This chapter begins by describing the concept of robustness and then introduces the most widely recognized robust approaches for portfolio construction: Robust statistics, shrinkage estimation, Monte Carlo simulation (portfolio resampling), constraining portfolio weights, Bayesian approach (Black‐Litterman model) and stochastic programming. The equal‐weighted portfolio (also often referred to as the 1/N portfolio) can be considered as a robust version of the mean‐variance portfolio. The sensitivity of the mean‐variance portfolio arises from the expected return vector and the covariance matrix of returns, but the equal‐weighted portfolio is constructed without using these two inputs that are subject to estimation error. Utilizing the covariance matrix of returns is a better choice than the expected returns, not only because it forms portfolios with low risk, but also because the expected return of stocks is known to have a much larger effect on estimation error.