A Modified Model-based Seasonal Adjustment that Reduces Spectral Troughs and Negative Seasonal Correlation
نویسنده
چکیده
The Wiener-Kolmogorov (WK) signal extraction filter, extended to handle nonstationary signal and noise, has minimum Mean Square Error (MSE) among filters that preserve the signal’s initial values; however, the stochastic dynamics of the signal estimate typically differ substantially from that of the target. The use of such filters, although widespread, is observed to produce dips in the spectrum of the seasonal adjustments of seasonal time series. These spectral troughs tend to correspond to negative autocorrelations at lags 12 and 24 in practice, a phenomenon that will be called “negative seasonality.” So-called “square root” WK filters were introduced by Wecker in the case of stationary signal and noise, to ensure that the signal estimate shared the same stochastic dynamics as the original signal, and thus remove the problem of spectral dips. This represents a different statistical philosophy: not only do we want to closely estimate a target quantity, but we desire that the internal properties and dynamics of our estimate closely resemble those of the target. The MSE criterion ignores this aspect of the signal extraction problem, whereas the square root WK filters account for this issue at the cost of accruing additional MSE. This paper provides empirical documentation of negative seasonality, and provides matrix formulas for square root WK filters that are appropriate for finite samples of nonstationary time series. We apply these filters to produce seasonal adjustments without inappropriate spectral troughs.
منابع مشابه
Seasonal Adjustment and the Business Cycle in Unemployment
Several recent studies show that seasonal variation and cyclical variation in unemployment are correlated. A common nding is that seasonality tends to diier across the business cycle stages of recessions and expansions. Since seasonal adjustment methods assume that the two sources of variation can somehow be separated, the present study examines the impact of seasonal adjustment on the analysis...
متن کاملSeasonality and Forecasting of Monthly Broiler Price in Iran
The objective of this study was to model seasonal behavior of broiler price in Iran that can be used to forecast the monthly broiler prices. In this context, the periodic autoregressive (PAR), the seasonal integrated models, and the Box-Jenkins (SARIMA) models were used as the primary nominates for the forecasting model. It was shown that the PAR (q) model could not be considered as an appropri...
متن کاملآشکارسازی روند سریهای زمانی هواشناسی در حوزه آبخیز گرگان رود در سه دهه اخیر
Due to global warming, and its resulting changes in the frequency and amount of precipitation and temperature, there has been a great concern on climate change impacts by the scientific community. This study focuses on trend analysis of annual and seasonal rainfall (P), maximum temperature (Tmax) and minimum temperature (Tmin) time series from seven meteorological stations in Gorgranrood rive...
متن کاملFlexible seasonal long memory and economic time series
We discuss speci cation, frequency domain estimation and application of a exible seasonal long memory time series model based on fractional di erencing. This type of model lends itself to seasonal unit root testing using standard distribution theory with null hypotheses of stationarity and nonstationarity. We apply Wald tests. We suggest periodogram regression estimation for simple models, whic...
متن کاملUnit Root Properties of Seasonal Adjustment and Related Filters
Linear filters used in seasonal adjustment (model-based or from the X-11 method) contain unit root factors in the form of differencing operators and seasonal summation operators. The extent to which the various filters (seasonal, seasonal adjustment, trend, and irregular) contain these unit root factors determines whether the filters reproduce or annihilate (i) fixed seasonal effects, and (ii) ...
متن کامل