Measurement of Trend (a 2 by <i>c</i> Table)

Steve Selvin

in Epidemiologic Analysis

Published in print August 2001 | ISBN: 9780195146189
Published online September 2009 | e-ISBN: 9780199864720 | DOI:
Measurement of Trend (a 2 by c Table)

Show Summary Details


This chapter compares the frequency of infants with a single congenital malformation to that of infants with multiple congenital malformations, focusing on evaluating changes over time. Extensive data on infants with major congenital malformations are routinely collected as part of a state surveillance system called the California Birth Defects Monitoring Program. Records of infants identified as having a single major malformation or more than one major malformation were obtained from this program. A selection of these infants was made from the years 1983 to 1991 in two Bay Area counties (San Francisco and Santa Clara). Chi-square and regression techniques are used to assess the overall association between the occurrence of multiple birth defects and the year of birth. A summary chi-square statistic is partitioned into compartments reflecting linear and nonlinear trends over time. A parallel logistic regression model is also used to evaluate the pattern of change during the nine years. Analyses of the California birth defects surveillance data show a clear increase, almost linear, in the risk of multiple major birth defects among children with at least one major congenital anomaly over the period 1983 to 1991. A straight line summary “explains” about 90% of the variance in the proportions of multiple birth defects.

Keywords: infants; congenital malformation; California Birth Defects Monitoring Program; chi-square; birth defects

Chapter.  3443 words.  Illustrated.

Subjects: Public Health and Epidemiology

Full text: subscription required

How to subscribe Recommend to my Librarian

Buy this work at Oxford University Press »

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.