Estimating model-based nonnegative population marginal means in application to medical expenditures covered by different health care policies – A study on Medical Expenditure Panel Survey

Abstract

The medical care expenditure is historically an important public health issue, which greatly impacts the government’s health policies as well as patients’ financial and medical decisions. In population health research, we commonly discretize a numeric attribute to a few ordinal groups to examine population characteristics. Oftentimes, the population marginal mean estimation by the ANOVA approach is inflexible since it uses pre-defined grouping of the covariate. In this paper, we propose a method to estimate the population marginal mean using the B-spline-based regression in a manner of a generalized additive model as an alternative for the ANOVA. Since the medical expenditure is always nonnegative, a Bayesian approach is also implemented for the nonnegative constraint on the marginal mean estimates. The proposed method is flexible to estimate marginal means for user-specified grouping after model fitting in a post-hoc manner, a clear advantage over the ANOVA approach. We show that this method is inferentially superior to the ANOVA through theoretical investigations and an extensive Monte Carlo study. The real data analysis using Medical Expenditure Panel Survey data assisted by some visualization tools demonstrates an applicability of the proposed approach and leads us some interesting observations that may be relevant to public health discussions.

Keywords

B-spline generalized additive model nonnegative constraints Bayesian method Medical Expenditure Panel Survey population marginal mean survey design

Get full access to this article

View all access options for this article.

References

Newhouse

JP.

Medical-care expenditure: a cross-national survey. J Human Res 1977; 12: 115–125.

Geweke

Exact inference in the inequality constrained normal linear regression model. J Appl Econometrics 1986; 1: 127–141.

Hastie

Tibshirani

Generalized additive models. Stat Sci 1986; 1: 297–318.

Searle

Speed

Milliken

GA.

Population marginal means in the linear model: an alternative to least squares means. Am Stat 1980; 34: 216–221.

Rawlings

Pantula

Dickey

DA.

Applied regression analysis: a research tool. New York, NY: Springer Science & Business Media, 2001.

Jorm

Korten

Rodgers

, et al. Sexual orientation and mental health: results from a community survey of young and middle–aged adults. Br J Psychiatr 2002; 180: 423–427.

Gregersen

Møller

Raben

, et al. Determinants of appetite ratings: the role of age, gender, BMI, physical activity, smoking habits, and diet/weight concern. Food Nutrition Res 2011; 55: 7028.

Kirkpatrick

Tarasuk

The relationship between low income and household food expenditure patterns in Canada. Public Health Nutrition 2003; 6: 589–597.

Mossello

Pieraccioli

Nesti

, et al. Effects of low blood pressure in cognitively impaired elderly patients treated with antihypertensive drugs. JAMA Intern Med 2015; 175: 578–585.

10.

Marx

Eilers

PH.

Direct generalized additive modeling with penalized likelihood. Computat Stat Data Analys 1998; 28: 193–209.

11.

Hastie TJ and Tibshirani RJ. Generalized additive models. CRC press, 1990

12.

Gourieroux

Holly

Monfort

Likelihood ratio test, Wald test, and Kuhn-Tucker test in linear models with inequality constraints on the regression parameters. Econometrica: J Econometric Soc 1982; 50: 63–80.

13.

Rodriguez-Yam

Davis

Scharf

LL.

Efficient Gibbs sampling of truncated multivariate normal with application to constrained linear regression. Unpublished manuscript

2004.

14.

Eilers

Marx

BD.

Flexible smoothing with B-splines and penalties. Stat Sci 1996; 11: 89–102.

15.

De Boor

Package for calculating with B-splines. SIAM J Numer Analys 1977; 14: 441–472.

16.

De Boor

Mathématicien

E-U

, et al. A practical guide to splines. New York, NY: Springer-Verlag, 1978.

17.

Tian

Wang

Cai

, et al. The highest confidence density region and its usage for joint inferences about constrained parameters. Biometrics 2011; 67: 604–610.

18.

Levinsky

Ash

, et al. Influence of age on Medicare expenditures and medical care in the last year of life. JAMA 2001; 286: 1349–1355.

19.

Shugarman

Campbell

Bird

, et al. Differences in Medicare expenditures during the last 3 years of life. J General Intern Med 2004; 19: 127–135.

20.

Howdon

Rice

Health care expenditures, age, proximity to death and morbidity: Implications for an ageing population. J Health Economics 2018; 57: 60–74.

21.

Cho

Chung

Roh

, et al. Health care for older persons: a country profile—Korea. J Am Geriatrics Soc 2004; 52: 1199–1204.

22.

Hoover

Crystal

Kumar

, et al. Medical expenditures during the last year of life: findings from the 1992–1996 Medicare current beneficiary survey. Health Services Res 2002; 37: 1625–1642.

23.

Kuriyama

Tsuji

Ohkubo

, et al. Medical care expenditure associated with body mass index in Japan: the Ohsaki Study. Int J Obes 2002; 26: 1069–1074.

24.

Finkelstein

Trogdon

Cohen

, et al. Annual medical spending attributable to obesity: payer-and service-specific estimates: amid calls for health reform, real cost savings are more likely to be achieved through reducing obesity and related risk factors. Health Affairs 2009; 28: w822–w831.

25.

Thorpe

Florence

Howard

, et al. The impact of obesity on rising medical spending: higher spending for obese patients is mainly attributable to treatment for diabetes and hypertension. Health Affairs 2004; 23: W4-480-W484-486.

26.

Trasande

Liu

Fryer

, et al. Effects of childhood obesity on hospital care and costs, 1999–2005: estimating the social costs of obesity allows us to determine whether investment in various interventions would be worth considering. Health Affairs 2009; 28: w751–w760.

27.

Kyle

Pirlich

Lochs

, et al. Increased length of hospital stay in underweight and overweight patients at hospital admission: a controlled population study. Clin Nutrition 2005; 24: 133–142.

28.

Cawley

Meyerhoefer

The medical care costs of obesity: an instrumental variables approach. J Health Economics 2012; 31: 219–230.

29.

Sheng

Feng

Zhang

, et al. Associations between obesity and spinal diseases: a medical expenditure panel study analysis. Int J Environ Res Public Health 2017; 14: 183.

30.

Shiffler

RE.

Maximum Z scores and outliers. Am Stat 1988; 42: 79–80.

31.

Burnham

Anderson

DR.

Multimodel inference: understanding AIC and BIC in model selection. Sociol Meth Res 2004; 33: 261–304.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.01 MB

0.52 MB