BACKGROUND Evidence from the United States has shown that tuberculin sensitivity increases with length of stay among residents in homes for the elderly, implying an increasing risk of infection. There is no evidence as to whether or not residents in homes in the United Kingdom have a similar risk. METHODS A study was undertaken to determine whether residence in a home for the elderly increases the risk of tuberculosis infection. Over a six month period all residents in homes for the elderly in Liverpool received a tuberculin test. A health questionnaire was completed by the field team for each resident. A total of 2665 residents in homes for the elderly were surveyed. RESULTS Heaf test grade positivity declined with age, the odds ratio being 0.71 for each 10 year period. Adjusting for age, there was no change in Heaf test grade with length of stay in the home. Heaf test positivity was stronger in smokers (odds ratio 1.59) than ex-smokers (odds ratio 1.20) and non-smokers. Heaf test grade positivity was directly related to pack years. Allowing for age and smoking, the odds ratio for men compared with women for a positive test was 1.62 (95% confidence interval 1.32 to 1.99). CONCLUSIONS Heaf test positivity declines with age. Residence in a home for the elderly is not associated with increased rate of tuberculosis sensitivity. Smoking and male gender is associated with increased Heaf test positivity.