|
Activity Number:
|
369
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #307096 |
|
Title:
|
Missing Data and Consequences in Ranked Set Sampling
|
|
Author(s):
|
Jessica Kohlschmidt*+ and Elizabeth Stasny and Douglas Wolfe
|
|
Companies:
|
The Ohio State University and The Ohio State University and The Ohio State University
|
|
Address:
|
5980 OSweeney Lane, Dublin, OH, 43016,
|
|
Keywords:
|
ranked set sampling ; ranking ; sampling ; missing data ; imputation ; weighting
|
|
Abstract:
|
Missing data is a natural consequence of sampling. Some researchers ignore the missing data. If the data is missing completely at random, this procedure provides meaningful estimates. In many situations, the data missingness is due to a phenomenon occurring in the population. Ignoring the pattern of missingness can lead to inaccurate conclusions. We often have missing data on the variable of interest, but, in RSS, we have additional information available about each unit we wish to quantify. This extra information can be used to help determine estimation methods that may be superior to current methods. We investigate methods to deal with missing data that use the ranking information we have for each unit and the observed measurements of the variable of interest.
|
