If we want to estimate expected on individual securities or on a portfolio, we need theory. Estimates based on past data are inaccurate, partly because of the many ways in which people can mine past data. Explaining average return is like explaining variance but does little to help us estimate expected return. Theory can help, though, by telling us how factors are priced and why factors and securities are mispriced.
No takes yet. Share an insight, caveat, or question.
Fischer Black (1993) studied this question.