The best-fitting model(s) of equal risk contribution: evidence from environmental-friendly portfolio

Purpose - This research aims to select the best-fitting model(s) of equal risk contribution portfolios (ERC). ERC is a robust estimation in the absence of reasonable expectations about future returns. Design/methodology/approach - The portfolio consists of five environmental-friendly exchange-traded funds (ETFs). It applies equal risk optimization, beneficial when the assets are firmly linked, such as the ETFs. This paper operationalizes 20 covariance models in portfolio construction, and a portfolio with classic covariance is the benchmark to beat. To select the best-fitting model(s), the paper applies statistical inferences of the model confidence set. This research also constructs the newly-developed minimum connectedness optimization method and utilizes maximum drawdown as the primary evaluation tool. Findings - The outbreak of COVID-19 hugely impacts the portfolio drawdown. The results also show that the classic covariance is hard to beat, partly explained by estimation error and model misspecification. This paper suggests that equal risk contribution can benefit from copula-based covariance. It consistently and significantly outperforms the other models in various robustness tests. Practical implications - In the absence of substantial predictions about future returns and the existence of strongly linked assets, selecting appropriate portfolio components by risk contribution is a sound choice. Originality/value - This is the first paper to select the best-fitting model(s) of ERC portfolio during the COVID-19.