Multivariate Time Series Fit

See also: Fitting in ModelRisk, Vose Multivariate Time Series window

The Multivariate Time Series Fit window from ModelRisk

Quantities that move together in time are typically modeled using multivariate time series ("MultiTS") models. MultiTS models allow one to easily account for the relations and correlation that exist between the "marginal" components.

A typical example of a situation where one can use multivariate time series is yield curve modeling for example: where we model the interest rates for different times-to-maturity. At any point in time an interest rate for some time to maturity (say, 5 years) is typically related to:

• the (immediate) past,

• the interest rates at for other times-to-maturity (e.g. 1 month, 1 year, 10 years...)

Use the ModelRisk Multivariate Time Series Fit window to fit a number of multivariate time series models to historical data.

To see the output functions of this window, click here.

Window elements

In the source data region you can specify an array of cells in the spreadsheet with data to fit to. Select between data in rows and data in columns to specify the correct orientation - be careful to select the correct orientation as an error will produce a fit, but it will be nonsensical.

On the lower left corner of the window you see a matrix with which you can specify which two series to show a preview plot for. Use the check mark View all series (marked by default) to display all component time series.

In the viewing controls region below the preview plot you can specify the number of forecasts to display (an integer greater than 1), whether to fix the axis-scale and whether to display LogReturns or actual values.

For the output of the fitted series, you can choose to orient the simulated values in columns or rows - so it is possible to have the historical data in one orientation (e.g. rows) in the spreadsheet, and the forecasted values in another (e.g. columns).