|
Activity Number:
|
380
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #303786 |
|
Title:
|
Efficient Sampling in Case-Control Studies
|
|
Author(s):
|
Ashlyn H. Munson*+ and William Navidi
|
|
Companies:
|
Colorado School of Mines and Colorado School of Mines
|
|
Address:
|
Department of Mathematical and Computer Sciences, Golden, CO, 80401,
|
|
Keywords:
|
Case-control study ; Sampling ; Partial Likelihood
|
|
Abstract:
|
When a rare disease is suspected to be associated with a particular exposure, it is often appropriate to use a case-control study. Cases are identified as failures (occurrences of a disease) over a period of time and all those members of the cohort who are not diseased at the time of the failure are labeled controls. The risk set consists of these cases and controls. The cost may be too great to measure exposure information for all controls in the risk set. Therefore, controls are selected to form the sample risk set with a given case. Previous studies have utilized simple random sampling and counter-matching to create the sample risk set. Our research suggests that a more efficient sampling method exists, which reduces the variance of the risk estimate. This method is applicable to situations using surrogate measures for control exposures, and measuring confounder data.
|
