Scientific Beta

The first part of this paper highlights the sources of a lack of robustness in the design of smart beta strategies and describes the methods employed by Scientific Beta to improve robustness. The second part of the paper presents the protocol Scientific Beta employs to measure robustness, through its four dimensions: Conditional performance and risk analysis to various regimes; Stability of performance and risk over time; Robust statistical inference of the significance of a strategy’s outperformance; and Out-of-sample testing to confirm robustness.

The first part of this paper discusses why robustness is relevant for investors in smart beta strategies and describes the sources of a lack of robustness. We further explain the need for robustness checks in performance analysis of such strategies and the various methods by which Scientific Beta improves robustness.

The second part discusses measurements of robustness and describes the robustness protocol that we employ internally to assess the robustness of newly developed strategies. This toolkit of robustness tests is quite relevant to investors and can be used in their evaluation of smart beta strategies. It is notably based on an analysis of conditional performance in a multi-dimensional context (market, volatility, sector, factors, and macroeconomic variables). It also draws on an evaluation of robust statistical inference and on out-of-sample robustness tests of the performance and risk of the indices proposed using long-term data. Finally, we apply our robustness protocol to an example strategy and evaluate the outcome against its proposed objectives.