|
Activity Number:
|
617
- Recent Developments on Order-Related Designs and Inferences
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 3, 2017 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #323894
|
|
|
Title:
|
Quantile Regression with Nominated Samples: An Application to a BMD Cohort Study
|
|
Author(s):
|
Mohammad Jafari Jozani and Ayilara Olawale Fatai*
|
|
Companies:
|
University of Manitoba and University of Manitoba
|
|
Keywords:
|
Nomination sampling ;
quantile regression ;
bone mineral density ;
ranking
|
|
Abstract:
|
In this talk we consider the problem of quantile regression for bone mineral density (BMD) analysis in a very large cohort study in Manitoba, Canada. Measuring BMD using dual X-ray approach in the follow-up studies is very costly for such a large cohort study. We propose to use nominated samples in order to reduce the cost. A new objective function to account for the ranking information in nominated samples is proposed. We compare the mean squared error of the proposed quantile regression estimates and observe that it provides higher relative efficiency when compared with its counterparts under simple random sampling for analyzing the upper (or lower) tails of the distribution of BMD.
|
Authors who are presenting talks have a * after their name.
