Journal of Economic and Social Measurement - Volume 30, issue 2-3

Authors: Cohen, Steven B.

Article Type: Research Article

Abstract: The quality and data content of household specific health surveys are often enhanced through integrated designs which include the conduct of follow back surveys to medical providers and facilities that have provided care to household respondents. In terms of data …quality, household reported medical conditions can be evaluated for accuracy relative to provider specific records on medical conditions for the same patient and specific health events. With respect to health care expenditures collected from household respondents for their reported health care events, available linked medical provider level data is a more accurate source of information. The availability of such supplemental data on use and expenditures allows for the conduct of methodological studies to evaluate the accuracy of household reported data and informs adjustment strategies to household data in the absence of provider specific data to reduce bias attributable to response error. In this paper, the capacity of integrated survey designs to achieve reductions in bias attributable to survey nonresponse is discussed. Examples are drawn from the Medical Expenditure Panel Survey (MEPS), an ongoing longitudinal panel survey designed to produce estimates of health care utilization, expenditures, sources of payment, and insurance coverage of the US civilian non-institutionalized population. Show more

Keywords: Survey integration, nonresponse

DOI: 10.3233/JEM-2005-0244

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 101-114, 2005

Authors: Cohen, Steven B. | Wun, Lap-Ming

Article Type: Research Article

Abstract: In health care surveys similar to the MEPS, the use of additional administrative data and medical records for survey participants permits additional methodological investigations and evaluations to examine the accuracy of household reported data. When differentials are observed in the …response profiles through these evaluations and comparisons, the design permits well specified adjustment and estimation strategies to correct for measurement error. In addition to serving as the primary source for the expenditures in the MEPS, the design of the Medical Provider Component provides data that could potentially facilitate adjustments to household reported utilization data that correct for reporting errors (both under-reporting and over-reporting (telescoping errors)), under the assumption that the medical provider reports are the gold standard. In this paper, we examine the level of concordance between household and medical provider utilization reports. An adjustment strategy to correct for response error attributable to household utilization reports is also presented. Show more

Keywords: Health care utilization, response error, MEPS

DOI: 10.3233/JEM-2005-0245

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 115-126, 2005

Authors: Yu, William W. | Machlin, Steven R.

Article Type: Research Article

Abstract: The Medical Expenditure Panel Survey Household Component (MEPS-HC) is designed to provide nationally representative annual estimates of health care use, expenditures, sources of payment, and insurance coverage for the US civilian noninstitutionalized population. The expenditure data from MEPS have been …shown to exhibit a marked positive skewness, with a few high expenditure respondents and many low or zero expenditure respondents. As a consequence of this departure from the normal distribution, the frequency with which a conventional confidence interval for a MEPS expenditure estimate will not capture the true population parameter may be higher than the probability stated for the confidence interval. Based on repeated sample simulations using data from the 1996 to 2001 MEPS-HC, this paper evaluates and compares the actual probability achieved for confidence intervals derived from expenditure data by types of expenditure and varying sample sizes. The results are also compared to estimated confidence probabilities obtained from repeated sample simulations for other types of variables that do not exhibit as marked a positive skewness as health care expenditures. Show more

Keywords: Skewness of medical expenditures, MEPS

DOI: 10.3233/JEM-2005-0246

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 127-134, 2005

Authors: Cohen, Steven B. | Ezzati-Rice, Trena | Yu, William

Article Type: Research Article

Abstract: In this paper, an evaluation model is presented to assess the utility of probabilistic models in terms of their capacity to successfully oversample policy relevant population subgroups that are subject to transitions. Examples of these applications are drawn from the …Medical Expenditure Panel Survey (MEPS). Given the high concentration of health care expenditures in a given year among a relatively small percentage of the population, a prediction model that can accurately identify the persistence of high levels of expenditures is an important analytical tool. This type of modeling effort also enhances the ability to discern the causes of high health care expenses and the characteristics of the individuals who incur them. This feature also applies to prediction models that can accurately identify those individuals with persistently low or average levels of expenditures. The models that are presented have particular relevance as statistical tools to facilitate efficient sampling strategies that permit the selection of an over-sample of individuals likely to incur high levels of medical expenditures in the future. Show more

Keywords: Medical expenditure predictions, MEPS

DOI: 10.3233/JEM-2005-0247

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 135-144, 2005

Authors: Zuvekas, Samuel H. | Cohen, Joel W.

Article Type: Research Article

Abstract: We examine the extent to which the health care services delivered by physicians and hospitals in public and private health plans are capitated, and how this changed from 1996 to 2000. The data are from the 1996 to 2000 years of the …nationally representative Medical Expenditure Panel Survey (MEPS). Information on whether health care use was covered by capitated arrangements was obtained from billing offices of physicians and hospitals. We compare changes in the percentage of office-based physician visits, hospital outpatient department (OPD) visits, hospital emergency department (ED) visits, and hospital inpatient stays that are covered by capitation arrangements. We also compare differences by health insurance coverage and socio-demographic characteristics. We use standard two-tail tests of significance, accounting for the complex survey design of the MEPS. We find that only 15 percent of visits to office-based physicians were capitated in 1996, declining to 13 percent in 2000. Even among HMO enrollees, visits covered by a provider capitation arrangement represented a minority of all office visits, declining to 25 percent for Private HMO enrollees and 15 percent for Medicaid HMO enrollees in 2000. Even smaller proportions of hospital services were capitated. Conclusions: Capitation remains relatively rare even among public and private HMO enrollees. Show more

Keywords: Capitation, HMOs, medicaid, private plans

DOI: 10.3233/JEM-2005-0248

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 145-156, 2005

Authors: Eyerman, Joe | Bowman, Katherine | Butler, Dicy | Wright, Douglas

Article Type: Research Article

Abstract: Research has demonstrated that cash incentives paid to respondents in sample surveys can increase the level of cooperation, reduce non-response bias, and lower data collection costs. However, recent research has shown that gains in response rate and reduced data collection …costs associated with monetary incentives may vary across sub-groups in the population. Consequently, monetary incentives may result in inconsistent reductions in non-response error and systemic changes in sample composition. This paper describes an incentive experiment conducted as part of the 2001 National Household Survey on Drug Abuse (NHSDA), and evaluates the impact of monetary incentives on measures of cooperation for different population sub-groups. Findings indicate that the incentive had a positive impact on cooperation. Furthermore, the incentive neither introduced additional differences in cooperation propensities, nor did it eliminate the pre-existing differences in cooperation among population sub-groups. Show more

DOI: 10.3233/JEM-2005-0250

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 157-169, 2005

Authors: Ritter, Grant | Reif, Sharon | Gadzuk, Anita | Krenzke, Thomas | Mohadjer, Leyla | Lee, Margaret | Horgan, Constance M.

Article Type: Research Article

Abstract: In the past, incentive payments have proven successful in increasing survey response rates. In particular, incentives have been shown to increase the yield rate for harder-to-interview respondents. Despite this success, incentives are not without controversy. Opponents note that incentives may …make the survey appear less important, destroy civic responsibility, and create an unnecessary expectation. Over time researchers may have to pay sizable incentives to achieve the response rates obtained 20 years ago before the use of incentives was common. Incentives could also have a detrimental impact on sample composition. The Alcohol and Drug Services Study (ADSS) included an incentive payment sub-study as part of its client follow-up phase. The sample for this sub-study randomized clients into four groups. One group was paid $25, the amount received by other responding clients in the ADSS main study. Respondents in the other three groups were paid an alternative amount (i.e., $0, $10, or $35). In examining the impact of varying incentives to sampling benchmarks, such as response rate and sample composition, the ADSS incentive sub-study found that the fears of opponents concerning the use of incentives were substantially unfounded, at least among the substance abuse treatment clients in the follow-up phase of ADSS. Show more

DOI: 10.3233/JEM-2005-0252

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 171-189, 2005

Authors: Krenzke, Thomas | Mohadjer, Leyla | Ritter, Grant | Gadzuk, Anita

Article Type: Research Article

Abstract: The Alcohol and Drug Services Study (ADSS) was conducted for the Substance Abuse and Mental Health Services Administration between 1996 and 1999 to assess the nation's substance abuse treatment system. The sample for ADSS was selected using a multi-stage stratified …design. Clients were sampled from selected substance abuse treatment facilities as part of the Phase II sample. Client follow-up comprised interviews and urine specimen collection in Phase III of the survey. One component of ADSS examined the impact of different incentive payments on measures of response rate and response quality using ADSS Phase III client interview data. To test for the effects of four payment levels, several measures of response quality were used. The analysis of consistency involving respondent self-reports, abstracted record data, and urine test results showed no conclusive evidence that incentive payments have any positive or negative effect on data consistency. The analysis of item non-response rates showed that an increase in incentive payments was associated with a subtle decrease in item type non-response rates. Furthermore, mixed results were observed when analyzing the relationship between incentive payment and clients reporting more (or less) of certain types of behavior. Show more

DOI: 10.3233/JEM-2005-0251

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 191-217, 2005

Authors: Wright, Douglas | Bowman, Katherine | Butler, Dicy | Eyerman, Joe

Article Type: Research Article

Abstract: The purpose of this paper is to determine whether giving a monetary incentive has an effect on reported drug use rates. Sampling weights were adjusted to account for the differential response rates between the incentive and non-incentive cases. Then logistic …regression models of substance use were fitted as a function of the incentive level ($0, $20, and $40) while controlling on other variables that might mask the relationship. The incentive had a statistically significant effect on the reported past-year use of marijuana and on past-month use of cocaine, but no effect on past-month or lifetime use of marijuana. Offering a monetary incentive to respond can result in different estimated prevalence rates for the incentive and non-incentive groups. The extent of the difference may be a function of the perceived level of social disapproval of the substance and the reference period (past month, past year, or any past use). Some of the difference appears to be due to differences in substance use rates between the group that had traditionally reported without an incentive and the new group attracted by the incentive. Other differences appear to result from more honest reporting among the traditional respondents. Show more

DOI: 10.3233/JEM-2005-0254

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 219-231, 2005

Authors: Kulka, Richard A. | Eyerman, Joe | McNeeley, Madeline E.

Article Type: Research Article

Abstract: Incentive payments to survey respondents have been used extensively for many years to improve survey response rates. There is considerable research evidence supporting the value of compensation for increasing cooperation and improving the speed and quality of response in a …broad range of data collection efforts. This paper examines current issues in the use of monetary incentives in sample surveys, including a review of the literature concerning the direct and indirect impact of incentives on survey statistics, and the practical and operational issues for their use. This paper also examines the two recent experiments conducted to assess the effectiveness of incentives in studies of substance use – the Alcohol and Drug Services Study and the National Household Survey on Drug Abuse. These studies are reviewed in light of the current issues identified in the literature. They are described in detail in the companion papers included in this issue of the Journal of Social and Economic Measurement. Show more

DOI: 10.3233/JEM-2005-0253

Citation: Journal of Economic and Social Measurement, vol. 30, no. 2-3, pp. 233-249, 2005