MODELING AND FORECASTING EXCHANGE RATE VOLATILITY IN EEC COUNTRIES

This main objective of this paper is to examine the properties of the GARCHmodel and its usefulness in modeling and forecasting the volatility of exchange ratemovements in selected EEC countries (Romania, Hungary and Serbia). The dailyreturns of exchange rates on Hungarian forint (HUF), Romanian lei (ROL) andSerbian dinar (RSD), all against the US dollar are analyzed during the period 03.January 2000 to 15. April 2013 in respect. In order to measure the involved risk,symmetric and asymmetric GARCH models are applied. The accuracy of exchangerate volatility forecast is evaluated through reference to the most commonly usedcriteria. These include a Mincer-Zarnowitz regression based test, Mean AbsoluteError (MAE), Root Mean Square Error (RMSE) and Diebold and Mariano test (DMtest). The results of Mincer-Zarnowitz regression test for selected exchange ratereturn series showed a clear lack of explanotory power and sub-optimality of theTGARCH model. The results of the Mean Absolute Error (MAE) and the Root MeanSquare Error (RMSE) for the forecasted volatility showed that symmetric modelbetter predict conditional variance of the exchange rate returns, but estimating resultsindicating that the parameters of forecasts are not satisfactory, i.e. models have littlepredictive power. Results for Diebold-Mariano test results for Diebold-Mariano testshowed that symmetric model outperforming TGRACH forecast in case of Hungarianforint and Serbian dinar sample series, and that only in case of Romania lei TGARCHoutperforming the GARCH forecast.

The utility of shift-sampling method to enhance the precision of the calculation of gravity effect in frequency domain ·

20 and 30 graviy inversion in frequency domain was widely applied in the interpretation of potential field data, because, unlike the interpretation in space domain, it permits to reduce significaltly computer time. Precision of the interpretation in frequency domain is dependent upon the precision of the transformation between the space and frequency domain. This precision can be improved by the shift - sampling method, which is based on the discrete Fourier transform (OFT) deviation equation.In this paper, shift sampling method is applied to estimate it·s utilization in the calculation gravity effect on both 20 and 30 mathematical models, in which an infinite horizontal cylinder is used as 20 model and a sedimentary basin approximated by vertical rectangular prisms is used as 30 model.With application of shift- sampling method, precision of the calculation gravity effect in frequency domain is enhanced. For both models, root-meansquare error reduced by several tens times. This makes gravity anomaly calculated in frequency domain almost exactly in consistence with the gravity anomaly calculated in space domain. Therefore thismethod helps in the solving the problem of gravity inversion in consistence frequency domain.

PENGEMBANGAN MODEL ADOPSI TEKNOLOGI E-VOTING

Electronic voting atau e-voting adalah suatumetode pengalihan pemilihan dari manual menjadilebih terkoordinir. Hal ini dilakukan dengankombinasi dari hardware dan software. Pemilih akanberpartisipasi di dalam e-voting dengan syaratmereka tidak akan ditipu. Pemilih ingin mengetahuidan percaya bahwa proses tersebut dapat di pantauoleh masyarakat yang memiliki kemampuan untukmemahami bagaimana sistem dapat bekerja.Model penelitian yang digunakan dalampenelitian ini dikembangkan berdasarkanpenelitian Tsuma dan analisis structural equationmodeling untuk menentukan bentuk model. Bentukmodel diuji dengan 19 pengujian yaitu Chi-squareatau p-value, GFI (Goodness of Fit Index), RMR(Root Mean Square Residual), RMSEA (Root MeanSquare Error of Approximation) ECVI (ExpectedCross-Validation Index), TLI/NNFI (Non-NormedFit Index), NFI (Normed Fit Index), PNFI(Parsimony Normed Fit Index), AGFI (AdjustedGoodness of Fit Index), RFI (Relative Fit Index),CFI (Comparative Fit Index), AIC, CAIC, CN(Critical N), IFI(Incremental Fit Index),PGFI(Parsimony Goodness of Fit Index), NCP(Non-centrality Parameter), CMIN/Df dan SRMR(Standardized RMR).Kata kunci : e-voting, model dan structuralequation modeling.

SISTEM PERAMALAN UNTUK PENGADAAN MATERIAL UNIT INJECTION DI PT. XYZ

Peramalan merupakan suatu teknik untukmengidentifikasi suatu model yang dapat digunakanuntuk meramalkan kondisi pada waktu yang akandatang. Berdasarkan hasil peramalan tersebut,bagian manajerial dalam suatu perusahaan dapatmembuat perencanaan dan sebagai pengambilankeputusan yang diperlukan untuk dilaksanakan padawaktu yang akan datang. Metode yang dipilih dalamperamalan adalah Weighted Moving Average(WMA) karena menghasilkan nilai galat dan MeanSquare Error (MSE) terkecil dibandingkan denganmenggunakan metode lain yang termasuk kedalammetode model time series.

Optimal parameters for the Green-Ampt infiltration model under rainfall conditions

The Green-Ampt (GA) model is widely used in hydrologic studies as a simple, physically-based method to estimate infiltration processes. The accuracy of the model for applications under rainfall conditions (as opposed to initially ponded situations) has not been studied extensively. We compared calculated rainfall infiltration results for various soils obtained using existing GA parameterizations with those obtained by solving the Richards equation for variably saturated flow. Results provided an overview of GA model performance evaluated by means of a root-meansquare- error-based objective function across a large region in GA parameter space as compared to the Richards equation, which showed a need for seeking optimal GA parameters. Subsequent analysis enabled the identification of optimal GA parameters that provided a close fit with the Richards equation. The optimal parameters were found to substantially outperform the standard theoretical parameters, thus improving the utility and accuracy of the GA model for infiltration simulations under rainfall conditions. A sensitivity analyses indicated that the optimal parameters may change for some rainfall scenarios, but are relatively stable for high-intensity rainfall events.

On Asymptotic Prediction Problems for Multivariate Autoregressive Models in the Unstable Nonexplosive Case

This paper considers the prediction problems of a k-dimensional, pth order autoregressive process with unstable but non-explosive roots and dependent error variables. The estimated predictor has been shown to be asymptotically equivalent to the optimal predictor. An expression for the meansquare error of the estimated predictor has also been derived .

The drag of a compressible turbulent boundary layer on a smooth flat plate with and without heat transfer

The theoretical treatments given by earlier authors are classified, reviewed and where necessary extended; then the predictions of twenty of these theories are evaluated and compared with all available experimental data, the root-meansquare error being computed for each theory. The theory of van Driest-II gives the lowest root-mean-square error (11.0%).A new calculation procedure is developed from the postulate that a unique relation exists betweencfFcandRFRwherecfis the drag coefficient,Ris the Reynolds number, andFcandFRare functions of Mach number and temperature ratio alone. The experimental data are found to be too scanty for bothFcandFRto be deduced empirically, soFcis calculated by means of mixing-length theory andFRis found semi-empirically. Tables and charts of values ofFcandFRare presented for a wide range ofMGandTS/TG. When compared with all experimental data, the predictions of the new procedure give a root-mean-square error of 9.9%.