|
Activity Number:
|
365
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #304433 |
|
Title:
|
How Misclassification of Race/Ethnicity Categories in Sampling Stratification Affects Survey Estimates
|
|
Author(s):
|
Donsig Jang*+ and Amang Sukasih and Kelly H. Kang and Stephen Cohen
|
|
Companies:
|
Mathematica Policy Research, Inc. and Mathematica Policy Research, Inc. and National Science Foundation and National Science Foundation
|
|
Address:
|
600 Maryland Avenue, SW, Suite 550, Washington, DC, 20024,
|
|
Keywords:
|
effective sample size ; NSRCG ; raking
|
|
Abstract:
|
Misclassification occurs when there is a discrepancy in classification based on two different sources. Such an error could result in the loss of effective sample sizes in key domains within a race/ethnicity group. We assessed whether the misclassification of race/ethnicity occurred during the sampling frame construction, assuming that the data obtained from the respondents most closely represents the "true values." For each true value, we calculated a proportion of cases misclassified into different categories. This proportion was calculated as the usual weighted survey estimate. Misclassification error can be reduced by use of weighting techniques such as post-stratification or raking adjustment. In this study, we investigated how misclassification in sampling variables affects survey estimates produced using weights that had been raked into three marginal population totals.
|
