Abstract
This paper presents a flexible framework for signal extraction of time series measured as stock or flow at diverse sampling frequencies. Our approach allows for a coherent treatment of series across diverse sampling rules, a deeper understanding of the main properties of signal estimators and the role of measurement, and a straightforward method for signal estimation and interpolation for discrete observations. We set out the essential theoretical foundations, including a proof of the continuous-time Wiener-Kolmogorov formula generalized to nonstationary signal or noise. Based on these results, we derive a new class of low-pass filters that provide the basis for trend estimation of stock and flow time series. Further, we introduce a simple and accurate method for low-frequency signal estimation and interpolation in discrete samples, and examine its properties for simulated series. Illustrations are given on economic data.
Appendix: Proofs
Throughout, we shall assume that
for
Since
which is orthogonal to y∗(0) by Assumption A. Due to the representation (19), it is sufficient to show that the error process is uncorrelated with [Idw](t). For any real h
which uses the fact that
If fu is integrable, we can write
When integrated against
This uses
This Fourier representation is valid even when
where the derivatives are interpreted in the sense of distributions – i. e., when this quantity is integrated against a suitably smooth test function, the derivatives are passed over via integration by parts:
Since
This cancels with the first term of (34), which shows that
Derivation of the Weighting Kernel in Illustration 2: We compute the Fourier Transform via the Cauchy Integral Formula (Ahlfors 1979), letting
We can replace x by
along the real axis by computing the sum of the residues in the upper half plane, and multiplying by
respectively. Summing these and multiplying by i gives the desired result, after some simplification. To extend beyond the
Derivation of the Low-Pass Weighting Kernel. We consider extending the frf to the complex plane, written as
so that the residue of f at a pole in the upper plane, say
Simplifying, and summing over the relevant residues yields
First we show that the difference between the two filters has no bias. Letting
follows from binomial expansion. Matching coefficients, we see that a necessary and sufficient condition for similar polynomial treatment is
for
Typically the initialization values
We first establish the decomposition of the discretization MSE. Using the notation
which is convenient for numerical computation. The integral expression for (27) is easily approximated via a Riemann sum. The ODF discretization MSE can be computed using the formula (also discussed in MT)
This too can be rewritten as
This can also be computed via a Riemann approximation; of course, computation of these quantities require a knowledge of the true spectrum fw, and thus is a theoretical exercise. Hence the PADF discretization MSE equals
which decomposes the error in terms of the ODF discretization MSE and the extra MSE due to using a sub-optimal discretization.
Now for the main assertion of the proposition, it suffices to show that the ratio of
divided by
In the first term, each summand is
again divided by
This completes the stock case. For the flow case, the ODF has frf
so that
The first term is the ODF discretization MSE, whereas the second term is the extra MSE due to using a suboptimal discretization. As in the stock case, the total error is the integral of a function K, whereas the lower bound on the error is given by the integral of a function H. In contrast to the stock case, H is given by
in the flow case. Also, the total error in the flow case is the integral of
As in the case of a stock-sampled series, the MSE depends explicitly on c. With these derivations, the analysis of the ratio of PADF to ODF discretization MSE follows along the same lines as for the stock case. □
References
Ahlfors, L. 1979. Complex Analysis. New York: McGraw-Hill.Search in Google Scholar
Alexandrov, T., S. Bianconcini, E. Dagum, P. Maass, and T. McElroy. 2012. “The Review of Some Modern Approaches to the Problem of Trend Extraction.” Econometric Reviews 31:593–624.10.1080/07474938.2011.608032Search in Google Scholar
Bell, W. 1984. “Signal Extraction for Nonstationary Time Series.” Annals of Statistics 12:646–64.10.1214/aos/1176346512Search in Google Scholar
Bell, W., and S. Hillmer. 1984. “Issues Involved with the Seasonal Adjustment of Economic Time Series.” Journal of Business and Economics Statistics 2:291–320.Search in Google Scholar
Bergstrom, A. R. 1988. “The History of Continuous-Time Econometric Models.” Econometric Theory 4:365–83.10.1007/978-94-011-1542-1_2Search in Google Scholar
Brockwell, P. 1995. “A Note on the Embedding of Discrete-Time ARMA Processes.” Journal of Time Series Analysis 16:451–60.10.1111/j.1467-9892.1995.tb00246.xSearch in Google Scholar
Brockwell, P. 2001. “Lévy-Driven CARMA Processes.” Annals of the Institute of Statistical Mathematics 53:113–24.10.1023/A:1017972605872Search in Google Scholar
Brockwell, P. 2004. “Representations of Continuous-Time ARMA Processes.” Journal of Applied Probability 41:375–82.10.1239/jap/1082552212Search in Google Scholar
Brockwell, P., and T. Marquardt. 2005. “Lévy-Driven and Fractionally Integrated ARMA Processes with Continuous Time Parameter.” Statistica Sinica 15:477–94.Search in Google Scholar
Clark, P. 1987. “The Cyclical Component of U.S. Economic Activity.” The Quarterly Journal of Economics 102:797–814.10.2307/1884282Search in Google Scholar
Folland, G. 1995. Introduction to Partial Differential Equations. Princeton: Princeton University Press.Search in Google Scholar
Hannan, E. 1970. Multiple Time Series. New York: Wiley.10.1002/9780470316429Search in Google Scholar
Harvey, A. 1985. “Trends and Cycles in Macroeconomic Time Series.” Journal of Business Economic Statistics 3:216–27.Search in Google Scholar
Harvey, A. 1989. Forecasting, Structural Time Series Models and the Kalman Filter. Cambridge: Cambridge University Press.10.1017/CBO9781107049994Search in Google Scholar
Harvey, A., and J. Stock. 1993. “Estimation, Smoothing, Interpolation, and Distribution for Structural Time-Series Models in Continuous Time.” In Models, Methods and Applications of Econometrics, edited by P. C. B. Phillips, 55–70. Oxford: Blackwell.Search in Google Scholar
Harvey, A., and T. Trimbur. 2003. “General Model-Based Filters for Extracting Cycles and Trends in Economic Time Series.” Review of Economics and Statistics 85:244–55.10.1162/003465303765299774Search in Google Scholar
Harvey, A., and T. Trimbur. 2007. “Trend Estimation, Signal-Noise Rations and the Frequency of Observations.” In Growth and Cycle in the Eurozone, edited by G. L. Mazzi and G. Savio, 60–75. Basingstoke: Palgrave MacMillan.Search in Google Scholar
Hodrick, R., and E. Prescott. 1997. “Postwar U.S. Business Cycles: An Empirical Investigation.” Journal of Money, Credit, and Banking 29:1–16.10.4324/9780203070710.pt8Search in Google Scholar
Kailath, T., A. Sayed, and B. Hassibi. 2000. Linear Estimation. Upper Saddle River, New Jersey: Prentice Hall.Search in Google Scholar
Koopmans, L. 1974. The Spectral Analysis of Time Series. New York: Academic Press.Search in Google Scholar
McElroy, T. 2013. “Forecasting Continuous-Time Processes with Applications to Signal Extraction.” Annals of the Institute of Statistical Mathematics 65:439–56.10.1007/s10463-012-0373-xSearch in Google Scholar
McElroy, T., and T. Trimbur. 2011. “On the Discretization of Continuous-Time Filters for Nonstationary Stock and Flow Time Series.” Econometric Reviews 30:475–513.10.1080/07474938.2011.553554Search in Google Scholar
Priestley, M. 1981. Spectral Analysis and Time Series. London: Academic Press.Search in Google Scholar
Ravn, M., and H. Uhlig. 2002. “On Adjusting the HP Filter for the Frequency of Observation.” Review of Economics and Statistics 84:371–80.10.1162/003465302317411604Search in Google Scholar
Watson, M. 1986. “Univariate Detrending Methods with Stochastic Trends.” Journal of Monetary Economics 18:49–75.10.1016/0304-3932(86)90054-1Search in Google Scholar
Whittle, P. 1983. Prediction and Regulation. Oxford: Blackwell Publishers.Search in Google Scholar
©2017 by De Gruyter