In this article, the methodology used by the Health Care Financing Adm
inistration in the 1992 release of 1990 mortality statistics is descri
bed, and the performance of one outlier hospital is evaluated as a cas
e study. The study hospital is compared to all other hospitals, and to
a smaller cohort of 200-to-299-bed minor teaching hospitals, in terms
of predicted and observed mortality rates and mortality model determi
nants. Proportionately more patients treated in the study hospital wer
e women and had cerebrovascular degeneration or chronic renal disease;
fewer patients had cardiovascular disease. Substantially more patient
s from this hospital were transfers from a skilled nursing facility. F
ewer patients were admitted through the emergency department. Although
patients tended to be more seriously ill overall compared with other
hospitals in the country, observed mortality rates were still higher t
han predicted. Possible explanations for the discrepancy were coding i
nconsistencies, inability to control adequately for the severity of il
lness of transfers from skilled nursing facilities, or quality of care
problems.