The Nobel Memorial Prize for Robert F. Engle



and curvature. The correlations between the estimated factors and the empirical level, slope, and
curvature are pφ1
t,lt) = 0.97, p(β2t,st) = -0.99, and p(β3t,ct) = 0.99, where (lt, st, ct) are the empirical
level, slope and curvature of the yield curve. In Table 3 and Figure 8 (left column) we present
descriptive statistics for the estimated factors. From the autocorrelations of the three factors, we can see
that the first factor is the most persistent, and that the second factor is more persistent than the third.
Augmented Dickey-Fuller tests suggest that β
1 and β2 may have a unit roots, and that β3 does not.11
Finally, the pairwise correlations between the estimated factors are not large.

Modeling and Forecasting Yield Curve Level, Slope and Curvature

We model and forecast the Nelson-Siegel factors as univariate AR(1) processes. The AR(1)
models can be viewed as natural benchmarks determined a priori: the simplest great workhorse
autoregressive models. The yield forecasts based on underlying univariate AR(1) factor specifications

are:
where

yt.h /1 (τ) = β1, t+h /1 + P2, t+h /1


1 -e ~λτ
λτ


Рз, t+h /t


where


βt c c. + γ.β.,, i = 1, 2, 3,
/, t+h /1        i ∙i4t,               , , ,


л

and ci and ^i are obtained by regressing βit


on an intercept and 3 i th .12


For comparison , we also produce yield forecasts based on an underlying multivariate VAR(1)


specification, as:


yth/ /1 (τ) = P1, t+h /1 + P2, t+h /1


1 -e ~λτ
λτ


Рз, t+h /1


1 -e λτ

--------e

λτ


-λτ

/


11 We use SIC to choose the lags in the augmented Dickey-Fuller unit-root test. The MacKinnon
critical values for rejection of hypothesis of a unit root are -3.4518 at the one percent level, -2.8704 at the
five percent level, and -2.5714 at the ten percent level.

12 Note that we directly regress factors at t+h on factors at t, which is a standard method of
coaxing least squares into optimizing the relevant loss function,
h-month-ahead RMSE, as opposed to the
usual 1-month-ahead RMSE. We estimate all competitor models in the same way, as described below.

10



More intriguing information

1. Fortschritte bei der Exportorientierung von Dienstleistungsunternehmen
2. Analyse des verbraucherorientierten Qualitätsurteils mittels assoziativer Verfahren am Beispiel von Schweinefleisch und Kartoffeln
3. INSTITUTIONS AND PRICE TRANSMISSION IN THE VIETNAMESE HOG MARKET
4. The Role of Immigration in Sustaining the Social Security System: A Political Economy Approach
5. Input-Output Analysis, Linear Programming and Modified Multipliers
6. Industrial Cores and Peripheries in Brazil
7. The name is absent
8. Menarchial Age of Secondary School Girls in Urban and Rural Areas of Rivers State, Nigeria
9. Ability grouping in the secondary school: attitudes of teachers of practically based subjects
10. The name is absent