We examine the effect of changes in skilled-immigrant population shares in 98 Canadian cities between 1981 and 2006 on per capita patents. The Canadian case is of interest because its 'points system' for selecting immigrants is viewed as a model of skilled immigration policy. Our estimates suggest unambiguously smaller beneficial impacts of increasing the university-educated immigrant population share than comparable U.S. estimates, whereas our estimates of the contribution of Canadian-born university graduates are virtually identical in magnitude to the U.S. estimates. The modest contribution of Canadian immigrants to innovation is, in large part, explained by the low employment rates of Canadian STEM-educated immigrants in STEM jobs. Our results point to the value of providing employers with a role in the immigrant screening process.