Objectives: The two purposes of this study were: (1) to estimate the yearly utilization rates and the cohort utilization rates of preventive health services provided for children by the National Health Insurance Program (NHIP) for the period from 1996 to 2001; and (2) to explore differences between these two kinds of estimates. Methods: We estimated and analyzed the differences based on a National Health Insurance Database that the National Health Research Institutes constructed for a random sample of the population in the NHIP. Results: From 1996 to 2000, the yearly total utilization rate of preventive health services for infants increased from 28.26% to 59.29%. From 1996 to 2001, the yearly utilization rates for children aged 1-3 and 3-4 increased from 35. 59% to 79.16% and from 10.58% to 26.70%, respectively. The trends of the cohort utilization rates were similar to those of the yearly utilization rates. Conclusions: The utilization level of preventive health services provided for children by the NHIP gradually improved from 1996 to 2001, with an overall increase of more than 100%. However, there is still much room for improvement, especially for the utilization level of children aged 3-4. The yearly utilization rate can be a good reference for predicting the cohort utilization rate of a cohort that has not been completely observed. Nevertheless, when making relevant inferences, we should pay attention to estimation errors due to changes in the cohort utilization rates, the number of births, and the distribution of timing for receiving preventive health services for children.