|
Activity Number:
|
167
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2003 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Health Policy Statistics
|
| Abstract - #301493 |
|
Title:
|
Using Capture-Recapture Techniques to Test Data Source Reliability
|
|
Author(s):
|
Howard M. Townsend*+ and Don Broach and Matthew Fitzgerald and Dana Keller and Dan Edris and Frank Funderburk
|
|
Companies:
|
Delmarva Foundation and Delmarva Foundation for Medical Care and Delmarva Foundation for Medical Care and Delmarva Foundation for Medical Care and Delmarva Foundation for Medical Care and Delmarva Foundation for Medical Care
|
|
Address:
|
46 Wayman Ave., Easton, MD, 21601-8112,
|
|
Keywords:
|
quality of care ; capture-recapture ; GLM ; AIC
|
|
Abstract:
|
We adapted capture-recapture techniques to develop a technique for determining the optimal combination medical administrative data sources to assess the quality of health care services received by Medicaid-eligible patients. The methodology is demonstrated using a simulated data set. We identified hypothetical patients from three data sources and listed patients present in each source. Data were arranged in a 2^3 incomplete multiway contingency table with one missing cell corresponding to patients who were not listed in any source. We developed a priori hypotheses about which source main effects and interactions effects would be important to in determining the population size and establish a candidate set of models (GLMs with log link function using Poisson distribution) based on the hypotheses. We used Akaike Information Criterion (AIC) for model selection. Additionally, maximum likelihood estimates were used to estimate the missing cell count. The model with the lowest AIC value (and highest AIC weight) of the candidate set included only the main effects of registry data and contained an estimated 98% of the Medicaid-eligible patients who were eligible for services.
|
