Online Program Home
  My Program

Abstract Details

Activity Number: 530 - SPEED: Survey Research Methods
Type: Contributed
Date/Time: Wednesday, August 2, 2017 : 10:30 AM to 11:15 AM
Sponsor: Survey Research Methods Section
Abstract #325086
Title: A Novel Approach to Developing 5-Star Ratings for Home Health Care Systems
Author(s): Kimberly Ault* and Laura Smith and Harper Gordek and Wayne Anderson
Companies: RTI International and RTI International and RTI International and RTI International
Keywords: Clustering ; Decision Trees ; Distance Functions
Abstract:

Four publicly reported composite measures (care of patients, communication between providers and patients, specific care issues, and overall rating of care) are used to produce an overall summary measure for each agency. The "star" rating assignment process consists of three main steps: 1) computing the Euclidian distance of the measure scores between each pair of home health agencies, 2) grouping the measure scores into an initial set of clusters using Ward's minimum variance method, and 3) refining the selections to produce a final set of clusters. This presentation will describe the methodology used to produce five-star quality ratings for home healthcare agencies. Additionally, a review of the steps used to evaluate the ratings will be presented including a brief review of clustering methods considered, determining if five groupings was a good fit, and testing size limits for health care agencies. Potential improvements that may be taken will also be presented. Data from the Home Health Consumer Assessment of Healthcare Providers and Systems (HHCAHPS) is used to demonstrate the clustering methodology.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association