Improving the Efficiency of Inferences From Hybrid Samples for Effective Health Surveillance Surveys: Comprehensive Review of Quantitative Methods.

BACKGROUND: Increasingly, survey researchers rely on hybrid samples to improve coverage and increase the number of respondents by combining independent samples. For instance, it is possible to combine 2 probability samples with one relying on telephone and another on mail. More commonly, however, researchers are now supplementing probability samples with those from online panels that are less costly. Setting aside ad hoc approaches that are void of rigor, traditionally, the method of composite estimation has been used to blend results from different sample surveys. This means individual point estimates from different surveys are pooled together, 1 estimate at a time. Given that for a typical study many estimates must be produced, this piecemeal approach is computationally burdensome and subject to the inferential limitations of the individual surveys that are used in this process. OBJECTIVE: In this paper, we will provide a comprehensive review of the traditional method of composite estimation. Subsequently, the method of composite weighting is introduced, which is significantly more efficient, both computationally and inferentially when pooling data from multiple surveys. With the growing interest in hybrid sampling alternatives, we hope to offer an accessible methodology for improving the efficiency of inferences from such sample surveys without sacrificing rigor. METHODS: Specifically, we will illustrate why the many ad hoc procedures for blending survey data from multiple surveys are void of scientific integrity and subject to misleading inferences. Moreover, we will demonstrate how the traditional approach of composite estimation fails to offer a pragmatic and scalable solution in practice. By relying on theoretical and empirical justifications, in contrast, we will show how our proposed methodology of composite weighting is both scientifically sound and inferentially and computationally superior to the old method of composite estimation. RESULTS: Using data from 3 large surveys that have relied on hybrid samples composed of probability-based and supplemental sample components from online panels, we illustrate that our proposed method of composite weighting is superior to the traditional method of composite estimation in 2 distinct ways. Computationally, it is vastly less demanding and hence more accessible for practitioners. Inferentially, it produces more efficient estimates with higher levels of external validity when pooling data from multiple surveys. CONCLUSIONS: The new realities of the digital age have brought about a number of resilient challenges for survey researchers, which in turn have exposed some of the inefficiencies associated with the traditional methods this community has relied upon for decades. The resilience of such challenges suggests that piecemeal approaches that may have limited applicability or restricted accessibility will prove to be inadequate and transient. It is from this perspective that our proposed method of composite weighting has aimed to introduce a durable and accessible solution for hybrid sample surveys.

Design and operation of the National Asthma Survey.

OBJECTIVES: This report presents detailed information on the National Asthma Survey (NAS), a module of the State and Local Area Integrated Survey program conducted by the Centers for Disease Control and Prevention's (CDC) National Center for Health Statistics. NAS, sponsored by the CDC's National Center for Environmental Health, was designed to produce national prevalence estimates of adults and children with asthma; to describe the health, socioeconomic, behavioral, and environmental predictors that relate to controlling asthma better; and to characterize the content of care and limitations of persons with asthma. National prevalence estimates were constructed to be consistent with those produced from the CDC's National Health Interview Survey (NHIS), although prevalence estimates for subpopulations may or may not be consistent with NHIS. METHODS: Two separate random-digit-dial telephone studies were fielded: a national study and a four-state study in Alabama, California, Illinois, and Texas. Children aged 0-17 years and adults aged 18 years and over were included in both studies. The screening procedure differed between the studies. Percentages can be generated for the four states combined or for each state separately. A substudy was conducted in the national study to examine the accuracy of proxy reports of asthma. RESULTS: Data were collected from February 2003 to March 2004. A total of 955 detailed asthma interviews were completed in the national study and 5,741 in the four-state study. A data file has been released for each study that contains asthma, health, and demographic data, as well as sampling weights. The weighted overall response rates were 47.2% for the national sample and 48.5% for the four-state sample.

Common femoral artery stenosis after deployment of vascular clip closure device.

We describe a case of symptomatic common femoral artery stenosis following use of a vascular clip closure device (StarClose). Operative repair was performed, with removal of the clip device and subsequent vein patch angioplasty.

Address-based versus random-digit-dial surveys: comparison of key health and risk indicators.

Use of random-digit dialing (RDD) for conducting health surveys is increasingly problematic because of declining participation rates and eroding frame coverage. Alternative survey modes and sampling frames may improve response rates and increase the validity of survey estimates. In a 2005 pilot study conducted in six states as part of the Behavioral Risk Factor Surveillance System, the authors administered a mail survey to selected household members sampled from addresses in a US Postal Service database. The authors compared estimates based on data from the completed mail surveys (n = 3,010) with those from the Behavioral Risk Factor Surveillance System telephone surveys (n = 18,780). The mail survey data appeared reasonably complete, and estimates based on data from the two survey modes were largely equivalent. Differences found, such as differences in the estimated prevalences of binge drinking (mail = 20.3%, telephone = 13.1%) or behaviors linked to human immunodeficiency virus transmission (mail = 7.1%, telephone = 4.2%), were consistent with previous research showing that, for questions about sensitive behaviors, self-administered surveys generally produce higher estimates than interviewer-administered surveys. The mail survey also provided access to cell-phone-only households and households without telephones, which cannot be reached by means of standard RDD surveys.

Paclitaxel-eluting stents in coronary artery disease.

PURPOSE: Clinical information regarding paclitaxel-eluting coronary artery stents is reviewed. SUMMARY: Restenosis is a significant complication of percutaneous coronary intervention. Coronary artery stenting has reduced restenosis compared with traditional balloon angioplasty, although restenosis still occurs with bare-metal coronary artery stents. The pathogenesis of in-stent restenosis is believed to involve smooth-muscle-cell proliferation and migration in response to vessel injury. A neointimal layer of extracellular matrix and collagen forms, which may impinge on the vessel lumen. Paclitaxel inhibits vascular smooth-muscle-cell proliferation and reduces neointimal mass. Local delivery of paclitaxel through a coronary stent has been shown to reduce restenosis rates and percent diameter stenosis and to produce other angiographic benefits compared with bare-metal stents. Fewer major adverse coronary events are seen with paclitaxel-eluting stents, predominantly because of a reduction in the need for target-vessel revascularization with minimal impact on rates of mortality and myocardial infarction (MI). The Taxus Express(2) stent, the only approved paclitaxel-eluting stent in the United States, costs about three times as much as a bare-metal stent. Cost-effectiveness analyses are needed to determine if the Taxus stent is cost-effective in clinical practice. CONCLUSION: Paclitaxel-eluting stents reduce the rates of restenosis and target-vessel revascularization compared with bare-metal stents and have comparable effects on mortality and MI rates.

Design and Operation of the National Survey of Children's Health, 2003.

Objectives-This report presents the development, plan, and operation of the National Survey of Children's Health(NSCH), a module of the State and Local Area Integrated Telephone Survey, conducted by the Centers for Disease Control and Prevention's(CDC) National Center for Health Statistics. This survey was designed to produce national and State-specific prevalence estimates for a variety of physical, emotional, and behavioral health indicators and measures of children's experiences with the health care system. The survey also includes questions about the family (e.g., parents' health status, stress and coping behaviors, family activities) and about respondents' perceptions of the neighborhoods where their children live. Primary funding for this survey was provided by the Maternal and Child Health Bureau, Health Resources and Services Administration. Additional support was received from the CDC's National Center for Infectious Diseases, using funds provided by the National Vaccine Program Office. Methods-A random-digit-dial sample of households with children under 18 years of age was selected from each of the 50 States and the District of Columbia. One child was randomly selected from all children in each identified household to be the subject of the survey. The respondent was the parent or guardian who knew the most about the child's health and health care. Results-A total of 102,353 interviews were completed from January 2003 to July 2004. The weighted overall response rate was 55.3%. A data file has been released that contains demographic information on the selected child, substantive health and well-being data for the child and his/her family, and sampling weights. Estimates based on the sampling weights generalize to the noninstitutionalized population of children in each State and nationwide.

Pacemaker lead infection secondary to Haemophilus parainfluenzae.

Cardiac device infections are a rare complication of pacing and defibrillator therapy. The number of implanted devices will likely continue to rise with increasing implantation of the cardioverter defibrillator and cardiac resynchronization devices. This report describes a case of an uncommon pathogen for device-associated endocarditis.

Estimating the prevalence of uninsured children: an evaluation of data from the National Survey of Children with Special Health Care Needs, 2001. Data evaluation and methods research.

UNLABELLED: The National Survey of Children with Special Health Care Needs revealed that 8.3% of children under 18 years of age were uninsured, a rate lower than the rate estimated by other national surveys. This report presents the results of an evaluation of the quality of this estimate, based on analyses of non-response, question design, interviewer and respondent effects, and the weighing and estimation process. National and State-level statistics on health insurance coverage for children with special health care needs (CSHCN) and for children without special needs are included in an appendix. SOURCE OF DATA: The National Survey of CSHCN is a survey module of the State and Local Area Integrated Telephone Survey. This survey of parents and guardians collected health insurance coverage information for a national sample of 215, 162 children. Data were collected from October 2000 through April 2002. RESULTS: Compared with other surveys, weighted data from the National Survey of CSHCN describe a population with a slightly larger proportion of Hispanic children and children from households with higher incomes. The National Survey of CSHCN was also the only survey to use a child-level design: A randomized experiment that varied the health insurance questions found that repeating the coverage questions for each child produced lower unisurance rates than household-level questions that first asked if anyone in the househol was insured. CONCLUSION: Question design differences explain much of the discrepancy between survey estimates of the uninsurance rate, but a definitive conclusion regarding the relative accuracy of the uninsurance rates is not possible.

AIDS associated with severe cor pulmonale and large pericardial effusion with cardiac tamponade.

Cardiac involvement in patients with advanced HIV/AIDS is common, including pericardial effusion and pulmonary hypertension. Although there is an increased incidence of pericardial effusion in patients with AIDS, most are small and asymptomatic. The presence of a pericardial effusion and/or pulmonary hypertension is associated with shortened survival. We present a case of a 43-year-old man with AIDS and advanced cardiovascular involvement who developed severe cor pulmonale and a large pericardial effusion with cardiac tamponade.

The impact of touch-tone data entry on reports of HIV and STD risk behaviors in telephone interviews.

Respondents concerns about privacy can decrease reporting of HIV and STD risk behaviors in general population telephone surveys. The purpose of this paper is to describe the results of an experimental study evaluating whether one method for increasing privacy, touch-tone data entry (TTDE), is effective in increasing estimates of sexual behaviors from a population-based survey. We conducted a random-digit-dial telephone survey of adults in New Jersey (n = 405), with half the respondents using TTDE for answering sexual behavior questions. TTDE led to increased reports of same-sex sexual behavior, certain HIV and STD risk factors, and concern about one s risk for HIV and STD transmission. TTDE also narrowed the difference between men s and women s reports of the number of different sexual partners over the past 10 years. The feasibility and limitations of TTDE are discussed, as well as possible alternative interpretations that consider the impact of TTDE on the dynamics of the interaction between the respondent and the interviewer.

Design and operation of the National Survey of Children with Special Health Care Needs, 2001.

OBJECTIVES: This report presents the development, plan, and operation of the National Survey of Children with Special Health Care Needs (CSHCN), a module of the State and Local Area Integrated Telephone Survey, conducted by the National Center for Health Statistics, Centers for Disease Control and Prevention. This survey was designed to produce national and State-specific prevalence estimates of CSHCN, describe the types of services that they need and use, and assess aspects of the system of care for CSHCN. This study included two additional modules to provide health care coverage estimates for all children and to collect data on the reasons that low-income uninsured children lack health care coverage. Primary funding for this survey was provided by the Maternal and Child Health Bureau, Health Resources and Services Administration. METHODS: A random-digit-dial sample of households with children under 18 years of age was selected from each of the 50 States and the District of Columbia. Depending on the health care needs of the children in each household, a detailed interview was conducted for one randomly selected child with special needs and a brief health insurance interview was conducted for one randomly selected child without special needs. The respondent was the parent or guardian who knew the most about the child's health and health care. RESULTS: A total of 196,888 household screening interviews were completed from October 2000 to April 2002. This resulted in 38,866 completed special-needs interviews and 176,296 completed health insurance interviews for children without special needs. The weighted overall response rate for special-needs interviews was 61.0%.

Acute coronary syndrome secondary to a complex lesion within a stent implanted over 6 years previously.

We report on an acute coronary syndrome resulting from a complex severe lesion within a stent over 6 years after implantation. This may represent an uncommon long-term limitation of coronary artery stenting.

Screening for subclavian artery stenosis in patients who are candidates for coronary bypass surgery.

We prospectively evaluated 59 patients who were deemed candidates for coronary bypass surgery after coronary artery angiography for subclavian artery narrowing, which could compromise the ipsilateral internal thoracic artery graft. Bilateral arm blood pressure (BP) measurements, auscultation for supraclavicular or cervical bruits, and questioning about cerebrovascular ischemic symptoms were compared to brachiocephalic-subclavian arteriography. One neurologic complication occurred during arteriography. An upper extremity BP difference of > or = 15 mm Hg identified all patients with > or = 50% subclavian artery narrowing. We recommend brachiocephalic-subclavian arteriography only in patients with abnormal noninvasive screening for subclavian stenosis, not routinely.

Design and operation of the National Survey of Early Childhood Health, 2000.

OBJECTIVES: This report presents the development, plan, and operation of the National Survey of Early Childhood Health, a module of the State and Local Area Integrated Telephone Survey, conducted by the National Center for Health Statistics, Centers for Disease Control and Prevention. This survey was designed to assess parents' perceptions of their children's pediatric care. In addition, data were collected that can be used to examine relationships between the promotion of health in the pediatric office and promotion of health in the home. Funding for the survey was provided by The Gerber Foundation, the American Academy of Pediatrics, and the Maternal and Child Health Bureau, Health Resources and Services Administration. The UCLA Center for Healthier Children, Families, and Communities contributed to the design of the study and the questionnaire. METHODS: A national random-digit-dialed (RDD) sample of households with children 4-35 months of age was selected. The study included an oversample of households having an eligible black non-Hispanic or Hispanic child. In households with more than one eligible child, one was randomly selected to be the subject of the interview. The respondent was the parent or guardian who was most responsible for the child's health care. A computer-assisted telephone interviewing (CATI) system was used to collect the data. RESULTS: A total of 2,068 interviews were completed during the first half of 2000. The response rate was 65.6%. A data file has been released that contains demographic information on the focal child and respondent, substantive health and health-related data, and sampling weights. Estimates based on the sampling weights generalize to the entire U.S. population of children 4-35 months of age.