Estimation of sensitive data from a dichotomous population

This paper considers the problem of estimating the population proportion when the study variable is sensitive in nature. Two implicit unrelated question procedures are proposed, in which the unrelated character used can be chosen arbitrarily. In addition to unbiasedly estimating population proportion and variance, an empirical study is also carried out to examine the relative efficiency aspect of the proposed procedures. The new procedures are shown to be more efficient than the usual randomized response procedures.     

Improved inference on capture recapture models with behavioural effects

In the context of capture-recapture modeling for estimating the unknown size of a finite population it is often required a flexible framework for dealing with a behavioural response to trapping. Many alternative settings have been proposed in the literature to account for the variation of capture probability at each occasion depending on the previous capture history. Inference is typically carried out relying on the so-called conditional likelihood approach. We highlight that such approach may, with positive probability, lead to inferential pathologies such as unbounded estimates for the finite size of the population. The occurrence of such likelihood failures is characterized within a very general class of behavioural effect models. It is also pointed out that a fully Bayesian analysis overcomes the likelihood failure phenomenon. The overall improved performance of alternative Bayesian estimators is investigated under different non-informative prior distributions verifying their comparative merits with both simulated and real data.     

A SEMIPARAMETRIC MODEL FOR A FUNCTIONAL BEHAVIOURAL RESPONSE TO CAPTURE IN CAPTURE–RECAPTURE EXPERIMENTS

Capture–recapture experiments are commonly used to estimate the size of a closed population. However, the associated estimators of the population size are well known to be highly sensitive to misspecification of the capture probabilities. To address this, we present a general semiparametric framework for the analysis of capture–recapture experiments when the capture probability depends on individual characteristics, time effects and behavioural response. This generalizes well‐known general parametric capture–recapture models and extends previous semiparametric models in which there is no time dependence or behavioural response. The method is evaluated in simulations and applied to two real data sets.     

Estimation of the population mean and median using truncation-based ranked set samples

In this paper, a new sampling method is suggested, namely truncation-based ranked set samples (TBRSS) for estimating the population mean and median. The suggested method is compared with the simple random sampling (SRS), ranked set sampling (RSS), extreme ranked set sampling (ERSS) and median-ranked set sampling (MRSS) methods. It is shown that for estimating the population mean when the underlying distribution is symmetric, TBRSS estimator is unbiased and it is more efficient than the SRS estimator based on the same number of measured units. For asymmetric distributions considered in this study, TBRSS estimator is more efficient than the SRS for all considered distributions except for exponential distribution when the selection coefficient gets large. When compared with ERSS and MRSS methods, TBRSS performs well with respect to ERSS for all considered distributions except for U(0, 1) distribution, while TBRSS efficiency is higher than that of MRSS for U(0, 1) distribution. For estimating the population median, the TBRSS estimators have higher efficiencies when compared with SRS and ERSS. A real data set is used to illustrate the suggested method.     

Efficient estimation of population mean of sensitive variable in presence of scrambled responses

This paper addresses the problem of estimating the population mean of a sensitive variable in presence of scrambled response. We have suggested a randomized response model which uses known values of mean and variance of scrambling variable. We have shown that the proposed randomized response model is always better than that of Gjestvang and Singh's (2009) and Singh and Tarray's (2014) randomized response models. A numerical study for efficiency comparison is also presented.     

Inverse Adaptive Cluster Sampling with Unequal Selection Probabilities: Case Studies on Crab Holes and Arsenic Pollution

Adaptive cluster sampling is an efficient method of estimating the parameters of rare and clustered populations. The method mimics how biologists would like to collect data in the field by targeting survey effort to localised areas where the rare population occurs. Another popular sampling design is inverse sampling. Inverse sampling was developed so as to be able to obtain a sample of rare events having a predetermined size. Ideally, in inverse sampling, the resultant sample set will be sufficiently large to ensure reliable estimation of population parameters. In an effort to combine the good properties of these two designs, adaptive cluster sampling and inverse sampling, we introduce inverse adaptive cluster sampling with unequal selection probabilities. We develop an unbiased estimator of the population total that is applicable to data obtained from such designs. We also develop numerical approximations to this estimator. The efficiency of the estimators that we introduce is investigated through simulation studies based on two real populations: crabs in Al Khor, Qatar and arsenic pollution in Kurdistan, Iran. The simulation results show that our estimators are efficient.     

Calibrated Estimators of Population Mean for a Mail Survey Design

In this article, we consider the problem of estimating the population mean of a study variable in the presence of non-response in a mail survey design. We introduce calibrated estimators of the population mean of a study variable in the presence of a known auxiliary variable. Using simulation the proposed calibrated estimators of population mean are compared to the Hansen and Hurwitz (1946) estimator under different situations for fixed cost as well for fixed sample size. The results are then extended for the use of multi-auxiliary information and stratified random sampling. We consider the problem of estimating the average total family income in the US in the presence of known auxiliary information on total income per person, age of the person, and poverty. We compute the relative efficiency of the proposed estimator over the Hansen and Hurwitz (1946) estimator through the use of large real datasets. Results are also presented for sub-populations consisting of whites, blacks, others, and two or more races in addition to considering them together in a population.     

Finding the maximum efficiency for multistage ranked-set sampling

Multistage ranked-set sampling (MRSS) is a generalization of ranked-set sampling in which multiple stages of ranking are used. It is known that for a fixed distribution under perfect rankings, each additional stage provides a gain in efficiency when estimating the population mean. However, the maximum possible efficiency for the MRSS sample mean relative to the simple random sampling sample mean has not previously been determined. In this paper, we provide a method for computing this maximum possible efficiency under perfect rankings for any choice of the set size and the number of stages. The maximum efficiency tends to infinity as the number of stages increases, and, for large numbers of stages, the efficiency-maximizing distributions are symmetric multi-modal distributions where the number of modes matches the set size. The results in this paper correct earlier assertions in the literature that the maximum efficiency is bounded and that it is achieved when the distribution is uniform.     

Effect of plant-capture in a capture-recapture experiment

An efficiency study is made of a plant-capture approach for estimating population size in recapture studies. The population is augmented by the insertion of a known number of planted individuals who have already been marked and whose behaviour is identical to that of other members. A comparison is made with the case where no plants are used by considering asymptotic efficiency and a simulation study.     

Some Strategies of Two-Stage Sampling for Estimating Population Ratios Over two Occasions

In this paper strategies based on a two-stage successive sampling scheme are proposed for estimating the ratio of the population totals of two characters on the most recent occasion. It is found that the proposed strategies perform better than the standard ratio when used in estimating the ratio of farmers' income to non-farmers' income. But when applied to the estimation of ratio of girth to height of teak trees, a loss in efficiency is observed.     

Nonlinear regression analysis for complex surveys 1

In a clustered finite population, it is assumed that a given function depending on an unknown parameter may be adopted to reveal the relationship among the variables of interest. The finite population parameter corresponding to this unknown parameter is defined as a solution of an estimating equation defined by a properly chosen population loss function. An estimation procedure that takes sample weights into account is considered. Use of this function in estimating the population mean per cluster is discussed. Large sample properties of estimators are investigated.     

On the estimation of homogeneous population size from a complex dual-record system

ABSTRACT

A dual-record system (DRS) (equivalently two sample capture–recapture experiments) model, with time and behavioural response variation, has attracted much attention specifically in the domain of official statistics and epidemiology, as the assumption of list independence often fails. The relevant model suffers from parameter identifiability problem, and suitable Bayesian methodologies could be helpful. In this article, we formulate population size estimation in DRS as a missing data problem and two empirical Bayes approaches are proposed along with the discussion of an existing Bayes treatment. Some features and associated posterior convergence for these methods are mentioned. Investigation through an extensive simulation study finds that our proposed approaches compare favourably with the existing Bayes approach for this complex model depending upon the availability of directional nature of underlying behavioural response effect. A real-data example is given to illustrate these methods.     

Utilization of higher order moments of scrambling variables in randomized response sampling

In this paper, a new estimator for estimating the proportion of a potentially sensitive attribute in survey sampling has been introduced. The proposed estimator makes use of higher order moments of the scrambling variable at the estimation stage. The proposed estimator has been found to be more efficient than the estimator due to Kuk [1990. Asking sensitive questions indirectly. Biomerika 77(2), 436–438] and Franklin [1989. A comparison of estimators for randomized response sampling with continuous distributions from a dichotomous population. Comm. Statist. Theory Methods 18, 489–505] type estimators in randomized response sampling. Recently, Guerriero and Sandri [2007. A note on the comparison of some randomized response procedures. J. Statist. Plann. Inference 137, 2184–2190] have shown that the family of randomized response models proposed by Kuk [1990. Asking sensitive questions indirectly. Biomerika 77(2), 436–438] is better than the Simmons’ family in terms of efficiency and protection.     

Variance estimation in model assisted survey sampling

Two versions of Yates-Grundy type variance estimators are usually employed for large samples when estimating a survey population total by a generalized regression (Greg, in brief) predictor motivated by consideration of a linear regression model. Their two alternative modifications are developed so that the limiting values of the design expectations of the model expectations of variance estimators 'match' respectively the (I) model expectations of the Taylor approximation of the design variance of the Greg predictor and the (II) limiting value of the design expectation of the model expectation of the squared difference between the Greg predictor and the population total. The exercise is extended to yield modifications needed when randomized response (RR) is only available rather than direct response (DR) when one encounters sensitive issues demanding protection of privacy. A comparative study based on simulation is presented for illustration..     

An efficient randomized response model utilizing higher order moments ratios of scrambling variables

In this paper, we have 89 suggested an improved randomized response (RR) model for estimating π, the proportion of respondents in the population belonging to the sensitive group. We have studied the properties of the RR model. The proposed model is found to be more efficient than the RR model studied by Gjestvang and Singh (2006). Numerical illustration is given in support of the present study.     

On a criterion for evaluating an estimator

A criterion for evaluating an estimator of the mean μ of a population is studied. The criterion considered is that the estimator be within a units of μ a large percentage (say, (1-β) 100%) of the time. This is referred to as the α -β criterion for estimating μ. A variation of this criterion is also studied.     

Estimation of bivariate characteristics using ranked set sampling

The superiority of ranked set sampling (RSS) over simple random sampling (SRS) for estimating the mean of a population is well known. This paper introduces and investigates a bivariate version of RSS for estimating the means of two characteristics simultaneously. It turns out that this technique is always superior to SRS and the usual univariate RSS of the same size. The performance of this procedure for a specific distribution can be evaluated using simulation or numerical computation. For the bivariate normal distribution, the efficiency of the procedure with respect to that of SRS is evaluated exactly for set size m = 2 and 3. The paper shows that the proposed estimator is more efficient than the regression RSS estimators proposed by Yu & Lam (1997) and Chen (2001). Real data that consist of heights and diameters of 399 trees are used to illustrate the procedure. The procedure can be generalized to the case of multiple characteristics.     

Comparison of estimation methods for the finite population mean in simple random sampling: symmetric super-populations

In this paper, a new estimator combined estimator (CE) is proposed for estimating the finite population mean ¯ Y _N in simple random sampling assuming a long-tailed symmetric super-population model. The efficiency and robustness properties of the CE is compared with the widely used and well-known estimators of the finite population mean ¯ Y _N by Monte Carlo simulation. The parameter estimators considered in this study are the classical least squares estimator, trimmed mean, winsorized mean, trimmed L-mean, modified maximum-likelihood estimator, Huber estimator (W24) and the non-parametric Hodges–Lehmann estimator. The mean square error criteria are used to compare the performance of the estimators. We show that the CE is overall more efficient than the other estimators. The CE is also shown to be more robust for estimating the finite population mean ¯ Y _N , since it is insensitive to outliers and to misspecification of the distribution. We give a real life example.     

ASYMPTOTIC PROPERTIES OF AN OPTIMAL ESTIMATING FUNCTION APPROACH TO THE ANALYSIS OF MARK RECAPTURE DATA

ABSTRACT

A drawback of non parametric estimators of the size of a closed population in the presence of heterogeneous capture probabilities has been their lack of analytic tractability. Here we show that the martingale estimating function/sample coverage approach to estimating the size of a closed population with heterogeneous capture probabilities is mathematically tractable and develop its large sample properties.     

Estimation of sensitivity level of personal interview survey questions

In this paper, an optional randomized response model is proposed. The estimator of the mean of the stigmatized variable based on the optional randomized response sampling is shown to be more efficient than the usual estimator of the mean based on randomized response technique method. In addition to estimating population mean and variance, it has been shown that the optional randomized response technique is useful in quantifying the sensitivity levels of the questions in the personal interview surveys. An estimator for the sensitivity level of a question is proposed and an empirical study is carried out to show the validity of the proposed estimation technique. We also propose a test for the sensitivity level of the stigmatized variable.