Interpolate yields

For econometric discussions not necessarily related to EViews.

Moderators: EViews Gareth, EViews Moderator

jbian
Posts: 6
Joined: Tue Jan 12, 2016 6:44 am

Interpolate yields

Postby jbian » Tue Jan 12, 2016 6:48 am

Hi all,

the data on Treasury yields are only available in one to 30 years of maturities. How can I interpolate them into fixed maturities
of 3, 6, 9, 12, 15, 18, 21, 24, 30, 36, 48, 60, 72, 84, 96, 108, and 120 months?

Hope someone can help me. Thanks a lot!!

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Interpolate yields

Postby startz » Tue Jan 12, 2016 9:32 am

Some of these are easy. The 3 month yield is available. The 12 month yield is a lot like the 1 year yield.

For others, you might want to fit a Nelson-Siegel yield curve and then use that for interpolation. You should also decide whether you care about the distinction between coupon and coupon-free bonds.

jbian
Posts: 6
Joined: Tue Jan 12, 2016 6:44 am

Re: Interpolate yields

Postby jbian » Tue Jan 12, 2016 2:16 pm

Hi startz,

thx for your reply. The dataset I have is the zero-coupon yields (with maturities ranging from 1 year to 12 years) calculated by Gürkaynak, Sack and Wright (2006) based on "a large set of outstanding Treasury notes and bonds". I want to use them to back out the 1-, 3-, 6-, 12-month etc. yield. Do you know a program or algorithm dealing with the calculation?

Thx

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Interpolate yields

Postby startz » Tue Jan 12, 2016 2:59 pm

The 3 month and 6 month rates are observable, and available in the FRED database. The translation from the 1 year rate to the 12 month rate is surprisingly easy to figure out. Other rates can be figured out by estimating Nelson-Siegel curves, but this will require some work.

jbian
Posts: 6
Joined: Tue Jan 12, 2016 6:44 am

Re: Interpolate yields

Postby jbian » Mon Jan 18, 2016 11:21 am

Hi startz,

I believe these observable 3 month and 6 month rates you mentioned are the Constant Maturity Treasury (CMT) yields? These yields are bond equivalent (coupon bearing) according to the FED's description. Do you know how to extract zero coupon yields from these CMT yields? Thx

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Interpolate yields

Postby startz » Mon Jan 18, 2016 11:25 am

3 and 6 month treasury bill rates are available. These don't have coupons.

jbian
Posts: 6
Joined: Tue Jan 12, 2016 6:44 am

Re: Interpolate yields

Postby jbian » Mon Jan 18, 2016 11:38 am

Do you mean the rate published here https://www.treasury.gov/resource-cente ... data=yield ? So I can interpret them as zero coupon yields?

But on the FED's webpage is says
"Does the yield curve assume semiannual interest payments or is it a zero-coupon curve?

The yield curve is based on securities that pay interest on a semiannual basis, the yields are considered "bond-equivalent" yields and the yield curve is considered a Par Yield Curve. Treasury does not create or publish daily zero-coupon curve rates."

Little bit confused now with all the definitions of the yields now...

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Interpolate yields

Postby startz » Mon Jan 18, 2016 11:44 am


jbian
Posts: 6
Joined: Tue Jan 12, 2016 6:44 am

Re: Interpolate yields

Postby jbian » Mon Jan 18, 2016 11:59 am

Thx!

jbian
Posts: 6
Joined: Tue Jan 12, 2016 6:44 am

Re: Interpolate yields

Postby jbian » Mon Jan 18, 2016 1:10 pm

Hi startz,

do you not where can I find rates on Treasury Bill futures? Because I also need the forward rates...

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Interpolate yields

Postby startz » Mon Jan 18, 2016 1:19 pm

'Fraid not off-hand.


Return to “Econometric Discussions”

Who is online

Users browsing this forum: No registered users and 2 guests