Description Usage Arguments Value References See Also
This function computes the two-dimensional kernel estimation needed for the
DSFM2D
funtion to work. Following Fengler and al. (2007), it
is using the product of two QuarticKernel1D
functions.
1 | KernelDensity2D(y, I, J, x1, x2, u, U, h)
|
y |
a list of numeric matrix of the data at each time t. |
I |
the total number of matrix in |
J |
a list of the total number of covariates in each matrix of |
x1 |
a list of numeric vector for the first dimension at each time t. |
x2 |
a list of numeric vector for the second dimension at each time t. |
u |
a numeric matrix of the estimation grid. |
U |
the length of |
h |
a numeric matrix of the bandwidth. |
It returns \hat{p}_t(u), \hat{q}_t(u) and the couples J_t\hat{p}_t(u) and J_t\hat{q}_t(u).
Fengler, Matthias R, Wolfgang K Haerdle, and Enno Mammen (2007). "A Semiparametric Factor Model for Implied Volatility Surface Dynamics". In: Journal of Financial Econometrics 5.2, pp. 189-218.
Borak, Szymon, Matthias R. Fengler, and Wolfgang K. Haerdle (2005)."DSFM Fitting of Implied Volatility Surfaces". In: 5th International Conference on Intelligent Systems Design and Applications (ISDA'05), pp. 526-531. IEEE.
Other kernel.functions: KernelDensity1D
,
NormalKernel1D
,
QuarticKernel1D
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.