Sensitivity Analysis and the Expected Value of Perfect Information

Medical Decision Making - Tập 18 Số 1 - Trang 95-109 - 1998
James C. Felli1, Gordon B. Hazen2
1Defense Resources Management Institute, Naval Postgraduate School, Monterey, California 93943-5201, USA.
2Industrial Engineering and Management Sciences

Tóm tắt

Measures of decision sensitivity that have been applied to medical decision problems were examined. Traditional threshold proximity methods have recently been supple mented by probabilistic sensitivity analysis, and by entropy-based measures of sen sitivity. The authors propose a fourth measure based upon the expected value of perfect information (EVPI), which they believe superior both methodologically and prag matically. Both the traditional and the newly suggested sensitivity measures focus en tirely on the likelihood of decision change without attention to corresponding changes in payoff, which are often small. Consequently, these measures can dramatically over state problem sensitivity. EVPI, on the other hand, incorporates both the probability of a decision change and the marginal benefit of such a change into a single measure, and therefore provides a superior picture of problem sensitivity. To lend support to this contention, the authors revisit three problems from the literature and compare the results of sensitivity analyses using probabilistic, entropy-based, and EVPI-based mea sures. Key words: sensitivity analysis; expected value of perfect information. (Med Decis Making 1998;18:95-109)

Từ khóa


Tài liệu tham khảo

10.1002/sim.4780091104

Sonnenberg FA, 1994, Med Care, 32, JS52

10.1177/0272989X8700700203

Felli JC, 1996, International Engineering Consortium Annual Review of Communications., 49, 243

O'Brien BJ, 1994, Med Care, 32150

10.1111/j.1540-5915.1988.tb00262.x

10.1111/j.1540-5915.1984.tb01211.x

10.1287/opre.16.2.254

10.1287/opre.11.4.536

Starr MK, 1966, Industrial Management Review, 8, 71

10.1016/0377-2217(91)90296-8

10.1111/j.1540-5915.1985.tb01491.x

10.1002/bdm.3960030306

10.1111/j.1539-6924.1988.tb01180.x

Connelly DP, 1989, Arch Pathol Lab Med, 113, 750

10.1177/0272989X8600600205

10.1016/0010-4809(86)90020-0

10.1177/0272989X8500500205

Dittus RS, Proceedings of the 1992 Winter Simulation Conference

10.1016/0735-1097(89)90158-7

Shannon CE, 1948, Technical Journal, 27, 379

Genrich JF, 1989, J Petroleum Technology, 930, 983

10.1080/01621459.1994.10476865

10.1177/0272989X8100100208

10.1109/TSSC.1966.300074

10.1016/0010-4809(68)90016-5

10.1016/0002-9343(73)90204-0

Heckerman D., Proceedings of the Seventh Conference on Uncertainty in Artificial Intelligence

Heckerman D., 1990, Toward normative expert systems the Pathfinder project. Technical Report KSL-90-08, Medical Computer Science Group, Section on Medical Informatics

Feinstein AR, 1985, Clinical Epidemiology, The Architecture of Clinical Research

Spiegelhalter DJ, 1994, J Royal Statistical Association, 157

Spiegelhalter DJ, Freedman LS Bayesian approaches to clinical trials In. Bernardo JM, Degroot MH, Lindley DV, Smith AFM (eds) Bayesian Statistics 3. New York Oxford University Press, 1988 453-77

10.1016/S0895-4356(96)00206-5

10.1016/S0895-4356(96)00208-9

10.1001/archinte.1993.00410110045008

10.1016/S0895-4356(96)00207-7

Wadland WC, 1989, J Fam Pract, 29, 372

Felli JC, Working paper Defense Resources Management Institute, Naval Postgraduate School

Von Winterfeldt D., 1986, Decision Analysis and Behavioral Research

10.1002/9780470316870

Thông tin
Thông tin xuất bản

Medical Decision Making

Tập 18 Số 1

95-109

Thông tin tác giả