Activity Number:
|
39
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, August 11, 2002 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Section on Statistics in Epidemiology*
|
Abstract - #301774 |
Title:
|
Use of Independent Assumption in the "Matched" Study of Obstetrics and Gynecology
|
Author(s):
|
Yen-Hong Kuo*+
|
Affiliation(s):
|
Jersey Shore Medical Center, Meridian Health System
|
Address:
|
1945 State Route 33, Neptune, New Jersey, 07753, US
|
Keywords:
|
matched study ; independent assumption ; case-control
|
Abstract:
|
This study was conducted to assess the use of independent assumption in the "matched" study. Articles published in the journals of "American Journal of Obstetrics and Gynecology" or "Obstetrics & Gynecology" in 2001 with the keyword of "matched" and clearly defined matching criteria in the abstract were identified via MEDLINE. A total of 23 articles with a case/treatment-to-control ratio of 1:1 were included. Among them, only 12 studies (52%) were actually 1-to-1 matched. The median number of matching criteria was three and the maximum was eight, when one self-controlled study was excluded. Age or gestational age was used as a criterion in ten studies (91%). For making comparisons, a total of three studies (25%) from both journals either used independent assumption (n=2) or did not specify (n=1). In all of the other eleven non 1-to-1 matched studies (either "matched" was used to indicate no statistically significant difference, or lacking of statements with respect to 1-to-1 matching), the independent assumption was used. This study reveals that the independent assumption was misused in some of the 1-to-1 matched studies. In addition, the inappropriate use of the term of "matched" was common.
|
- 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 2002 program |