We assessed the validity of a three-month physical activity questionnaire. The validation instrument was a seven-day self-report diary of physical activity and food intake, given to 113 randomly selected persons. We obtained Spearman correlations of 0.60, 0.48, and 0.91 and kappa scores of 0.36, 0.23, and 0.62 from the physical activity recall and diary for moderate, vigorous, and total activity. We conclude that the three-month recall questionnaire reasonably reflects activity in this community-based sample.