WeightedDesmooth_AR1
[this page | pdf | back links]
Function Description
Returns an array corresponding to the AR(1) weighted
de-smoothed (or ‘de-correlated’) values of a series, as described in the book Extreme Events. This
involves:
(a) Postulating
(for, say, a return series) that there is some underlying ‘true’ return series,
, and that the observed
series, 
, derives from it via a
first order autoregressive model, 
;
(b) Identifying the value
of 
(between 0 and 0.5) for
which has zero weighted first
order correlation (which implies that the weighted covariance between 
and 
is zero; and
(c) Using this value
of deriving using the following
formula:
In step (b) we weight the elements in the covariance
computation using weights 
(where 
corresponds to the
weight given to the component arising from the term in 
.
The value of in (b) can be accessed
using MnWeightedDesmooth_AR1_rho.
If the weights are equal then returns the same as MnDesmooth_AR1.
NAVIGATION LINKS
Contents | Prev | Next
Output type / Parameter details
Output type: Double()
| Parameter Name | Variable Type | Description |
| InputArray | Double() | Input Array to be desmoothed |
| WeightArray | Double() | Array of weights to apply in desmoothing algorithm |
Links to:
-
Interactively run function
-
Interactive instructions
-
Example calculation
-
Output type / Parameter details
-
Illustrative spreadsheet
-
Other Statistical functions
-
Computation units used
Note: If you use any Nematrian web service either programmatically or interactively then you will be deemed to have agreed to the Nematrian website License Agreement