|
Activity Number:
|
195
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #307554 |
|
Title:
|
The Impact of Unequal Minority Distribution across Schools on PPS Oversampling Methods
|
|
Author(s):
|
William Robb*+ and Joshua Brown and James Ross and Ronaldo Iachan
|
|
Companies:
|
ORC Macro and ORC Macro and ORC Macro and ORC Macro
|
|
Address:
|
126 College Street, Burlington, Vermont,
|
|
Keywords:
|
PPS ; minority ; oversampling ; school-based ; GINI ; weighted MOS
|
|
Abstract:
|
Probability Proportional to Size sampling methods are widely used in multistage cluster samples. The measure of size used for primary sampling units can be weighted so as to concentrate the sample among units that are relatively rare - a method that is used extensively to oversample minority respondents. The success of oversampling depends on the magnitude of the weights used and the degree of differential concentration of minorities among sampling units. We present recent work quantifying the degree to which minority yields can be increased in school-based surveys using these methods given the degree of unequal distribution of minorities across schools, the impact of these methods on design effects, and the implications of the degree of minority concentration in the resulting sample, relative to that in the population.
|
