
Financial Risk Manager Part 1
Get started today
Ultimate access to all questions.
The following sample autocorrelation estimates are obtained using 300 data points:
| Lag | 1 | 2 | 3 |
|---|---|---|---|
| Coefficient | 0.25 | -0.1 | -0.05 |
Compute the value of the Ljung-Box Q statistic.
Exam-Like
Community
TTanishq
Explanation:
The Ljung-Box Q statistic formula is:
[Q(m) = n \sum_{j=1}^{h} \left( \frac{n + 2}{n - j} \right) \rho_j^2 = n(n + 2) \sum_{j=1}^{h} \left( \frac{\rho_j^2}{n - j} \right)]
In this case, time lag ( m = 3 ).
Thus,
[Q(3) = 300(302) \left[ \frac{0.25^2}{299} + \frac{(-0.1)^2}{298} + \frac{(-0.05)^2}{297} \right] = 22.74]
Step-by-step calculation:
- n = 300 data points
- Οβ = 0.25, Οβ = -0.1, Οβ = -0.05
- Q(3) = 300 Γ 302 Γ [(0.0625/299) + (0.01/298) + (0.0025/297)]
- Q(3) = 90,600 Γ [0.000209 + 0.0000336 + 0.00000842]
- Q(3) = 90,600 Γ 0.00025102 = 22.74
The Ljung-Box Q statistic tests whether any of a group of autocorrelations of a time series are different from zero, and 22.74 is the correct calculated value.
Comments
Loading comments...