Estimating Factor Exposures and Returns in APT Models
Summary
The document explains how to estimate asset exposures to factors and how to interpret factor-attributed returns in an Arbitrage Pricing Theory framework. For a single factor, exposure is the covariance between factor and asset returns divided by the factor’s variance. With several factors, exposures are generally estimated together through a multiple regression, often using ordinary least squares or generalized method of moments; they are not simply separate correlations or covariance ratios.
It describes factor returns as dependent on how the factors are constructed. For example, a factor formed from a group of stocks might use a capitalization-weighted return for that group. Another approach estimates factor risk premia by regressing expected asset returns on estimated betas, with Fama–MacBeth regression cited as a common procedure. Factor construction may use clustering or principal component analysis. The discussion distinguishes APT factors that represent co-moving asset groups from state variables in intertemporal asset pricing, and notes that practical choices depend on the model and the factors being tested.
Key ideas
- In a single-factor model, beta is covariance with the factor divided by the factor’s variance.
- Multiple factor exposures are typically estimated jointly with regression and can differ from individual correlations.
- The method for calculating a factor’s return depends on how the factor is defined and constructed.
- Factor risk premia can be estimated by regressing asset returns on estimated exposures.
- Clustering and principal component analysis are possible approaches to forming factors.
Tags
Full text
# How to perform risk factor calculation?
# How to perform risk factor calculation?
I am studying Arbitrage Pricing Theory (APT) and I have a question about calculating factor exposures.
Assume:
\begin{equation} r = \beta_1r_1 + \beta_2r_2 + ... + \beta_kr_k + r_e \end{equation}
Where:
$\beta_i$ is the exposure of the asset to a factor
$r$ is the return attributable to a factor
I believe that beta will be the covariance of the factor with the underlying asset. Is this correct? Also how is the return attributable to a specific factor calculated? Is there a single way this is done or are there a variety of approaches?
## Answer by chrisaycock (score 6, accepted)
https://quant.stackexchange.com/a/793
> I believe that beta will be the covariance of the factor with the underlying asset. Is this correct?
Close, it's the covariance divided by the variance of the factor.
\begin{equation} \beta_{f,a} = \frac{\sigma_{f,a}}{\sigma^2_f} \end{equation}
> Also how is the return attributable to a specific factor calculated? Is there a single way this is done or are there a variety of approaches?
That depends on how you derive your factors. As mentioned in this earlier question, I once derived factors with cluster analysis. Thus, each factor was really a collection of highly correlated large-cap stocks. That meant the factor return was simply the cap-weighted average of all constituent stock returns, just like in a stock index.
## Answer by Richard Herron (score 10)
https://quant.stackexchange.com/a/801
I don't have much to add, but wanted to address the "price of risk" question.
APT is kind of "economics"-free and tries to price assets without the utility maximization required in CAPM/ICAPM. Ross's APT observes that groups of assets move together (e.g., tech stocks) and that is the risk you're bearing because the idiosyncratic risk, like the firing of HP's CEO, can be diversified away. Because this risk is easily diversifiable, the market won't pay you to take it. So in your APT model these factors are returns to asset classes, industries, etc.
Although the model looks the same, in Merton's ICAPM, the factors are state variables (e.g., industrial production, inflation). These are purely academic points -- in practice you run a multivariate regression with return on the LHS and whatever factors you think are priced on the RHS. OLS and GMM are common. So you'll estimate $$E ~ \left[ ~r_i~ \right] = \alpha_i + \beta_i^1 f_1 + \beta_i^2 f_2 + \ldots + \beta_i^k f_k$$
Your final question.
> Also how is the return attributable to a specific factor calculated?
Now you regress the returns back on the betas. $$E ~ \left[ ~r_i~ \right] = \sum_{j \in K} \lambda_j \beta_i^j$$
Where $\lambda_j$ is the return to factor $j$. Typically the Fama-MacBeth approach is used here. If you've done it correct and found something, $\lambda > 0$ (i.e., the market is paying you to take this risk).
## Answer by shabbychef (score 3)
https://quant.stackexchange.com/a/800
If you have a series of observations of the return as a vector, $\mathbf{r}$ with corresponding observations of the factor returns in matrix $Z$, then the least squares estimate of the vector of betas is $$\hat{\beta} = \left(X'X\right)^{-1} X'\mathbf{r},$$ where $X$ is the matrix with $Z$ and a column of all ones (for the intercept term). The last value of $\hat{\beta}$ will be the estimate of the 'idiosyncratic' return. In general, the estimate of the $j$th coefficient, $\hat{\beta_j}$ will not be correlation of the return to the return of the $j$th factor, nor will it be that value adjusted for the volatility of the factor.
If you have only one factor (in which case it is CAPM, not APT), then the computation does simplify. Also, if the sample returns of the different factors are independent vectors (highly unlikely to happen by accident), you will get the simplification.
See wikipedia for more on multiple linear regression.
## Answer by SBF (score -1)
https://quant.stackexchange.com/a/794
You can use PCA as well, not the cluster analysis.Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.