Objective. This article compares prevalence estimates of excess weight among Canadian children and youth according to three sets of body mass index (BMI) reference cut-points. The cut-points are based on growth curves generated by the World Health Organization (WHO), the International Obesity Task Force (IOTF), and the US Centers for Disease Control (CDC). A secondary objective is to compare estimates by method of data collection. Methods. Prevalence estimates of overweight and obesity were produced for 2- to 17-year-olds using the three sets of BMI cut-points. Estimates are based on data from 8 661 respondents from the 2004 Canadian Community Health Survey and 1 840 respondents from the 1978/79 Canada Health Survey. In both surveys, the height and weight of children were measured. Results. The 2004 prevalence estimate for the combined overweight/obese category is higher (35%) when based on the WHO cut-points compared with the IOTF (26%) or CDC (28%) cut-points. Estimates of the prevalence of obesity are similar based on WHO and CDC cut-points (13%), but lower when based on IOTF cut-points (8%). Absolute differences in excess weight estimates between 1978/79 and 2004 are similar based on the three sets of cut-points, but the relative increase is greater when based on the IOTF cut-points. Estimates vary substantially by method of data collection. Conclusion. When interpreting prevalence estimates of overweight and obesity for children and youth, it is important to consider the definitions used and the method of data collection.