Background and Purpose-Many studies have reported increases in daily cardiovascular mortality and hospital admissions associated with increases in levels of air pollutants. However, little is known about the relationship between hospital admissions for stroke and air pollution. This study was undertaken to determine whether there is an association between air pollution and hospital admissions for stroke in Kaohsiung, Taiwan. Methods-Data on a total of 23 179 stroke admissions were obtained for the period 1997 through 2000. The relative risk of hospital admissions was estimated with a case-crossover approach. Results-In the single-pollutant models, on warm days (Ն20°C), significant positive associations were found between levels of PM 10 , NO 2 , SO 2 , CO, and O 3 and both primary intracerebral hemorrhage and ischemic stroke admissions. On cool days (Ͻ20°C), only CO levels and ischemic stroke admissions were significantly associated. For the 2-pollutant models, PM 10 and NO 2 remained consistently and significantly associated with admissions for both types of stroke on warm days. We observed estimated relative risks of 1.54 (95% confidence interval [95%], 1.31 to 1.81) and 1.56 (95% CI, 1.32 to 1.84) for primary intracerebral hemorrhage for each interquartile range increase in PM 10 and NO 2 . The values for ischemic stroke were 1.46 (95% CI, 1.32 to 1.61) and 1.55 (95% CI, 1.40 to 1.71), respectively. The effects of CO, SO 2 , and O 3 were mostly nonsignificant when either NO 2 or PM 10 was controlled for. Conclusions-This study provides an association between exposure to air pollution and hospital admissions for stroke.