JSM 2004 - Toronto

Abstract #301127

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page
Activity Number: 196
Type: Contributed
Date/Time: Tuesday, August 10, 2004 : 8:30 AM to 10:20 AM
Sponsor: Section on Survey Research Methods
Abstract - #301127
Title: Variance Estimation for the National Compensation Survey When PSUs are Clustered Prior to the Second Phase of Sampling
Author(s): Christopher J. Guciardo*+ and Alan H. Dorfman and Lawrence R. Ernst and Michael Sverchkov
Companies: Bureau of Labor Statistics and Bureau of Labor Statistics and Bureau of Labor Statistics and Bureau of Labor Statistics
Address: 2 Massachusetts Ave. NE, Washington, DC, 20212,
Keywords: replication ; jackknife ; zero-calibrated ; NCS ; BRR
Abstract:

The National Compensation Survey uses a three-phase sample: areas (PSUs), establishments, and jobs. For phase two, we initially planned to take independent, stratified samples within each PSU, by fixing a sample size for each PSU and then allocating these sizes to industry sampling strata, ensuring at least one establishment sampled per PSU x industry stratum. Yet for the smaller, noncertainty PSUs, desired sizes were often less than the number of industry strata; so 99 of these PSUs were collapsed into a single cluster before sampling. Variances were estimated using balanced repeated replication (BRR), with the collapsing of the 99 PSUs ignored in the calculation of the variance estimates. Wang, Dorfman, and Ernst (to appear) evaluated via a simulation study the accuracy of using standard BRR for this type of sampling and also investigated an alternative variance estimator combining model-based and design-based ideas. We investigate alternate variance estimators, including zero-calibrated BRR and jackknife, evaluating the accuracy of these variance estimates by drawing multiple samples from our frame.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004