• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.513-523
• /
• 2000

The X-12-ARIMA program was utilized on the analysis of the time series trend on 76 Korean industrial activities data in order to ensure that the trading day effect adjustment as well as the seasonal effect adjustment is needed to extract the fundamental trend-cycle factors from various economic time series data. The trading day effect is strongly correlated with the activity of production and shipping but not with the activity of inventory. Furthermore, the industrial activities were classified with respect to the sensitivity on the tranding day effect.

• The Korean Journal of Applied Statistics
• /
• v.23 no.6
• /
• pp.997-1021
• /
• 2010

This paper compares the two most widely used seasonal adjustment methods: the X-12-ARIMA and TRAMO-SEATS procedures. The basic features of these methods are discussed and compared in both their theoretical and empirical aspects. In doing so, the X-13A-S program is used to reevaluate their applicability to Korean macroeconomic data by considering possible structural breaks in the series. The finding is that both methods provide very reliable and stable estimates of seasonal factors and seasonally adjusted data. As for the empirical comparisons, TRAMO-SEATS appears to outperform X-12-ARIMA, although the results are somewhat mixed depending on the comparison criteria used and on the series under analysis. In particular, the performance of TRAMO-SEATS turns out to compare more favorably when seasonal adjustment is carried out to each sub-samples (by taking possible structural breaks into account) than when the whole sample period is used. The result suggests that as the model-based TRAMO-SEATS has a considerable theoretical appeal, some features of TRAMO-SEATS should further be incorporated into X-12-ARIMA until a standard and integrated procedure is reached by combining the theoretical coherence of TRAMO-SEATS and the empirical usefulness of X-12-ARIMA.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2166-2176
• /
• 2017

Electricity price prediction plays a crucial part in making the schedule and managing the risk to the competitive electricity market participants. However, it is a difficult and challenging task owing to the characteristics of the nonlinearity, non-stationarity and uncertainty of the price series. This study proposes a hybrid improved strategy which incorporates data preprocessor components and a forecasting engine component to enhance the forecasting accuracy of the electricity price. In the developed forecasting procedure, the Seasonal Adjustment (SA) method and the Ensemble Empirical Mode Decomposition (EEMD) technique are synthesized as the data preprocessing component; the Coupled Simulated Annealing (CSA) optimization method and the Least Square Support Vector Regression (LSSVR) algorithm construct the prediction engine. The proposed hybrid approach is verified with electricity price data sampled from the power market of New South Wales in Australia. The simulation outcome manifests that the proposed hybrid approach obtains the observable improvement in the forecasting accuracy compared with other approaches, which suggests that the proposed combinational approach occupies preferable predication ability and enough precision.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.18 no.2
• /
• pp.4116-4120
• /
• 1976

With the use of many rivers increased nearly to the capacity, the need for information concerning daily quantities of water and the total annual or seasonal runoff has became increased. A systematic record of the flow of a river is commonly made in terms of the mean daily discharge Since. a single observation of stage is converted into discharge by means of rating curve, it is essential that the stage discharge relations shall be accurately established. All rating curves have the looping effect due chiefly to channel storage and variation in surface slope. Loop rating curves are most characteristic on streams with somewhat flatter gradients and more constricted channels. The great majority of gauge readings are taken by unskilled observers once a day without any indication of whether the stage is rising or falling. Therefore, normal rating curves shall show one discharge for one gauge height, regardless of falling or rising stage. The above reasons call for the correction of the discharge measurements taken on either side of flood waves to the theoretical steady-state condition. The correction of the discharge measurement is to consider channel storage and variation in surface slope. (1) Channel storage As the surface elevation of a river rises, water is temporarily stored in the river channel. There fore, the actual discharge at the control section can be attained by substracting the rate of change of storage from the measured discharge. (2) Variation in surface slope From the Manning equation, the steady state discharge Q in a channel of given roughness and cross-section, is given as {{{{Q PROPTO SQRT { 1} }}}} When the slope is not equal, the actual discharge will be {{{{ { Q}_{r CDOT f } PROPTO SQRT { 1 +- TRIANGLE I} CDOT TRIANGLE I }}}} may be expressed in the form of {{{{ TRIANGLE I= { dh/dt} over {c } }}}} and the celerity is approximately equal to 1.3 times the mean watrr velocity. Therefore, The steady-state discharge can be estimated from the following equation. {{{{Q= { { Q}_{r CDOT f } } over { SQRT { (1 +- { A CDOT dh/dt} over {1.3 { Q}_{r CDOT f }I } )} } }}}} If a sufficient number of observations are available, an alternative procedure can be applied. A rating curve may be drawn as a median line through the uncorrected values. The values of {{{{ { 1} over {cI } }}}} can be yielded from the measured quantities of Qr$.$f and dh/dt by use of Eq. (7) and (8). From the 1/cI v. stage relationship, new vlues of 1/cI are obtained and inserted in Eq. (7) and (8) to yield the steady-state discharge Q. The new values of Q are then plotted against stage as the corrected steadystate curve.