The level of uncertainty will depend on several factors: the nature of the functional form used in the multivariate analysis; the type of econometric technique employed; the appropriateness of the statistical assumptions embedded in the model or technique; the comprehensiveness of the variables included in the analysis; and the accuracy of the data that are utilized. [...] The proportion of the population that spent at least the latter part of their formative years in a large urban area and obtained a degree is almost twice that of those that spent their formative years in rural parts of Canada. [...] One is to decompose the growth in the number of degree holders over the 1996-to-2001 period into that which is due to migratory flows (domestic and international) and that which is due to in situ growth of degree holders. [...] To the extent that the lamination of degree holders over this five-year period is representative of past laminations, decomposing growth in this way provides a perspective on the origins of the differences in degree shares of urban and rural areas. [...] To identify the relative contribution of these three sources to degree-holder growth, we impose the counterfactual that no degree holders were added to the age cohort over the previous five years; that is, the number of degree holders in year t was the same as that in year t-5.