This paper is an attempt to answer the long standing question of whether more affluent households save a larger fraction of their income. The major difficulty in empirically assessing the relationship between incomes and saving rates is to construct a credible proxy for long-run income - purged of transitory fluctuations and measurement error. The Canadian Family Expenditure Survey provides us with both unusually good data on savings rates and potential predictors with which we can construct reliable long-run income proxies. Our empirical analysis suggests that the estimated relationship between saving rates and long-run incomes is sensitive to the predictor used to proxy long-run income. Nevertheless, our preferred estimates indicate that, except for poorest households (who simply do not save), saving rates do not differ substantially across predicted long-run income groups.