Analyzing the performance of different factors is an important part of the development of a factor-based trading strategy. A researcher may construct and analyze over a hundred different factors, so a process to evaluate and compare these factors is needed. Most often this process starts by trying to understand the time-series properties of each factor in isolation and then study how they interact with each other.

To give a basic idea of how this process may be performed, we use the five factors introduced earlier in this chapter: EBITDA/EV, revisions, share repurchase, momentum, and earnings growth. These are a subset of the factors that we use in the factor trading strategy model discussed later in the chapter. We choose a limited number of factors for ease of exposition. In particular, we emphasize those factors that possess more interesting empirical characteristics.

Exhibit 12.5(A) presents summary statistics of monthly returns of long-short portfolios constructed from these factors. We observe that the average monthly return ranges from −0.05% for the earnings growth to 0.90% for the momentum factor. The *t*-statistics for the mean return are significant at the 95% level for the EBITDA/EV, share repurchase, and momentum factors. The monthly volatility ranges from 3.77% for the revisions factor to 7.13% for the momentum factor. In other words, the return and risk characteristics among factors vary significantly. We note that the greatest monthly ...

Start Free Trial

No credit card required