I'm very much new to this area and I need to know on how to calculate the pricing error in Fama/French 5-Factor model. The evaluation was done using the Fama-Macbeth approach.

I did everything as shown in this answer. Fama-Macbeth second step confusion. The calculations were done in excel.

Now I'm having this with me,

enter image description here

That is the averaged, lambda values of Mkt-RF, SMB , HML , RMW , CMA. What is the pricing error in this case? and how to calculate it?

And how to estimate the SML line?

enter image description here

As I understood, is this the pricing error? But in Fama French 5 factor approch how can I calculate this?

Because there are 5 slopes I can be calculated since there are 4 beta values


1 Answer 1


John Cochrane (in Asset Pricing) p. 244:

Sampling error is, after all, about how a statistic would vary from one sample to the next if we repeated the observations.

Clarification on linear regression

Any linear regression $y = X \beta + \epsilon$ involves the following parameters and variables:

  • The unknown parameters, denoted as $\beta$ , a $(\mathrm{p} \times 1)$ vector
  • The dependent variables $Y$, a $(\mathrm{n} \times 1)$ vector
  • The independent variables $X$, a $(\mathrm{n} \times \mathrm{p})$ matrix
  • The residuals $\epsilon$, a $(\mathrm{n} \times 1)$ vector

What you are trying to get, are point estimates for your regression-coefficients $\beta$. However, this estimates are tied to the sample you are analyzing. If you calculate $\beta$ for another sample, you will get different coefficients (see the cite above). So in fact, you obtain expected values $X$, i.e. $\operatorname{E}(X)$, and as a measure of uncertainty of this estimate, you use $\sigma_{X}$.

Fama-MacBeth Regression

The Fama-MacBeth approach is a cross-sectional regression at each period of time: $$R_{t}^{ei}= \beta_{i}^{'}\lambda_t+a_{it}$$

where $R_{t}^{ei}$ is the excess-return of asset $i$ at time $t$ and $\beta_{i}^{'}$ denotes the estimated beta-factor of the stock.

What is the pricing error?

The pricing error is the part of the return $R_{t}^{ei}$, unexplained by your factors $\beta$, i.e. the pricing error is $a_{it}$.

You get a pricing error $\hat{a}_{it}$ for each cross-sectional regression, i.e. if you have e.g. a time-series of 120 month, you obtain 120 values for $\hat{a}_{it}$. After that, you just calculate the time-series average of these cross-sectional estimates:

$$\hat{a}_i = \frac{1}{T} \sum_{t=1}^{T}{\hat{a}}_{it}$$

How significant is this value $\hat{a}_i$?

You notice the hat on $\hat{a}_i$? That is because your estimate for $a_i$ is tied to the specific sample you are analyzing. How much would your $a_i$ differ, if you would e.g. have used other 120 month for your analysis?

We are used to deducing the sampling variance of the sample mean of a series $x_t$ by looking at the variation of $x_t$ through time in the sample. The estimate for the (squared) sampling error of $\hat{a}_i$ under the Fama-MacBeth assumptions is:

$$\sigma^2(\hat{a}_i) = \frac{1}{T^2} \sum_{t=1}^{T}{\left( \hat{a}_{it} - \hat{a}_i \right)^2}$$

, i.e. you divide the variance of $\hat{a}_{it}$ by $T$ (see here). The standard error $SE$ is then:

$$SE(\hat{a}_i) = \sqrt{\sigma^2(\hat{a}_i)}$$

Why do you need the standard error?

To test the statistical significance of you estimated pricing error $\hat{a}_i$. Under the null-hypothesis $a_i = 0$, your test-statistic is:

$$t_{score} = \frac{\hat{a}_i}{SE(\hat{a}_i)} \sim\mathcal{T}_{k}$$

$t_{score}$ has a t-distribution with $k = T-p$ (i.e. the number of observations $T$ minus the amount $p$ of estimated parameters $\beta_i$ in your regression) degrees of freedom if the null hypothesis is true.

  • $\begingroup$ I have one question left though. Is the alpha the residual of the Fama Mac Beth Regression or an intercept I estimate? And also, is this average alpha calculated for every asset i= 1,...,n? If I had 20 stocks I regress e.g. do I have to calculate an alpha (and test statistic) for every stock? $\endgroup$
    – J.Pop
    Commented Feb 13, 2019 at 13:00
  • $\begingroup$ Alpha $a_t$ denotes the average error of a cross-sectional regression estimate you run at each point of time $t$. If you have e.g. 120 monthly returns of e.g. 100 stocks, you obtain an $a_t$ for each of the 120 cross-sectional regressions. The test statistic is derived from this time series of 120 $a_i$'s. $\endgroup$ Commented Feb 13, 2019 at 17:15
  • $\begingroup$ @skoestlmeier So $\hat{a}_{it}$ is the average pricing errors across assets at each time t? And how is the test of $t_{score} = \frac{\hat{a}_i}{SE(\hat{a}_i)} \sim\mathcal{T}_{k}$ different from the $\hat{\alpha}^{'}cov(\hat{\alpha})^{-1}\hat{\alpha}\sim\chi_{N-1}^2$ as in Cochrane (2011)? $\endgroup$
    – SNU
    Commented Apr 25, 2019 at 12:33
  • $\begingroup$ The main difference is that a simple t-test as a univariat method just holds for the one specific time-series for $\hat{\alpha}_i$ you are looking for. What you describe is the GRS-test where i recommend you to read this wonderful answer. In fact, it is a jointly test for the significance of the estimated values across all $\hat{\alpha}_i$ simultaneously. $\endgroup$ Commented Apr 26, 2019 at 11:14
  • $\begingroup$ @skoestlmeier Many thanks for your reply and the link! $\endgroup$
    – SNU
    Commented Apr 30, 2019 at 20:14

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.