Nelson-Siegel function using IRFunction​Curve.fitN​elsonSiege​l

The below coding is an example for coding under "Fit Nelson-Siegel function to bond market data". The only change I did to this is that:

line one: settle date 30- Apr-2008 changed to 30-Apr-2000 lin ten : set the same date 30-Apr-2000

Bassically what I did is chaging the date that we estimate the in model. I got the codings from the below link: http://uk.mathworks.com/help/fininst/fitnelsonsiegelirfunctioncurve.html?nocookie=true

But if you run this code, the relevant NS parameters and the graph goes totally away from the data points. It doesn't looks like the function " IRFunctionCurve.fitNelsonSiegel" working properly. Could anyone give suggestion for this please .

The example give in the URL used settle date '30-Apr-2008' and if we give a date closer to this date, it closely fit the curve. But, if we give a date few years away, the fitted curve is totally away from the datapoints. This looks like the function only works if we give a settle date closer to lowest maturity date, which is 07-Mar-2009 in this case.

The below are the codings:

Settle = repmat(datenum('30-Apr-2000'),[6 1]); Maturity = [datenum('07-Mar-2009');datenum('07-Mar-2011');... datenum('07-Mar-2013');datenum('07-Sep-2016');... datenum('07-Mar-2025');datenum('07-Mar-2036')];

CleanPrice = [100.1;100.1;100.8;96.6;103.3;96.3]; CouponRate = [0.0400;0.0425;0.0450;0.0400;0.0500;0.0425]; Instruments = [Settle Maturity CleanPrice CouponRate]; PlottingPoints = datenum('07-Mar-2009'):180:datenum('07-Mar-2036'); Yield = bndyield(CleanPrice,CouponRate,Settle,Maturity);

NSModel = IRFunctionCurve.fitNelsonSiegel('Zero',datenum('30-Apr-2000'),Instruments);

NSModel.Parameters

% create the plot plot(PlottingPoints, getParYields(NSModel, PlottingPoints),'r') hold on scatter(Maturity,Yield,'black') datetick('x')