators with lowest mean squared error for small to medium sized samples drawn from distributions with varying levels of asymmetry and tailweight.     

A sinuous stratified unrelated question randomized response model

ABSTRACT

This paper considers the use of stratified random sampling with proportional as well as Neyman allocations to unrelated question randomized response strategy. It has been shown that, for the prior information given, our new model is more efficient in terms of variance (in the case of completely truthful reporting) and mean square error (in case of less than completely truthful reporting). Numerical illustrations are also given in support of the present study.     

An efficient new “Partial” randomized response model

ABSTRACT

In this article, a new “Partial” randomized response model has been proposed. Its properties are studied both theoretically and empirically. The proposed model is proved to be more efficient than the randomized response models studied by Eichhorn and Hayre (1983 Eichhorn, B.H., Hayre, L.S. (1983). Scrambled randomized response methods for obtaining sensitive quantitative dada. J. Stat. Plann. Inference. 7:307–316.[Crossref], [Web of Science ®] , [Google Scholar]) and the “Partial” randomized response model.     

A modified optimal orthogonal new additive model

ABSTRACT

In this article, a new randomized response model has been proposed. The proposed model is found to be more efficient than the randomized response models studied by Singh (2010 Singh, S. (2010). Proposed optimal orthogonal new additive model (POONAM). Statistica. Anno LXX(1):73–81. [Google Scholar]). The relative efficiency of the proposed model has been studied with respect to the Singh (2010 Singh, S. (2010). Proposed optimal orthogonal new additive model (POONAM). Statistica. Anno LXX(1):73–81. [Google Scholar]) model. Numerical illustrations are also given in support of the present study.     

Sequential order statistics from dependent random variables

Abstract

This paper provides an extension for “sequential order statistics” (SOS) introduced by Kamps. It is called “developed sequential order statistics” (DSOS) and is useful for describing lifetimes of engineering systems when component lifetimes are dependent. Explicit expressions for the joint density function, the marginal distributions and the means of DSOS are derived. Under the well known “conditional proportional hazard rate” (CPHR) model and the Gumbel families of copulas for dependency among component lifetimes, some findings are reported. For example, it is proved that the joint density functions of DSOS and SOS have the same structure. Various illustrative examples are also given.     

A note on stratification and gain in precision in estimating diversity from large samples

Several indices of entropy have been suggested in the literature as weighted diversity measures of a population with respect to a classification process. Among them, Shannon's entropy and Havrda -Charvát's non-additive entropies of order a, have been exhaustively used.

When the population is finite but too large to be censused, the diversity with respect to a given classification process must be estimated from a sample.

In this note, on the basis of an asymptotic study of the sample indices in the stratified random sampling, we are going to confirm that when we deal with large samples one can guarantee a gain in precision from stratified random over simple random sampling. This gain becomes considerable when the ‘inaccuracy" (as intended by Kerridge and Rathie and Kannapan) between the frequency vector in each stratum and that in the whole population, varies greatly from stratum to stratum.