|
Activity Number:
|
46
- In Memory of Ken Brewer
|
|
Type:
|
Invited
|
|
Date/Time:
|
Sunday, August 7, 2022 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Memorial
|
|
Abstract #319189
|
|
|
Title:
|
Ken Brewer and the Synthesis of Design and Model-Based Survey Sampling
|
|
Author(s):
|
Phillip S. Kott*
|
|
Companies:
|
RTI International
|
|
Keywords:
|
weight;
remainder;
variance;
prediction
|
|
Abstract:
|
A while ago K.R.W. (Ken) Brewer published a little-noticed article in the Australian Journal of Statistics. The article synthesized the accepted "design-based" approach to survey sampling with a rival model-based approach employed in other branches of statistics. Design-based theory treats the mechanism for selecting a random sample as fundamental to drawing valid population inferences. The model-based approach treats the values of the selected sample as random variables. Those variables are modeled to draw population inferences. What is remarkable about Ken's article is that it appeared seven year before Richard Royall published his celebrated article advocating the prediction-theory (aka model-based) approach to finite-population sampling and 29 years before Sarndal et al. gave Ken's synthesis a name: model-assisted survey sampling. We will discuss Ken's AJS article and several subsequent ones that build on it.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2022 program
|
