Modern finance is built on linear regression. Hence Asness’s textbook use of linear regression is brilliant because simplicity is beautiful. He uses Aristotelian logic to elegantly bring out the information content buried in hedge fund performance.
The industry indeed needs assistance in knowing how to measure true alpha and how an apple to apple comparison can be done between active managers and hedge funds. Asness systematically proves that he is not only true to his vocation but also that he is inextricable from the Fama and French linear regression ecosystem.
In the world of data science, quantum computing, black holes and space X flights, the investors, journalists, the public at large and presumably asset managers should be more open to Asness's approach. For the few who are on the fence and struggling to understand how the quants are changing everything from finance to the cryptographic world, I have made a sequential summary of Asness’s regression logical steps.
In very simple words, consider the data you have to study as a set of points across Y and X-axis. Regression is the approach to fit a straight line between the data points so that it has the closest distance from all the points. But why do we fit a line? Because the objective is to find meaning, behavior, causality in the data.
Better you understand your data, better you can drive meaning out of it. The line and its slant allow you to get a snapshot of what happened in the past to the data and potentially get an insight into the future. This fitting of the line is at the heart of many quant systems today. Line fitting is at the heart of two Nobel prizes (1990 and 2013) and success in the quantitative asset management business is believed to be a function of better line fitting.
Sequentially this is what Asness does...
He takes hedge fund returns data as y and market return S$P 500 as x data point and he fits a line, which gets him the angle of the line and where it starts. Based on that Asness proves that hedge fund comparison to market (S&P500) as one to one is incorrect because the slant in the line (sensitivity or coefficient) is less than what is assumed by the industry. The relationship should be more like 0.46 to 1.
Eugene Fama got his fame and Nobel prize because of his 1960's work on market theories which were around the studying the slant. He also focused on extracting information content out of data and studying market returns. He found that the market was important but there was more than one robust behavior inside the market. Fama enhanced the market factor by two more factors, ‘Size’ and ‘Value’.
Fama’s size factor that Asness uses in his article suggests that a portfolio return would be higher if it had more small size companies than large size companies, technical jargon refers to this as ‘Size bias’. This meant that portfolio managers skill could only be judged net of the size factor as making a portfolio with small-sized companies required zero skill.
This is what Asness does showing that the hedge fund stripped off the size premium using the slanting line technique has a different look. When we add a new factor, it adds a new dimension and the line becomes a plane.
Y = C + Sensitivity (mkt factor) + Sensitivity ’ (Size factor)
Next Asness shifts the focus to the traditional active manager and repeats the slanting line method to strip the luck from the hedge fund manager’s skill (alpha) and proves that hedge funds have done better compared to active funds while active managers have underperformed one way.
Finally, Asness brings you to an apple to apple comparison by comparing the correlation of hedge funds vs. active managers.
His conclusion, hedge funds really do not add value vs. active managers, there is limited differentiation and nothing special left in hedge funds.
Slanting line education is how the world has advanced science in finance. The financial profession has fallen in love with the line and refuses to let go. The slanting line was a start. Science has moved ahead beyond regression. The science was started back in 1886 by Francis Galton who saw that natural data tended to fall back to mean. In the slanting line case, the line finds the “middle” of the data. Jules Regnault talked about it before Galton in the mean deviation of returns.
Now for every claim about the effectiveness of the slanting line approach, there are a host of other claims which suggests that the slanting line methodology is weak science. Two Nobel prizes have been awarded to academicians who suggested that the line works because of human psychology embedded in the data and not because of the data itself. A few of the challengers have gone ahead and showcased that the risk and return equation is itself broken and not always low risk leads to low returns and vice versa. This means that the slanting line can move from a positive slope to a negative slope.
This is why Nobel Prize-winning theories have failed to translate into robust alpha. Slanting line methodology and many other linear modeling approaches are textbook models that can’t compete with the computational heavy new age quant models which don’t rely on linear models but understand that markets are non-linear and complex by nature.
The world today has moved beyond the assumption that psychology drives data to understand that not assuming causality could be a better approach if you want to discover robust behavior in data. Reinforcement learning, deep learning, lazy learning etc. offer you a real shot at moving beyond simplistic extrapolation of the past data to anticipate the future. Though such new models are not free of their biases, at least they are not building assets and businesses on old assumptions from a tape reading world which is long dead. We are entering the world of alpha bots which don’t need to be trained for linear regression, they learn, adapt and learn again. The new manager you may hire may not be a human, it might be a bot named 01101111 and it may very well understand why naive diversification tends to work better than assuming specific factor exposure. It may know when size factor can fail and when it may continue to work
In an industry that suffers from underperformance, teaching the world about the history of regression-based metrics though important takes us away from the real fact that it's the same slanting line approach that has caused this underperformance in the first place. When you build models on somebody else's assumptions, you are operating a risky business. The market was never linear, it was always non-linear and size is a proxy which works and fails alternatively. The technology 40 years back was weak and simplification was a necessity. But to talk about linear regression both as an alpha measurement or alpha generation process is dangerous. Moreover, understanding inefficiencies do not automatically lead to model robustness. If Fama can himself admit that he doesn't know why the Size premium works, adjusting everything for size factor is an objective measurement but it's not enough to take the industry out of its innovation less state.
We have a real problem not just for investors who rightly have decided to not pay for underperformance but for asset managers who will be forced to innovate once the new wave of systematic, scientific and replicable models start delivering sustainable and robust alpha and then suddenly the industry will wonder how did hedge funds stage such a dramatic recovery.