当前位置： SCI文献检索 > AMERICAN JOURNAL OF OBSTETRICS AND GYNECOLOGY期刊下所有文献 > A new procedure for the statistical evaluation of intrauterine contraception.

A new procedure for the statistical evaluation of intrauterine contraception.

Abstract：

:An improved statistical method for assessing the efficacy of intrauterine contraception is presented. This method, called the log-rank method, is based on a daily life table, which yields the best estimates of the cumulative net termination probabilities. It provides a sensitive chi-square test statistic to detect differences among these probabilities for two or more contraceptive devices. When three or more devices are compared, the chi-square statistic may be partitioned into additive components representing comparisons among groups of devices. The log-rank method also permits adjusting for differences among subgroups by controlling for factors such as parity or age. Although calculations may be performed on a desk calculator, a FORTRAN-IV computer program is made available to interested researchers. :A new procedure for the statistical evaluation of IUDs, the log-rank method, is presented. The log-rank method is based on a daily life table. Comparisons of 2 or more devices are made by examining cumulative net probabilities of termination for any reason. The data required for analysis include patient identification, IUD type, date of insertion, date the patient was last seen or date of termination, and the reason for termination. Steps for calculating the cumulative net termination probabilities are presented. The method provides a sensitive chi-square test to detect differences among net terminiation probabilities. When there are more than 3 devices to compare, the chi-square statistic may be partitioned into additive components representing comparisons among groups of devices. It is also possible to adjust the method for such subgroup differences as parity and age. 2 applications of this method, performed with the FORTRAN-4 computer are presented. 3 IUDs are compared: TCu-300, the Dalkon Shield, and SCS-D. Results from the original study correlated with results using the log-rank method. In the 2nd application the log-rank analysis of 589 women using either the Lippes Loop or the Dalkon Shield is given. This statistical method is also useful in comparing other methods of contraception.

journal_name

Am J Obstet Gynecol

journal_title

American journal of obstetrics and gynecology

authors

Azen SP,Roy S,Pike MC,Casagrande J,Mishell DR Jr

doi

10.1016/0002-9378(77)90632-9

subject

Has Abstract

pub_date

1977-06-01 00:00:00

pages

329-35

issue

eissn

0002-9378

issn

1097-6868

pii

0002-9378(77)90632-9

journal_volume

128

pub_type

杂志文章

在线工具

A new procedure for the statistical evaluation of intrauterine contraception.