Inference and foundations

Skip to main content
Skip to footer

Language selection

Français

Search and menus

Search and menus

Search

Skip to filters. View results.

Results

All (105)

All (105) (40 to 50 of 105 results)

41. Bayesian inference for finite population quantiles from unequal probability samples Archived
Articles and reports: 12-001-X201200211758
Description:
This paper develops two Bayesian methods for inference about finite population quantiles of continuous survey variables from unequal probability sampling. The first method estimates cumulative distribution functions of the continuous survey variable by fitting a number of probit penalized spline regression models on the inclusion probabilities. The finite population quantiles are then obtained by inverting the estimated distribution function. This method is quite computationally demanding. The second method predicts non-sampled values by assuming a smoothly-varying relationship between the continuous survey variable and the probability of inclusion, by modeling both the mean function and the variance function using splines. The two Bayesian spline-model-based estimators yield a desirable balance between robustness and efficiency. Simulation studies show that both methods yield smaller root mean squared errors than the sample-weighted estimator and the ratio and difference estimators described by Rao, Kovar, and Mantel (RKM 1990), and are more robust to model misspecification than the regression through the origin model-based estimator described in Chambers and Dunstan (1986). When the sample size is small, the 95% credible intervals of the two new methods have closer to nominal confidence coverage than the sample-weighted estimator.
Release date: 2012-12-19
42. A hierarchical Bayesian nonresponse model for two-way categorical data from small areas with uncertainty about ignorability Archived
Articles and reports: 12-001-X201200111688
Description:
We study the problem of nonignorable nonresponse in a two dimensional contingency table which can be constructed for each of several small areas when there is both item and unit nonresponse. In general, the provision for both types of nonresponse with small areas introduces significant additional complexity in the estimation of model parameters. For this paper, we conceptualize the full data array for each area to consist of a table for complete data and three supplemental tables for missing row data, missing column data, and missing row and column data. For nonignorable nonresponse, the total cell probabilities are allowed to vary by area, cell and these three types of "missingness". The underlying cell probabilities (i.e., those which would apply if full classification were always possible) for each area are generated from a common distribution and their similarity across the areas is parametrically quantified. Our approach is an extension of the selection approach for nonignorable nonresponse investigated by Nandram and Choi (2002a, b) for binary data; this extension creates additional complexity because of the multivariate nature of the data coupled with the small area structure. As in that earlier work, the extension is an expansion model centered on an ignorable nonresponse model so that the total cell probability is dependent upon which of the categories is the response. Our investigation employs hierarchical Bayesian models and Markov chain Monte Carlo methods for posterior inference. The models and methods are illustrated with data from the third National Health and Nutrition Examination Survey.
Release date: 2012-06-27
43. Modelling of complex survey data: Why model? Why is it a problem? How can we approach it? Archived
Articles and reports: 12-001-X201100211602
Description:
This article attempts to answer the three questions appearing in the title. It starts by discussing unique features of complex survey data not shared by other data sets, which require special attention but suggest a large variety of diverse inference procedures. Next a large number of different approaches proposed in the literature for handling these features are reviewed with discussion on their merits and limitations. The approaches differ in the conditions underlying their use, additional data required for their application, goodness of fit testing, the inference objectives that they accommodate, statistical efficiency, computational demands, and the skills required from analysts fitting the model. The last part of the paper presents simulation results, which compare the approaches when estimating linear regression coefficients from a stratified sample in terms of bias, variance, and coverage rates. It concludes with a short discussion of pending issues.
Release date: 2011-12-21
44. A Bayesian analysis of small area probabilities under a constraint Archived
Articles and reports: 12-001-X201100211603
Description:
In many sample surveys there are items requesting binary response (e.g., obese, not obese) from a number of small areas. Inference is required about the probability for a positive response (e.g., obese) in each area, the probability being the same for all individuals in each area and different across areas. Because of the sparseness of the data within areas, direct estimators are not reliable, and there is a need to use data from other areas to improve inference for a specific area. Essentially, a priori the areas are assumed to be similar, and a hierarchical Bayesian model, the standard beta-binomial model, is a natural choice. The innovation is that a practitioner may have much-needed additional prior information about a linear combination of the probabilities. For example, a weighted average of the probabilities is a parameter, and information can be elicited about this parameter, thereby making the Bayesian paradigm appropriate. We have modified the standard beta-binomial model for small areas to incorporate the prior information on the linear combination of the probabilities, which we call a constraint. Thus, there are three cases. The practitioner (a) does not specify a constraint, (b) specifies a constraint and the parameter completely, and (c) specifies a constraint and information which can be used to construct a prior distribution for the parameter. The griddy Gibbs sampler is used to fit the models. To illustrate our method, we use an example on obesity of children in the National Health and Nutrition Examination Survey in which the small areas are formed by crossing school (middle, high), ethnicity (white, black, Mexican) and gender (male, female). We use a simulation study to assess some of the statistical features of our method. We have shown that the gain in precision beyond (a) is in the order with (b) larger than (c).
Release date: 2011-12-21
45. Small area estimation under transformation to linearity Archived
Articles and reports: 12-001-X201100111446
Description:
Small area estimation based on linear mixed models can be inefficient when the underlying relationships are non-linear. In this paper we introduce SAE techniques for variables that can be modelled linearly following a non-linear transformation. In particular, we extend the model-based direct estimator of Chandra and Chambers (2005, 2009) to data that are consistent with a linear mixed model in the logarithmic scale, using model calibration to define appropriate weights for use in this estimator. Our results show that the resulting transformation-based estimator is both efficient and robust with respect to the distribution of the random effects in the model. An application to business survey data demonstrates the satisfactory performance of the method.
Release date: 2011-06-29
46. The use of estimating equations to perform a calibration on complex parameters Archived
Articles and reports: 12-001-X201100111451
Description:
In the calibration method proposed by Deville and Särndal (1992), the calibration equations take only exact estimates of auxiliary variable totals into account. This article examines other parameters besides totals for calibration. Parameters that are considered complex include the ratio, median or variance of auxiliary variables.
Release date: 2011-06-29
47. Bayesian penalized spline model-based inference for finite population proportion in unequal probability sampling Archived
Articles and reports: 12-001-X201000111250
Description:
We propose a Bayesian Penalized Spline Predictive (BPSP) estimator for a finite population proportion in an unequal probability sampling setting. This new method allows the probabilities of inclusion to be directly incorporated into the estimation of a population proportion, using a probit regression of the binary outcome on the penalized spline of the inclusion probabilities. The posterior predictive distribution of the population proportion is obtained using Gibbs sampling. The advantages of the BPSP estimator over the Hájek (HK), Generalized Regression (GR), and parametric model-based prediction estimators are demonstrated by simulation studies and a real example in tax auditing. Simulation studies show that the BPSP estimator is more efficient, and its 95% credible interval provides better confidence coverage with shorter average width than the HK and GR estimators, especially when the population proportion is close to zero or one or when the sample is small. Compared to linear model-based predictive estimators, the BPSP estimators are robust to model misspecification and influential observations in the sample.
Release date: 2010-06-29
48. Pseudo empirical likelihood inference for multiple surveys and multiple-frame surveys Archived
Articles and reports: 11-536-X200900110806
Description:
Recent work using a pseudo empirical likelihood (EL) method for finite population inferences with complex survey data focused primarily on a single survey sample, non-stratified or stratified, with considerable effort devoted to computational procedures. In this talk we present a pseudo empirical likelihood approach to inference from multiple surveys and multiple-frame surveys, two commonly encountered problems in survey practice. We show that inferences about the common parameter of interest and the effective use of various types of auxiliary information can be conveniently carried out through the constrained maximization of joint pseudo EL function. We obtain asymptotic results which are used for constructing the pseudo EL ratio confidence intervals, either using a chi-square approximation or a bootstrap calibration. All related computational problems can be handled using existing algorithms on stratified sampling after suitable re-formulation.
Release date: 2009-08-11
49. A Bayesian allocation of undecided voters Archived
Articles and reports: 12-001-X200800110606
Description:
Data from election polls in the US are typically presented in two-way categorical tables, and there are many polls before the actual election in November. For example, in the Buckeye State Poll in 1998 for governor there are three polls, January, April and October; the first category represents the candidates (e.g., Fisher, Taft and other) and the second category represents the current status of the voters (likely to vote and not likely to vote for governor of Ohio). There is a substantial number of undecided voters for one or both categories in all three polls, and we use a Bayesian method to allocate the undecided voters to the three candidates. This method permits modeling different patterns of missingness under ignorable and nonignorable assumptions, and a multinomial-Dirichlet model is used to estimate the cell probabilities which can help to predict the winner. We propose a time-dependent nonignorable nonresponse model for the three tables. Here, a nonignorable nonresponse model is centered on an ignorable nonresponse model to induce some flexibility and uncertainty about ignorabilty or nonignorability. As competitors we also consider two other models, an ignorable and a nonignorable nonresponse model. These latter two models assume a common stochastic process to borrow strength over time. Markov chain Monte Carlo methods are used to fit the models. We also construct a parameter that can potentially be used to predict the winner among the candidates in the November election.
Release date: 2008-06-26
50. Robust Bayesian predictive inference for the finite population quantile of a small area Archived
Articles and reports: 11-522-X200600110392
Description:
We use a robust Bayesian method to analyze data with possibly nonignorable nonresponse and selection bias. A robust logistic regression model is used to relate the response indicators (Bernoulli random variable) to the covariates, which are available for everyone in the finite population. This relationship can adequately explain the difference between respondents and nonrespondents for the sample. This robust model is obtained by expanding the standard logistic regression model to a mixture of Student's distributions, thereby providing propensity scores (selection probability) which are used to construct adjustment cells. The nonrespondents' values are filled in by drawing a random sample from a kernel density estimator, formed from the respondents' values within the adjustment cells. Prediction uses a linear spline rank-based regression of the response variable on the covariates by areas, sampling the errors from another kernel density estimator; thereby further robustifying our method. We use Markov chain Monte Carlo (MCMC) methods to fit our model. The posterior distribution of a quantile of the response variable is obtained within each sub-area using the order statistic over all the individuals (sampled and nonsampled). We compare our robust method with recent parametric methods
Release date: 2008-03-17

Data (0)

Data (0) (0 results)

No content available at this time.

Analysis (97)

Analysis (97) (20 to 30 of 97 results)

21. Replication variance estimation after sample-based calibration
Articles and reports: 12-001-X202100200006
Description:
Sample-based calibration occurs when the weights of a survey are calibrated to control totals that are random, instead of representing fixed population-level totals. Control totals may be estimated from different phases of the same survey or from another survey. Under sample-based calibration, valid variance estimation requires that the error contribution due to estimating the control totals be accounted for. We propose a new variance estimation method that directly uses the replicate weights from two surveys, one survey being used to provide control totals for calibration of the other survey weights. No restrictions are set on the nature of the two replication methods and no variance-covariance estimates need to be computed, making the proposed method straightforward to implement in practice. A general description of the method for surveys with two arbitrary replication methods with different numbers of replicates is provided. It is shown that the resulting variance estimator is consistent for the asymptotic variance of the calibrated estimator, when calibration is done using regression estimation or raking. The method is illustrated in a real-world application, in which the demographic composition of two surveys needs to be harmonized to improve the comparability of the survey estimates.
Release date: 2022-01-06
22. Are probability surveys bound to disappear for the production of official statistics?
Articles and reports: 12-001-X202000100001
Description:
For several decades, national statistical agencies around the world have been using probability surveys as their preferred tool to meet information needs about a population of interest. In the last few years, there has been a wind of change and other data sources are being increasingly explored. Five key factors are behind this trend: the decline in response rates in probability surveys, the high cost of data collection, the increased burden on respondents, the desire for access to “real-time” statistics, and the proliferation of non-probability data sources. Some people have even come to believe that probability surveys could gradually disappear. In this article, we review some approaches that can reduce, or even eliminate, the use of probability surveys, all the while preserving a valid statistical inference framework. All the approaches we consider use data from a non-probability source; data from a probability survey are also used in most cases. Some of these approaches rely on the validity of model assumptions, which contrasts with approaches based on the probability sampling design. These design-based approaches are generally not as efficient; yet, they are not subject to the risk of bias due to model misspecification.
Release date: 2020-06-30
23. Small area estimation for unemployment using latent Markov models Archived
Articles and reports: 12-001-X201800254956
Description:
In Italy, the Labor Force Survey (LFS) is conducted quarterly by the National Statistical Institute (ISTAT) to produce estimates of the labor force status of the population at different geographical levels. In particular, ISTAT provides LFS estimates of employed and unemployed counts for local Labor Market Areas (LMAs). LMAs are 611 sub-regional clusters of municipalities and are unplanned domains for which direct estimates have overly large sampling errors. This implies the need of Small Area Estimation (SAE) methods. In this paper, we develop a new area level SAE method that uses a Latent Markov Model (LMM) as linking model. In LMMs, the characteristic of interest, and its evolution in time, is represented by a latent process that follows a Markov chain, usually of first order. Therefore, areas are allowed to change their latent state across time. The proposed model is applied to quarterly data from the LFS for the period 2004 to 2014 and fitted within a hierarchical Bayesian framework using a data augmentation Gibbs sampler. Estimates are compared with those obtained by the classical Fay-Herriot model, by a time-series area level SAE model, and on the basis of data coming from the 2011 Population Census.
Release date: 2018-12-20
24. Investigating alternative estimators for the prevalence of serious mental illness based on a two-phase sample Archived
Articles and reports: 12-001-X201800154928
Description:
A two-phase process was used by the Substance Abuse and Mental Health Services Administration to estimate the proportion of US adults with serious mental illness (SMI). The first phase was the annual National Survey on Drug Use and Health (NSDUH), while the second phase was a random subsample of adult respondents to the NSDUH. Respondents to the second phase of sampling were clinically evaluated for serious mental illness. A logistic prediction model was fit to this subsample with the SMI status (yes or no) determined by the second-phase instrument treated as the dependent variable and related variables collected on the NSDUH from all adults as the model’s explanatory variables. Estimates were then computed for SMI prevalence among all adults and within adult subpopulations by assigning an SMI status to each NSDUH respondent based on comparing his (her) estimated probability of having SMI to a chosen cut point on the distribution of the predicted probabilities. We investigate alternatives to this standard cut point estimator such as the probability estimator. The latter assigns an estimated probability of having SMI to each NSDUH respondent. The estimated prevalence of SMI is the weighted mean of those estimated probabilities. Using data from NSDUH and its subsample, we show that, although the probability estimator has a smaller mean squared error when estimating SMI prevalence among all adults, it has a greater tendency to be biased at the subpopulation level than the standard cut point estimator.
Release date: 2018-06-21
25. A note on Wilson coverage intervals for proportions estimated from complex samples Archived
Articles and reports: 12-001-X201700254872
Description:
This note discusses the theoretical foundations for the extension of the Wilson two-sided coverage interval to an estimated proportion computed from complex survey data. The interval is shown to be asymptotically equivalent to an interval derived from a logistic transformation. A mildly better version is discussed, but users may prefer constructing a one-sided interval already in the literature.
Release date: 2017-12-21
26. Bayesian predictive inference of a proportion under a two-fold small area model with heterogeneous correlations Archived
Articles and reports: 12-001-X201700114822
Description:
We use a Bayesian method to infer about a finite population proportion when binary data are collected using a two-fold sample design from small areas. The two-fold sample design has a two-stage cluster sample design within each area. A former hierarchical Bayesian model assumes that for each area the first stage binary responses are independent Bernoulli distributions, and the probabilities have beta distributions which are parameterized by a mean and a correlation coefficient. The means vary with areas but the correlation is the same over areas. However, to gain some flexibility we have now extended this model to accommodate different correlations. The means and the correlations have independent beta distributions. We call the former model a homogeneous model and the new model a heterogeneous model. All hyperparameters have proper noninformative priors. An additional complexity is that some of the parameters are weakly identified making it difficult to use a standard Gibbs sampler for computation. So we have used unimodal constraints for the beta prior distributions and a blocked Gibbs sampler to perform the computation. We have compared the heterogeneous and homogeneous models using an illustrative example and simulation study. As expected, the two-fold model with heterogeneous correlations is preferred.
Release date: 2017-06-22
27. A note on the concept of invariance in two-phase sampling designs Archived
Articles and reports: 12-001-X201600214662
Description:
Two-phase sampling designs are often used in surveys when the sampling frame contains little or no auxiliary information. In this note, we shed some light on the concept of invariance, which is often mentioned in the context of two-phase sampling designs. We define two types of invariant two-phase designs: strongly invariant and weakly invariant two-phase designs. Some examples are given. Finally, we describe the implications of strong and weak invariance from an inference point of view.
Release date: 2016-12-20
28. A short note on quantile and expectile estimation in unequal probability samples Archived
Articles and reports: 12-001-X201600114545
Description:
The estimation of quantiles is an important topic not only in the regression framework, but also in sampling theory. A natural alternative or addition to quantiles are expectiles. Expectiles as a generalization of the mean have become popular during the last years as they not only give a more detailed picture of the data than the ordinary mean, but also can serve as a basis to calculate quantiles by using their close relationship. We show, how to estimate expectiles under sampling with unequal probabilities and how expectiles can be used to estimate the distribution function. The resulting fitted distribution function estimator can be inverted leading to quantile estimates. We run a simulation study to investigate and compare the efficiency of the expectile based estimator.
Release date: 2016-06-22
29. Methodological Challenges in Official Statistics Archived
Articles and reports: 11-522-X201700014704
Description:
We identify several research areas and topics for methodological research in official statistics. We argue why these are important, and why these are the most important ones for official statistics. We describe the main topics in these research areas and sketch what seems to be the most promising ways to address them. Here we focus on: (i) Quality of National accounts, in particular the rate of growth of GNI (ii) Big data, in particular how to create representative estimates and how to make the most of big data when this is difficult or impossible. We also touch upon: (i) Increasing timeliness of preliminary and final statistical estimates (ii) Statistical analysis, in particular of complex and coherent phenomena. These topics are elements in the present Strategic Methodological Research Program that has recently been adopted at Statistics Netherlands
Release date: 2016-03-24
30. Big Data: A Survey Research Perspective Archived
Articles and reports: 11-522-X201700014713
Description:
Big data is a term that means different things to different people. To some, it means datasets so large that our traditional processing and analytic systems can no longer accommodate them. To others, it simply means taking advantage of existing datasets of all sizes and finding ways to merge them with the goal of generating new insights. The former view poses a number of important challenges to traditional market, opinion, and social research. In either case, there are implications for the future of surveys that are only beginning to be explored.
Release date: 2016-03-24

Reference (8)

Reference (8) ((8 results))

No content available at this time.

Report a problem or mistake on this page

Date modified:: 2024-09-18