ansfin - Final Exam, April 2003, ANSWERS Categorical Data...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Final Exam, April 2003, ANSWERS Categorical Data Analysis for Epidemiologic Studies, CHL5407H 1a. Analyses are simplified if we begin by constructing a table using only data from black mothers and mothers in the ’Other race’ category (see Table 1). The data are now in a form more typically seen when constructing inferences for pair- matched data about a binary covariate, using McNemar’s chi-square test, for example. The null hypothesis is that the true risk of having a low weight baby is the same for black mothers and for mothers in the ’Other race’ category. The alternative hypothesis is that these two risks are not equal. Equivalently the null and alternative hypotheses may be stated in terms of the true conditional odds ratio of having a low weight baby comparing black mothers to mothers in the ’Other race’ category. Accordingly the null hypothesis is that this true odds ratio is equal to one while the alternative hypothesis is that this true odds ratio is not equal to one. Table 1, Mother’s classification by race for each matched pair Cases Black Other Controls (Race=2) (Race=3) Total-----------------+--------+---------+ Black (Race=2) | 1 | 6 | 10-----------------+--------+--------- Other (Race=3) | 6 | 7 | 24-----------------+--------+---------+ Total 22 11 23 56 We can test the null hypothesis using McNemar’s chi-square test which for these data is equal to (6- 6) 2 / 12 = 0. The associated two-tailed p-value for this test is identically equal to 1 so we fail to reject the null hypothesis. These data are completely consistent with the null hypothesis since the estimated odds ratio is equal to 6 / 6 = 1. Consequently we can conclude from this analysis that we have no evidence that there is any difference in the risk of having a low weight baby between black mothers and mothers in the ’Other race’ category.between black mothers and mothers in the ’Other race’ category....
View Full Document

This note was uploaded on 11/20/2011 for the course STATISTICS ST3241 taught by Professor Manwai's during the Spring '11 term at National University of Singapore.

Page1 / 3

ansfin - Final Exam, April 2003, ANSWERS Categorical Data...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online