We estimate the time series and cross section of bond returns by way of three-stage ordinary least squares, which we label dynamic Fama-MacBeth regressions. Our approach allows for estimation of models with a large number of pricing factors. Even though we do not impose yield cross-equation restrictions in the estimation, we show that our bond return regressions generate a term structure of interest rates with small yield errors when compared with commonly reported specifications. We uncover specifications that give rise to lower pricing errors than do commonly advocated specifications, both in- and out-of-sample. Efficiency can be obtained through the generalized method of moments (GMM) estimator.
Download Info
To download:
If you experience problems downloading a file, check if you have the
proper application to
view it first. Information about this may be contained
in the File-Format links below. In case of further problems read
the IDEAS help
page. Note that these files are not on the IDEAS
site. Please be patient as the files may be large.
Publisher Info
Paper provided by Federal Reserve Bank of New York in its series Staff Reports with number
340.
References listed on IDEAS Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
John H. Cochrane & Monika Piazzesi, 2005.
"Bond Risk Premia,"
American Economic Review,
American Economic Association, vol. 95(1), pages 138-160, March.
[Downloadable!]
Other versions:
John H. Cochrane & Monika Piazzesi, 2002.
"Bond Risk Premia,"
NBER Working Papers
9178, National Bureau of Economic Research, Inc.
[Downloadable!] (restricted)
Cited by: (explanations, Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.)
Did you know? Citation analysis on IDEAS includes online papers that are freely accessible and whose text could be automatically analyzed, currently about 210000 papers.