Hostname: page-component-8448b6f56d-tj2md Total loading time: 0 Render date: 2024-04-19T13:30:05.370Z Has data issue: false hasContentIssue false
  • English
  • Français

EXPLORING TWO COST-ADJUSTMENT METHODS FOR SELECTION BIAS IN A SMALL SAMPLE: USING A FETAL CARDIOLOGY DATASET

Part of: Special Collection - Methods

Published online by Cambridge University Press:  22 August 2014

Hema Mistry
Hema Mistry*
Affiliation:
Warwick Medical School, University of Warwick, Hema.Mistry@warwick.ac.uk
Get access Rights & Permissions [Opens in a new window]

Abstract

Objectives: In economic evaluations of healthcare technologies, situations arise where data are not randomized and numbers are small. For this reason, obtaining reliable cost estimates of such interventions may be difficult. This study explores two approaches in obtaining cost estimates for pregnant women screened for a fetal cardiac anomaly.

Methods: Two methods to reduce selection bias in health care: regression analyses and propensity scoring methods were applied to the total mean costs of pregnancy for women who received specialist cardiac advice by means of two referral modes: telemedicine and direct referral.

Results: The observed total mean costs of pregnancy were higher for the telemedicine group than the direct referral group (4,918 versus 4,311 GBP). The regression model found that referral mode was not a significant predictor of costs and the cost difference between the two groups was reduced from 607 to 94 GBP. After applying the various propensity score methods, the groups were balanced in terms of sizes and compositions; and again the cost differences between the two groups were smaller ranging from -62 (matching “by hand”) to 333 GBP (kernel matching).

Conclusions: Regression analyses and propensity scoring methods applied to the dataset may have increased the homogeneity and reduced the variance in the adjusted costs; that is, these methods have allowed the observed selection bias to be reduced. I believe that propensity scoring methods worked better for this dataset, because after matching the two groups were similar in terms of background characteristics and the adjusted cost differences were smaller.

Keywords

Costs and cost-analysisCongenital heart diseasePregnancyNonrandomized
Type
Methods
Information
International Journal of Technology Assessment in Health Care , Volume 30 , Issue 3: Theme: Adaptive Approaches to Licensing , July 2014 , pp. 325 - 332
Copyright
Copyright © Cambridge University Press 2014 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

1. Petersen, S, Peto, V, Rayner, M. Congenital heart disease statistics 2003. British Heart Foundation Health Promotion Research Group. Oxford: University of Oxford, 2003. http://www.bhf.org.uk/heart-health/statistics.aspx (accessed May 5, 2014).Google Scholar
2. NHS, FASP. NHS Fetal Anomaly Screening Programme 18+0 to 20+6 Weeks Fetal Anomaly Scan National Standards and Guidance for England. Exeter: Royal College of Obstetricians and Gynaecologists; 2010.Google Scholar
3. Bull, C. Current and potential impact of fetal diagnosis on prevalence and spectrum of serious congenital heart disease at term in the UK. Lancet. 1999;354:1242–1247.CrossRefGoogle ScholarPubMed
4. Central Cardiac Audit Database. Antenatal diagnosis. Leeds, 2011. http://www.ccad.org.uk/002/congenital.nsf/vwContent/Antenatal%20Diagnosis?Opendocument (accessed May 5, 2014).Google Scholar
5. Dowie, R, Mistry, H, Young, TA, Franklin, R, Gardiner, HM. Cost implications of introducing a telecardiology service to support fetal ultrasound screening. J Telemed Telecare. 2008;14:421–426.Google Scholar
6. Mistry, H. Economic issues associated with the operation and evaluation of telemedicine. PhD Thesis, Brunel University, UK: 2011. http://bura.brunel.ac.uk/handle/2438/5830 (accessed May 5, 2014).Google Scholar
7. Cochrane Collaboration. Chapter 6: Assessment of study quality. In: Alderson, P, Green, S, Higgins, JPT, eds. Cochrane handbook for systematic reviews of interventions. The Cochrane Library, Issue 1. Chichester: Wiley; 2004.Google Scholar
8. Steer, P. The epidemiology of preterm labour. BJOG. 2005;112:1–3.Google Scholar
9. Mistry, H, Dowie, R, Young, T, Gardiner, H. The costs of maternity care for women with multiple pregnancy compared with high-risk and low-risk singleton pregnancy. BJOG. 2007;114:1104–1112.Google Scholar
10. Rosenbaum, PR, Rubin, DB. Reducing bias in observational studies using subclassification on the propensity score. J Am Stat Assoc. 1984;79:516–524.Google Scholar
11. Rubin, DB. Estimating causal effects from large data sets using propensity scores. Ann Intern Med. 1997;127:757–763.Google Scholar
12. Becker, SO, Ichino, A. Estimation of average treatment effects based on propensity scores. Stata J. 2002;2:358–377.Google Scholar
13. D’Agostino, RB. Propensity score methods for bias reduction in the comparison of a treatment to a non-randomised control group. Stat Med. 1998;17:2265–2281.3.0.CO;2-B>CrossRefGoogle Scholar
14. Rubin, DB. Using multivariate matched sampling and regression adjustment to control for bias in observational studies. J Am Stat Assoc. 1979;74:318–328.Google Scholar
15. Dehejia, RH, Wahba, S. Propensity score-matching methods for non-experimental causal studies. Rev Econ Stat. 2002;84:151–161.CrossRefGoogle Scholar
16. Dowie, R, Young, T, Mistry, H, Weatherburn, G. Economic evaluation of the role of telemedicine in paediatric cardiology. First report: Paediatric cardiology outpatient services. Final Report to the Department of Health. Uxbridge: Brunel University; 2003.Google Scholar
17. Gum, PA, Thamilarasan, M, Watanabe, J, Blackstone, EH, Lauer, MS. Aspirin use and all-cause mortality among patients being evaluated for known or suspected coronary artery disease: A propensity analysis. JAMA; 2001;286:1187–1194.CrossRefGoogle ScholarPubMed
18. Curtis, L. Pay and prices index. Unit Costs of Health and Social Care 2010. Canterbury, UK: Personal Social Services Research Unit, University of Kent at Canterbury; 2010.Google Scholar
19. Manly, BFJ. Randomisation, Bootstrap and Monte Carlo methods in biology (Texts in Statistical Science), 2nd ed. London: Chapman and Hall; 1997.Google Scholar
20. StataCorp. Stata Statistical Software: Release 10.0. College Station, TX: Stata Corporation; 2007.Google Scholar
21. Foster, EM. Propensity score matching - An illustrative analysis of dose response. Med Care. 2003;41:1183–1192.Google Scholar
22. McClellan, M, McNeil, BJ, Newhouse, JP. Does more intensive treatment of acute myocardial infarction in the elderly reduce mortality? Analysis using instrumental variables. JAMA. 1994;272:859–866.Google Scholar
23. Heckman, J. Sample selection bias as a specification error. Econometrica. 1979;47:153–161.CrossRefGoogle Scholar
24. Crown, WH. Antidepressant selection and economic outcome: A review of methods and studies from clinical practice. Br J Psychiatry. 2001;179:S18–S22.CrossRefGoogle Scholar
25. Crown, WH, Obenchain, RL, Englehart, L, et al. The application of sample selection models to outcomes research: The case of evaluating the effects of antidepressant therapy on resource utilization. Stat Med. 1998;17:1943–1958.3.0.CO;2-0>CrossRefGoogle Scholar
26. Shah, BR, Laupacis, A, Hux, JE, Austin, PC. Propensity score methods gave similar results to traditional regression modelling in observational studies: A systematic review. J Clin Epidemiol. 2005;58:550–559.Google Scholar
27. Deeks, JJ, Dinnes, J, D’Amico, , Sowden, AJ, Sakarovitch, C, Song, F, et al. Evaluating non-randomised intervention studies. Health Technol Assess. 2003;7:iii-x, 1–173.CrossRefGoogle ScholarPubMed
28. Cepeda, MS, Boston, R, Farrar, JT, Strom, BL. Comparison of logistic regression versus propensity score when the number of events is low and there are multiple confounders. Am J Epidemiol. 2003;158:280–287.Google Scholar
29. Peduzzi, P, Concato, J, Kemper, E, Holford, TR, Feinstein, AR. A simulation study of the number of events per variable in logistic regression analysis. J Clin Epidemiol. 1996;49:1373–1379.Google Scholar
30. Pearl, J. Section 11.3.5 Understanding propensity scores. Causality: Models, reasoning and inference. 2nd ed. New York: Cambridge University Press; 2009.Google Scholar
Supplementary material: File

Mistry Supplementary Material

Table S1

Download Mistry Supplementary Material(File)
File 21.9 KB
Supplementary material: File

Mistry Supplementary Material

Table S2

Download Mistry Supplementary Material(File)
File 22.7 KB