The Nobel Memorial Prize for Robert F. Engle



We could estimate the parameters 0. = {β1t, β2t, β3t, λt} by nonlinear least squares, for each month t.
Following standard practice tracing to Nelson and Siegel (1987), however, we instead fix λt at a
prespecified value, which lets us compute the values of the two regressors (factor loadings) and use
ordinary least squares to estimate the betas (factors), for each month
t. Doing so enhances not only
simplicity and convenience, but also numerical trustworthiness, by enabling us to replace hundreds of
potentially challenging numerical optimizations with trivial least-squares regressions. The question
arises, of course, as to an appropriate value for λ
t. Recall that λt determines the maturity at which the
loading on the medium-term, or curvature, factor achieves it maximum. Two- or three-year maturities are
commonly used in that regard, so we simply picked the average, 30 months. The λ
t value that
maximizes the loading on the medium-term factor at exactly 30 months is λ
t=0.0609.

Applying ordinary least squares to the yield data for each month gives us a time series of
estimates of {fi1
1, β21, β31} and a corresponding panel of residuals, or pricing errors. Note that, because
the maturities are not equally spaced, we implicitly weight the most “active” region of the yield curve
most heavily when fitting the model.9 There are many aspects to a full assessment of the “fit” of our
model. In Figure 4 we plot the implied average fitted yield curve against the average actual yield curve.
The two agree quite closely. In Figure 5 we dig deeper by plotting the raw yield curve and the three-
factor fitted yield curve for some selected dates. Clearly the three-factor model is capable of replicating
a variety of yield curve shapes: upward sloping, downward sloping, humped, and inverted humped. It
does, however, have difficulties at some dates, especially when yields are dispersed, with multiple
interior minima and maxima. Overall, however, the residual plot in Figure 6 indicates a good fit.

In Table 2 we present statistics that describe the in-sample fit. The residual sample
autocorrelations indicate that pricing errors are persistent. As noted in Bliss (1997b), regardless of the
term structure estimation method used, there is a persistent discrepancy between actual bond prices and
prices estimated from term structure models. Presumably these discrepancies arise from persistent tax
and/or liquidity effects.10 However, because they persist, they should vanish from fitted yield changes.

In Figure 7 we plot {β1121 ,331} along with the empirical level, slope and curvature defined
earlier. The figure confirms our assertion that the three factors in our model correspond to level, slope

9 Other weightings and loss functions have been explored by Bliss (1997b), Soderlind and
Svensson (1997), and Bates (1999).

10 Although, as discussed earlier, we attempted to remove illiquid bonds, complete elimination is
not possible.



More intriguing information

1. Implementation of Rule Based Algorithm for Sandhi-Vicheda Of Compound Hindi Words
2. An institutional analysis of sasi laut in Maluku, Indonesia
3. Moffett and rhetoric
4. 09-01 "Resources, Rules and International Political Economy: The Politics of Development in the WTO"
5. Making International Human Rights Protection More Effective: A Rational-Choice Approach to the Effectiveness of Ius Standi Provisions
6. Managing Human Resources in Higher Education: The Implications of a Diversifying Workforce
7. Short report "About a rare cause of primary hyperparathyroidism"
8. An Economic Analysis of Fresh Fruit and Vegetable Consumption: Implications for Overweight and Obesity among Higher- and Lower-Income Consumers
9. Group cooperation, inclusion and disaffected pupils: some responses to informal learning in the music classroom
10. Towards a Mirror System for the Development of Socially-Mediated Skills