Many surveys of the U.S. household population are experiencing higher refusal rates. Nonresponse can, but need not, induce nonresponse bias in survey estimates. Recent empirical findings illustrate cases when the linkage between nonresponse rates and nonresponse biases is absent. Despite this, professional standards continue to urge high response rates. Statistical expressions of nonresponse bias can be translated into causal models to guide hypotheses about when nonresponse. causes bias. Alternative designs to measure nonresponse bias exist, providing different but incomplete information about the nature of the bias. A synthesis of research studies estimating nonresponse bias shows the bias often present. A logical question at this moment in history is what advantage probability sample surveys have if they suffer from high nonresponse rates. Since postsurvey adjustment for nonresponse requires auxiliary variables, the answer depends on the nature of the design and the quality of the auxiliary variables.

Nonresponse Rates and Nonresponse Bias in Household Surveys

It's been over a decade since the first edition of Measurement Error in Nonlinear Models splashed onto the scene, and research in the field has certainly not cooled in the interim. In fact, quite the opposite has occurred. As a result, Measurement Error in Nonlinear Models: A Modern Perspective, Second Edition has been revamped and ex

Measurement Error in Nonlinear Models: A Modern Perspective, Second Edition

SHARE is a unique panel database of micro data on health, socio-economic status and social and family networks covering most of the European Union and Israel. To date, SHARE has collected three panel waves (2004, 2006, 2010) of current living circumstances and retrospective life histories (2008, SHARELIFE); 6 additional waves are planned until 2024. The more than 150 000 interviews give a broad picture of life after the age of 50 years, measuring physical and mental health, economic and non-economic activities, income and wealth, transfers of time and money within and outside the family as well as life satisfaction and well-being. The data are available to the scientific community free of charge at www.share-project.org after registration. SHARE is harmonized with the US Health and Retirement Study (HRS) and the English Longitudinal Study of Ageing (ELSA) and has become a role model for several ageing surveys worldwide. SHARE's scientific power is based on its panel design that grasps the dynamic character of the ageing process, its multidisciplinary approach that delivers the full picture of individual and societal ageing, and its cross-nationally ex-ante harmonized design that permits international comparisons of health, economic and social outcomes in Europe and the USA.

/pdf/data-resource-profile-the-survey-of-health-ageing-and-4vt73isq8x.pdf

Data Resource Profile: The Survey of Health, Ageing and Retirement in Europe (SHARE)

We conducted a large nationwide postal survey to estimate the prevalence of chronic pain with or without neuropathic characteristics in the French general population. A questionnaire aimed at identifying chronic pain (defined as daily pain for at least 3 months), evaluating its intensity, duration and body locations, was sent to a representative sample of 30,155 subjects. The DN4 questionnaire was used to identify neuropathic characteristics. Of the questionnaires, 24,497 (81.2%) were returned and 23,712 (96.8%) could be assessed. Seven thousand five hundred and twenty-two respondents reported chronic pain (prevalence=31.7%; [95%CI: 31.1-32.3]) and 4709 said the pain intensity was moderate to severe (prevalence=19.9%; [95%CI: 19.5-20.4]). Neuropathic characteristics were reported by 1631 respondents with chronic pain (prevalence=6.9%; [95%CI: 6.6-7.2]), which was moderate to severe in 1209 (prevalence=5.1% [95%CI: 4.8-5.4]). A higher prevalence of chronic pain with neuropathic characteristics was associated with middle age (50-64 years), manual professions and those living in rural areas. It was more frequently located in the lower limbs and its intensity and duration were higher in comparison with chronic pain without neuropathic characteristics. This large national population-based study indicates that a significant proportion of chronic pain patients report neuropathic characteristics. We identified distinctive socio-demographic profile and clinical features indicating that chronic pain with neuropathic characteristics is a specific health problem.

/pdf/prevalence-of-chronic-pain-with-neuropathic-characteristics-1sscp7ap0z.pdf

Prevalence of chronic pain with neuropathic characteristics in the general population

Background The context in which patients consume health information has changed dramatically with diffusion of the Internet, advances in telemedicine, and changes in media health coverage. The objective of this study was to provide nationally representative estimates for health-related uses of the Internet, level of trust in health information sources, and preferences for cancer information sources. Methods Data from the Health Information National Trends Survey were used. A total of 6369 persons 18 years or older were studied. The main outcome measures were online health activities, levels of trust, and source preference. Results Analyses indicated that 63.0% (95% confidence interval [CI], 61.7%-64.3%) of the US adult population in 2003 reported ever going online, with 63.7% (95% CI, 61.7%-65.8%) of the online population having looked for health information for themselves or others at least once in the previous 12 months. Despite newly available communication channels, physicians remained the most highly trusted information source to patients, with 62.4% (95% CI, 60.8%-64.0%) of adults expressing a lot of trust in their physicians. When asked where they preferred going for specific health information, 49.5% (95% CI, 48.1%-50.8%) reported wanting to go to their physicians first. When asked where they actually went, 48.6% (95% CI, 46.1%-51.0%) reported going online first, with only 10.9% (95% CI, 9.5%-12.3%) going to their physicians first. Conclusion The Health Information National Trends Survey data portray a tectonic shift in the ways in which patients consume health and medical information, with more patients looking for information online before talking with their physicians.

https://jamanetwork.com/journals/jamainternalmedicine/articlepdf/766849/ioi50160.pdf

Trust and sources of health information: the impact of the Internet and its implications for health care providers: findings from the first Health Information National Trends Survey.

This article investigates estimation of finite population totals in the presence of univariate or multivariate auxiliary information. Estimation is equivalent to attaching weights to the survey data. We focus attention on the several weighting systems that can be associated with a given amount of auxiliary information and derive a weighting system with the aid of a distance measure and a set of calibration equations. We briefly mention an application to the case in which the information consists of known marginal counts in a two- or multi-way table, known as generalized raking. The general regression estimator (GREG) was conceived with multivariate auxiliary information in mind. Ordinarily, this estimator is justified by a regression relationship between the study variable y and the auxiliary vector x. But we note that the GREG can be derived by a different route by focusing instead on the weights. The ordinary sampling weights of the kth observation is 1/πk , where πk is the inclusion probabilit...

Calibration Estimators in Survey Sampling

We propose the name generalized raking for the class of procedures developed in this article, because the classical raking ratio of W. E. Deming is a special case. Generalized raking can be used for estimation in surveys with auxiliary information in the form of known marginal counts in a frequency table in two or more dimensions. An important property of the generalized raking weights is that they reproduce the known marginal counts when applied to the categorical variables that define the frequency table. Our starting point is a class of distance measures and a set of original weights in the form of the standard sampling weights 1/π k , where π k is the inclusion probability of element k. New weights are derived by minimizing the total distance between original weights and new weights. The article makes contributions in three areas: (1) statistical inference conditionally on estimated cell counts, (2) simple calculation of variance estimates for the generalized raking estimators, and (3) presen...

Generalized Raking Procedures in Survey Sampling

A balanced sampling design is defined by the property that the Horvitz-Thompson estimators of the population totals of a set of auxiliary variables equal the known totals of these variables. Therefore the variances of estimators of totals of all the variables of interest are reduced, depending on the correlations of these variables with the controlled variables. In this paper, we develop a general method, called the cube method, for selecting approximately balanced samples with equal or unequal inclusion probabilities and any number of auxiliary variables.

/pdf/efficient-balanced-sampling-the-cube-method-3p7kld5x2u.pdf

Efficient balanced sampling: The cube method

SUMMARY A very general class of sampling methods without replacement and with unequal probabilities is proposed. It consists of splitting the inclusion probability vector into several new inclusion probability vectors. One of these vectors is chosen randomly; thus, the initial problem is reduced to another sampling problem with unequal probabilities. This splitting is then repeated on these new vectors of inclusion probabilities; at each step, the sampling problem is reduced to a simpler problem. The simplicity of this technique allows one to generate easily new sampling procedures with unequal probabilities. The splitting method also generalises well-known methods such as the Midzuno method, the elimination procedure and the Chao procedure. Next, a sufficient condition is given in order that a splitting method satisfies the Sen-Yates-Grundy condition. Finally, it is shown that the elimination procedure satisfies the Gabler sufficient condition.

Unequal probability sampling without replacement through a splitting method

http://doc.rero.ch/record/261027/files/Deville_J-C.-Variance_approximation-20160624.pdf

Jean-Claude Deville

Papers

Calibration Estimators in Survey Sampling

Generalized Raking Procedures in Survey Sampling

Efficient balanced sampling: The cube method

Unequal probability sampling without replacement through a splitting method

Variance approximation under balanced sampling