A population-based case-control study of the association between dietary lipids and lung cancer was carried out in Hawaii between March 1983 and October 1985. The sample included 226 men and 100 women with lung cancer and 597 male and 268 female controls, frequency-matched to the cases on sex and five-year age group. Personal interviews were conducted in the home by trained interviewers using a quantitative diet history method. The items in the questionnaire were chosen to provide an estimate of 85% or more of the intakes of dietary cholesterol and fat for individuals in each of the five ethnic groups included in the study. The results showed a significant positive association of dietary cholesterol and the risk of lung cancer in men, but not in women. The odds ratio for the risk of lung cancer among men in the highest compared with the lowest quartile of cholesterol intake was 2.2 (95% confidence interval 1.3-3.8). Although there was a significant trend (p less than 0.05), the effect of cholesterol suggested a threshold rather than a continuous gradient. The association of cholesterol and lung cancer was consistent for three of four ethnic groups analyzed separately. These results confirmed earlier findings by these investigators. The effect of cholesterol on the development of lung cancer was restricted to current cigarette smokers who smoked tobacco heavily and to squamous and small cell histologic types of lung cancer. Similar results were found for total, saturated, and, to some extent, unsaturated dietary fat, but because of the high correlation between fat and cholesterol (r = 0.76 for total fat and cholesterol), it was not possible to separate the effects of these nutrients.