Assume that I have a process $y_t$ such that $$y_t = c + \phi_1 y_{t-1} + \ldots + \phi_p y_{t-p} + u_t$$ where $u_t$ is i.i.d. white noise such that $E[u_t] = 0, \forall t$ and $E[u_t u_s]$ is equal to $\sigma^2$ if $t = s$ and 0 otherwise. Define $$x_t = \begin{bmatrix} 1 \\ y_{t-1} \\ \vdots \\ y_{t-p} \end{bmatrix} \quad \text{and} \quad \phi = \begin{bmatrix} c \\ \phi_{1} \\ \vdots \\ \phi_{p} \end{bmatrix}$$ so that we can write $$y_t = x_t'\phi + u_t.$$ This process can be estimated by OLS such that $$\hat{\phi} = \left(\sum_{t = 1}^{T} x_t x_t' \right)^{-1} \sum_{t = 1}^{T} x_t y_t$$ and $\sigma^2$ can be estimated by $$s^2 = \frac{1}{T - p - 1} \sum_{t = 1}^{T} \left(y - x_t'\hat{\phi} \right)^2.$$

Note that this analysis requires that we have access to $T + p$ samples of $y_t$ denoted as $(y_{-p+1}, y_{-p+2}, \ldots, y_0, y_1, \ldots, y_T)$. However, I have noticed that implementation of this result is very ambiguous. In a practical setting, you would have only $T$ observations from which estimation would be carried out using $T-p$ so that all the previous summations go from $p+1$ to $T$ and thus the correction should be done using $T - 2p - 1$. Using the R command ar with method ols uses $T - p$, while in a multivariate setting, package vars uses $T - kp - 1$ where $k$ is the number of endogenous variables.

Could someone explain the intuition behind these corrections over what I would assume to be the correct one (using $T - 2p - 1$)? I know that asymptotically it is all the same, but the corrections are done precisely in order to improve finite-sample properties and so I'm not sure why you wouldn't use such results.


1 Answer 1


As you point out, asymptotically it is all the same. I am not aware of a consensus in the literature as to which, if any, of the corrections improves finite-sample performance. I would also not expect such results to be clear-cut, as they might depend on things like the signal-to-noise ratio, the persistence of the AR process etc.

I would rather say that some of these corrections are inspired by the exact finite-sample results available in the linear regression model with strictly exogenous regressors and normally distributed error terms, where these corrections ensure exact t- and F-distributions for test statistics.


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.