Abstract Details
Activity Number:
|
376
|
Type:
|
Invited
|
Date/Time:
|
Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Health Policy Statistics Section
|
Abstract #310695
|
|
Title:
|
An Algorithm to Predict Probability of Spanish Reference, Calibrated by the Results of a Randomized Survey Experiment
|
Author(s):
|
Marc N. Elliott*+
|
Companies:
|
RAND Corporation
|
Keywords:
|
Indirect Estimation ;
Survey Mode ;
Spanish Language ;
Randomized Experiment
|
Abstract:
|
We link name and address information from Medicare beneficiaries to ACS and Census Data, predict Hispanic ethnicity via a Bayesian algorithm, and predict the probability of Spanish response to the CAHPS survey of Medicare beneficiaries under its initial protocol: mailout-mailback of a paper instrument, with telephone followup of nonrespondents. Prior to the experiment, only English mail surveys were used, so response rates by Spanish-preferring beneficiaries were low & Spanish response was limited to telephone followup. A logistic regression predicted the probability of Spanish-phone response with 98% concordance. The next year, 5000 of the 10,000 beneficiaries with the highest predicted probability of preferring Spanish were randomized to a bilingual mailing, with bilingual telephone followup. This intervention substantially increased mail and total response rates but not phone response rates in the target population, with a majority of intervention arm mail and phone response in Spanish. Finally, we used the experimental data to calibrate the algorithm to predict the probability of Spanish preference (response in Spanish under a fully bilingual survey protocol).
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.