Whether or not age by itself increases susceptibility to pneumococcal infections separate from the effects of chronic disease is controversial. To address this issue, data collected for a retrospective cohort study of pneumococcal infections among 63 middle-aged and older veterans and 126 uninfected controls were reanalysed. Univariate analysis suggested a linear increase in risk with increasing age for patients 50 years old and older (p = 0.03). Subjects over age 80 years seemed to be at particularly high risk when compared with patients under 50 (odds ratio = 4.3, p less than 0.03). The odds of pneumococcal infection increased by an estimated factor of 1.33 (95% confidence interval = 1.03, 1.71) for each 10-year increase in age. Controlling for other risk factors did not appreciably change the point estimate of the age effect, but statistical significance was lost. This result however suggests that age has an independent association with the risk of pneumococcal infections. The potential impact of this finding on public policy urges that the association of age with the risk of pneumococcal disease be re-examined in a study of sufficient sample size to resolve the issue.