Related Experiment Video
Updated: Feb 18, 2026

Applying an eMASS Customization Program as a Research Tool to Evaluate Consumer Benefits
Published on: September 27, 2019
Can Composite Measures Provide a Different Perspective on Provider Performance Than Individual Measures?
Michael Shwartz1, Amy K Rosen, James F Burgess
1*Center for Healthcare Organization and Implementation Research, VA Boston Healthcare System (152M) †Questrom School of Business ‡Department of Surgery, Boston University School of Medicine §School of Public Health, Boston University, Boston, MA.
Background:
Composite measures, which aggregate performance on individual measures into a summary score, are increasingly being used to evaluate facility performance. There is little understanding of the unique perspective that composite measures provide.
Objective:
To examine whether high/low (ie, high or low) performers on a composite measures are also high/low performers on most of the individual measures that comprise the composite.
Methods:
We used data from 2 previous studies, one involving 5 measures from 632 hospitals and one involving 28 measures from 112 Veterans Health Administration (VA) nursing homes; and new data on hospital readmissions for 3 conditions from 131 VA hospitals. To compare high/low performers on a composite to high/low performers on the component measures, we used 2-dimensional tables to categorize facilities into high/low performance on the composite and on the individual component measures.
Results:
In the first study, over a third of the 162 hospitals in the top quintile based on the composite were in the top quintile on at most 1 of the 5 individual measures. In the second study, over 40% of the 27 high-performing nursing homes on the composite were high performers on 8 or fewer of the 28 individual measures. In the third study, 20% of the 61 low performers on the composite were low performers on only 1 of the 3 individual measures.
Conclusions:
Composite measures can identify as high/low performers facilities that perform "pretty well" (or "pretty poorly") across many individual measures but may not be high/low performers on most of them.
Related Concept Videos
Central Tendency: Analysis
The mean is one such measure, calculated by totaling all values in a dataset and dividing by the number of values. For instance, the mean blood pressure reading (120, 130, 140, 150) would be 135. However, the mean can be affected by extreme values or outliers.
The median, another measure,...
Measures of Central Tendency
Multiple Comparison Tests
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...
Variability: Analysis
The range is a simple measure of variability, indicating the difference between the highest and...
Methods of Documentation VI: Case Management Model
For example, a patient with a chronic...
Methods of Documentation V: CBE
In CBE, healthcare professionals establish predefined standards of practice that define what constitutes...

