Factor investing is popular, and its adoption is accelerating. One reason it is increasingly being embraced is that portfolio return expectations seem to be evidence based. However, much of the so-called evidence consists of repeated analysis of the very datasets used to derive an investment model in the first place. To mitigate this trap, the authors estimate the risk premiums earned from factor investing over very long periods (up to 117 years) and across many markets (up to 23). They report on the long-term profitability of following strategies based on market capitalization, value versus growth, dividend yield, stock-return momentum, and low-volatility investing.