Time series analysis is one of the methods health services researchers, managers and planners have to examine and predict utilization over time. The focus of this study is univariate time series techniques, which model the change in a dependent variable over time, using time as the only independent variable. These techniques can be used with administrative healthcare databases, which typically contain reliable, time-specific utilization variables, but may lack adequate numbers of variables needed for behavioral or economic modeling. The inpatient discharge database of the Department of Veterans Affairs, the Patient Treatment File, was used to calculate monthly time series over a six-year period for the nation and across US Census Bureau regions for three hospital utilization indicators: Average length of stay, discharge rate, and multiple stay ratio, a measure of readmissions. The first purpose of this study was to determine the accuracy of forecasting these indicators 24 months into the future using five univariate time series techniques. In almost all cases, techniques were able to forecast the magnitude and direction of future utilization within a 10% mean monthly error. The second purpose of the study was to describe time series of the three hospital utilization indicators. This approach raised several questions concerning Department of Veterans Affairs hospital utilization.
Get full access to this article
View all access options for this article.
References
1.
BerkiS. E.OzminkowskiR. J.BrombergJ. A.AshcraftM. L. F. (1987). Regional Variation in Length of Stay in Veterans Administration Hospitals., Ann Arbor, Michigan: Great Lakes VA HSR&D Field Program.
2.
BowermanB. L.O'ConnellR. T. (1987). Time Series Forecasting: Unified Concepts and Computer Implemention., Second Edition. Boston: Duxbury Press.
3.
BoxG. E. P.JenkinsG. M. (1970). Time-Series Analysis: Forecasting and Control., San Francisco: Holden Day.
4.
CrabtreeB. F.RayS. C.SchmidtP. M.O'ConnorP. J.SchmidtD. D. (1990). ‘The individual over time: Time series applications in health care research’. Journal of Clinical Epidemiology, 43(3): 241–60.
5.
DesHarnaisS.ChesneyJ.FlemingS. (1988). ‘Trends and regional variations in hospital utilization and quality during the first two years of the prospective payment system’. Inquiry, 25:374–382.
6.
FarnumN. R.StantonL. W. (1989). Quantitative Forecasting Methods., Boston: PWS — KENT Publishing Company.
7.
FrissL.FriedmanBDemakisJ. (1989). ‘Geographic differences in the use of Veterans Administration hospitals’. Social Science in Medicine, 28(4): 347–54.
8.
GardnerW. S.McLaughlinC. P. (1980). ‘Forecasting: A cost control tool for health care managers’. Health Care Management Review, Summer: 31–8.
9.
GoldenC. W.McDevittC.BlochK. J. (1981). ‘A tool for predicting the future: Good forecasting builds good budgets’. Hospital and Financial Management, August: 18–26.
10.
GornickM. (1975). ‘Medicare patients: Regional differences in length of hospital stays, 1969–1971'. Social Security Bulletin, July: 16–33.
11.
GornickM. (1977). ‘Medicare patients geographic differences in hospital discharge rates and multiple stays’. Social Security Bulletin, June: 22–41.
12.
GrangerC. W. J. (1989). ‘Combining forecasts-twenty years later’. Journal of Forecasting, 3:197–204.
13.
GuerinD.MacKinnonD.P. (1985). ‘An assessment of the California child passenger restraint requirement’American Journal of Public Health, 75(2): 142–4.
14.
HarringtonM. B. (1977). ‘Forecasting areawide demand for health care services: A critical review of major techniques and their applications. Inquiry, 14: 254–68.
15.
HussW. R. (1985). ‘Comparative analysis of company forecasts and advanced time series techniques using electric utility energy sales data’. International Journal of Forecasting, 1:217–39.
16.
JenkinsG. M. (1982). ‘Some practical aspects of forecasting in organizations’. Journal of Forecasting, 1, 3–31.
17.
JensenL. (1990). ‘Guidelines for the application of ARIMA models in time series’. Research in Nursing and Health, 13:429–35.
18.
JoyceT. J.MocanN. H. (1990). ‘The impact of legalized abortion on adolescent childbearing in New York City’. American Journal of Public Health, 80:273–8.
19.
LiuK.MantonK. G. (1983). ‘The length-of-stay pattern of nursing home admissions. Medical Care, 21(12): 1211–22.
20.
MacStravicR. S. (1984). Forecasting use of Health Services: A Provider's Guide., Rockville, MD: Aspen Systems Corporation.
21.
MahmoudE. (1984). ‘Accuracy in forecasting': A survey’. Journal of Forecasting, 3:139–59.
22.
MakridakisS.WheelwrightS. C. (1989). Forecasting Methods for Management., New York: Wiley.
23.
MakridakisS.AndersenA.CarboneR.FildesR.HibonM.LewandowskiR.NewtonJ.ParzenE.WinklerR. (1984). The Forecasting Accuracy of Major Time Series Methods., New York: Wiley.
24.
MakridakisS.WheelwrightS. (1983). Forecasting: Methods and Applications., New York: Wiley.
25.
McClearyR.HayR. A. (1980). Applied Time, Series Analysis for the Social Sciences., Beverly Hills: Sage.
26.
MilnerP. C. (1988). ‘Forecasting the demand on accident and emergency departments in health districts in the Trent region’. Statistics in Medicine, 7:1061–72.
27.
MullerA. (1989). ‘Business recession, alcohol consumption, drinking and driving laws: Impact on Oklahoma motor vehicle fatalities and fatal crashes’. American Journal of Public Health, 79:1366–70.
28.
PackD. J. (1990). ‘In defense of ARIMA modeling’. International Journal of Forecasting, 6:211–18.
29.
PuriA.K.Van LieropJ. (1988). ‘Forecasting housing starts’. International Journal of Forecasting, 4:125–34.
30.
RosenheckR.MassariL. (1991). ‘Psychiatric inpatient care in the VA: Before, during, and after DRG-based budgeting’. American Journal of Psychiatry, 148(7): 888–91.
31.
RossH. L.McClearyR.EpperleinT. (1981–82). ‘Deterrence of drinking and driving in France: An evaluation of the law of July 12, 1978'. Law and Society Review, 16(3): 345–74.
32.
SawyerD. O.ManeyA. (1981). ‘Legal reform in child abuse reporting: A time series analysis’. Evaluation Review, 5(6): 758–87.
33.
SchnaarsS. P. (1986). ‘A comparison of extrapolation models on yearly sales forecasts’. International Journal of Forecasting, 2:71–85.
34.
SchnellD.ZaidiA.ReynoldsG. (1989). ‘A time series analysis of gonorrhea surveillance data’. Statistics in Medicine, 8:342–52.
35.
Martinez-SchnellB.ZaidiA. (1989). ‘Time series analysis of injuries’. Statistics in Medicine, 8:1497–508.
36.
Department of Veterans Affairs, Deputy Assistant Secretary for Planning and Management Analysis Statistical Service, Research Division. (1989). Veteran Population Projections, by Age and Period of Service, and by State and Age, 1980–2040., Washington, DC.
37.
Veterans Administration, Department of Medicine and Surgery (1987). Patient Treatment File Coding Instructions, MP-6, part XVIsupplement no. 4. 1. (December). Washington, DC.
WennbergJ. E.McPhersonK.CaperP. (1984). ‘Will payment based on diagnosis-related groups control hospital costs'?New England Journal of Medicine, 311(5): 295–300.
40.
WennbergJ. E. (1984). ‘Dealing with medical practice variations: A proposal for action’. Health Affairs, 3:6–32.
41.
WennbergJ. E.GittelsohnA. (1982). ‘Variations in medical care among small areas’. Scientific American, April: 120–9.
42.
WrayN. P.DeBehnkeR. D.AshtonC. M.DunnJ. K. (1988). ‘Characteristics of the recurrently hospitalized adult: An information synthesis’. Medical Care, 26:1046–56.
43.
WrightD. J.CaponG.PageR.QuirogaJ.TaseenA. A.TomasiniF. (1986). Evaluation of forecasting methods for decision support. International Journal of Forecasting, 2: 139–52.
44.
ZaidiA.SchnellD. J.ReynoldsG. H. (1989). ‘Time series analysis of syphilis surveillance data’. Statistics in Medicine, 8:353–62.
45.
ZookC. J.MooreF. D. (1980). ‘Highcost users of medical care’. New England Journal of Medicine, 302(18): 996–1002.
46.
ZookC. J.SavickisS. F.MooreF. D. (1980). ‘Repeated hospitalization for the same disease: A multiplier of national health costs’. Milbank Memorial Fund Quarterly, 58(3): 445–73.
