164 CATEGORICAL DATA: ANALYSIS OF TWO-WAY FREQUENCY TABLES
11.7 Workers were classified as having no (n = 949), mild (n = 44), moderate
(n = 13), or severe heart failure (n = 1). Researchers want to compare these
results with information on job history using a chi-square test. What do you
suggest they do first before performing a chi-square test?
11.8 In a public health survey in a rural county, information was obtained on age and
the question: Do you have one person you think of as your personal doctor?
The patients were grouped into three age groups. There were 99 respondents
who were 18-34 years old, of whom 70 said yes; 506 respondents who were
35-64 years old, of whom 430 said yes; and 220 respondents who were 65
years old or older, of whom 204 said yes. Test whether the three groups are
equally likely to have one person who they think of as their personal doctor.
REFERENCESAfifi, A. A., Clark, V. and May, S. [2004]. Computer-Aided Multivariate Analysis, 4th ed.,Agresti, A. [1996]. An Introduction to Categorical Data Analysis, New York: Wiley, 59-66.
Fleiss, J. L. [ I98 11. Statistical Methods for Rates and Proportions, 2nd ed., New York: Wiley,Rudas, T. [1998]. Odds Ratios in the Analysis of Contingency Tables, Thousand Oaks,
CA: Sage.
Schlesselman, J. J. [ 19821. Case-Control Studies, New York: Oxford University Press, 33-34,van Belle, G., Fisher, L. D., Heagerty, P. J. and Lumley, T. [2004]. Biostatistics: A Methodology
for the Health Sciences, Hoboken, NJ: Wiley-Interscience, 164-165, 169-170, 180.
Wickens, T. D. [ 19891. Multiway Contingency Tables Analysis for the Social Sciences, Hills-
dale, NJ: Lawrence Erlbaum Associates, 30,44-46.Boca Raton, FL: Chapman & Hall/CRC, 285-287.25-26,113-115.38, 105-123,211.