Small area variations in hospitalization rates: how much you see depends on how you look

UMMS Affiliation

Department of Quantitative Health Sciences

Publication Date


Document Type



Aged; Bayes Theorem; Catchment Area (Health); Diagnosis-Related Groups; Hospitals; Humans; Massachusetts; Patient Admission; Physician's Practice Patterns; Small-Area Analysis


Biostatistics | Epidemiology | Health Services Research


This research investigates the degree that estimates of the magnitude of small area variations in hospitalization rates depend on both the estimation method and the number of years of data used. Hospital discharge abstracts for patients 65 and older from acute care hospitals in Massachusetts from 1982 to 1987 were analyzed. The SCV statistic, the approach used in many current small area variation studies, and empirical Bayes (EB), an approach that adjusts more fully for the effect of random variation, were compared. EB estimates based on 3 years of data were best able to predict future area-specific hospitalization rates. Compared to EB estimates using 3 years of data, the SCV statistic with 1 year of data overestimated the median amount of systematic variation by over 70% for the 68 conditions studied; with 3 years of data, the SCV overestimated the median by 55%. Regardless of method, the same conditions were identified as relatively more variable and the same geographic areas were found to have higher than expected hospitalization rates. The magnitude of differences in hospitalization rates depends on how the data are analyzed and how many years of data are used. Hospitalization rates across small geographic areas may vary substantially less than reported previously.


Med Care. 1994 Mar;32(3):189-201. Link to article on publisher's site

Journal/Book/Conference Title

Medical care

PubMed ID


Related Resources

Link to Article in PubMed