Abstract
For many economic time-series variables that are observed regularly and frequently, for example weekly, the underlying activity is not distributed uniformly across the year. For the aim of predicting annual data, one may consider temporal aggregation into larger subannual units based on an activity timescale instead of calendar time. Such a scheme may strike a balance between annual modeling (which processes little information) and modeling at the finest available frequency (which may lead to an excessive parameter dimension), and it may also outperform modeling calendar time units (with some months or quarters containing more information than others). We suggest an algorithm that performs an approximate inversion of the inherent seasonal time deformation. We illustrate the procedure using two exemplary weekly time series.
Similar content being viewed by others
References
Barndorff-Nielsen OE (2010) Change of time and change of measure. World Scientific, Singapore
Burns AF, Mitchell WC (1949) Measuring business cycles. NBER, New York
Clark PK (1973) A subordinated stochastic process model with finite variance for speculative prices. Econometrica 41:135–155
Ghysels E, Gourieroux C, Jasiak J (1995) Trading patterns, time deformation and stochastic volatility in foreign exchange markets. Working paper, University of Montreal
Ghysels E, Santa-Clara P, Valkanov R (2005) There is a risk-return tradeoff after all. J Financ Econ 76: 509–548
Ghysels E, Santa-Clara P, Valkanov R (2006) Predicting volatility: getting the most out of return data sampled at different frequencies. J Econom 131:59–95
Jiang H, Gray HL, Woodward WA (2006) Time-frequency analysis–\(G(\lambda )\)-stationary processes. Comput Stat Data An 51:1997–2028
Jordà Ò, Marcellino M (2004) Time-scale transformations of discrete time processes. J Time Ser Anal 25:873–894
Lütkepohl H (1981) A model for non-negative and non-positive distributed lag functions. J Econom 16: 211–219
Man KS (2004) Linear prediction of temporal aggregates under model misspecification. Int J Forecast 20:659–670
McDowell A (2004) From the help desk: polynomial distributed lag models. Stata J 4:180–189
Park JY (2008) Martingale regression and time change. Working paper, Texas A & M University
Stock JH (1987) Measuring business cycle time. J Polit Econ 95:1240–1261
Stock JH (1988) Estimating continuous-time processes subject to time deformation. J Am Stat Assoc 83:77–85
Working H (1960) Note on the correlation of first differences of averages in a random chain. Econometrica 28:916–918
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
This appendix contains detailed derivations for the examples of Sect. 2. Most of them rely on the feature that prediction based on data at the generating frequency entails a straightforward evaluation of variances, while first differences of annual data follow first-order moving-average processes. The minimum forecast variance is then slightly smaller than the variance of the first differences. The role model case of the Lemma 1 can be used with little variation in all examples.
Lemma 1
Assume the random walk with independent increments \(X_{\tau ,w}=X_{\tau ,w-1}+\varepsilon _t\) and its annual aggregate \(Z_{\tau }=\sum _{w=1}^SX_{\tau ,w}\). The forecast error variance using the annual aggregate is given as
denoting \(\sigma _{\varepsilon }^2=\mathrm{var}\varepsilon _t\).
Proof
With an insubstantial modification, this is the situation analyzed by Working (1960), who obtained the main result that \(Z_{\tau }-Z_{\tau -1}=\eta _{\tau }\) follows a first-order moving-average process \(\eta _{\tau }=\xi _{\tau }+\theta \xi _{\tau -1}\) with first-order correlation
and variance
For some of our arguments, it is convenient to note that this expression follows from a triangular weighted sum of errors via
a two-sided weighted sum of error variances at the generating frequency. Solving the quadratic equation \(\rho _1=\theta /(1+\theta ^2)\) yields
The variance \(\mathrm{var}(\xi _{\tau })=\sigma _{\xi }^2\) corresponds to the minimum forecast variance and evolves from evaluating
\(\square \)
Working (1960) remarks that, for larger \(S,\, \rho _1\) approaches \(0.25\), and even the smallest \(S=2\) yields \(\rho _1=1/6\). Also note that \(\theta \approx \rho _1\), and that \(\sigma _{\xi }^2\) is only slightly smaller than \(\sigma _{\eta }^2\), the forecast variance due to the naive forecast \(Z_{\tau }\) that incorrectly assumes that it follows a random walk.
Example 1. First assume disaggregated data are available. Then
and thus
If only annual data are available, Lemma 1 can be applied directly. From the proof of the Lemma, observe that \(\sigma _{\xi }^2\) considerably exceeds the above expression that is a one-sided weighted sum. The correction factor is too close to one to compensate this discrepancy.
Example 2. In this case, \(Z_{\tau }-Z_{\tau -1}\) is independent white noise at the annual frequency, and both the forecast for annual and for disaggregated data are clearly given as \(\hat{Z}_{\tau +1}=Z_{\tau }\).
Example 3. Denote the information set formed by past observations \(\{X_s,s\le \tau \}\) by \(H_{\tau }(X)\). By definition,
and hence
The conditional expectation is identical if data \(X_{\tau ,w}\) are available and hence also the concomitant prediction error variance does not change.
Example 4. First consider the annual variable. All calculations closely follow the proof of Lemma 1. Here,
an MA(1) process \(\eta _{\tau }=\xi _{\tau }+\theta \xi _{\tau -1}\) with variance \(6\sigma _{\varepsilon }^2\), first-order covariance \(-2\sigma _{\varepsilon }^2\), and hence first-order correlation \(\rho _1=-1/3\). The implied MA coefficient follows from equating
which yields \(\theta =-0.5*(3-\sqrt{5})\approx -0.382\). The MSE is the variance of the implied white noise \(\xi _t\) or
The conditional expectation of \(Z_{\tau +1}\) based on quarterly data is \(X_{\tau ,1}+X_{\tau ,2}\), which yields a prediction error of just
with variance \(4\sigma _{\varepsilon }^2\).
Example 5. The generating process
has the forecast based on quarterly data
with error variance
By contrast, if only annual data are available, \(Z_{\tau }-Z_{\tau -1}=\eta _{\tau }\) again follows a first-order MA process
with variance \(\sigma _{\eta }^2=10\sigma _{\varepsilon }^2,\, \rho _1=-0.1\), and concomitant \(\theta \approx -0.1010\). This results in a prediction error variance of around \(9.899\sigma _{\varepsilon }^2\). The two regrouping variants can be evaluated similarly but calculations become a bit involved. As outlined in the text, they were determined by calculation and confirmed by Monte Carlo at \(7.84\sigma _{\varepsilon }^2\) for semesters and at slightly above \(9\sigma _{\varepsilon }^2\) for grouping into the first quarter and the remaining quarters as pseudo-semesters.
Rights and permissions
About this article
Cite this article
Kunst, R.M., Franses, P.H. Asymmetric time aggregation and its potential benefits for forecasting annual data. Empir Econ 49, 363–387 (2015). https://doi.org/10.1007/s00181-014-0864-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00181-014-0864-0