This paper proposes A Hybrid Wavelet-Auto-Regressive Integrated Moving Average (W-ARIMA) model to explore the ability of the hybrid model over an ARIMA model. It combines two methods, a Discrete Wavelet Transform (DWT) and ARIMA model using the Standardized Precipitation Index (SPI) drought data for forecasting drought modeling development. SPI data from January 1954 to December 2008 used was divided into two - (80%/20% for training/testing respectively). The results were compared with the conventional ARIMA model with Mean Square Error (MSE) and Mean Average Error (MAE) as an error measure. The results of the proposed method achieved the best forecasting performance.
In general, the nature of gold that acts as a hedge against inflation and its stable price over the course of the financial crisis has made it a unique commodity. Priceforecasts are a must for gold producers, investors and central bank to know the current trends in gold prices. Forecasting the future value of a variableis often done with time series analysis method. This study was conducted to determine the best model for forecasting gold commodity prices as well as forecasting world gold commodity prices in 2018 using Box-Jenkins approach. The data used in this study wasobtained from Investing.Com from 2015 until 2017. Thisstudy shows that ARIMA (1,1,1) is the best model to predict gold commodity prices based on Mean Absolute Percentage Error (MAPE). MAPE value for ARIMA (1,1,1) is 0.02%, where this value proves that forecasting using ARIMA (1,1,1) is the best forecasting becauseMAPE value is less than 10%.
Management is consistently facing fast-flowing and lots of changes in business, including in the inventory management. Especially for fast-moving inventories, the correct stocking, controlling, checking and safety stock calculation is highly needed to have an exquisite inventory management and to reduce the possibility of running out of inventory which leads to unavailability to meet the demand. One of the ways to overcome this is by doing an excellent and appropriate forecasting. Therefore, the objective of this concept paper is to analyse and recommend tools to improve inventory management using the appropriate time-series forecasting method. The firm studied in this study is serving its employees as customers that demand the routine items including stationeries and other routine products to support their job as auditors and consultants for its client. However, there are occasions when there is out-of-stock situation for fast-moving items, especially in the peak season period. Furthermore, the firm is only applying replenishment based on the used inventories from the previous month. Therefore, this study suggests to eliminate out-of-stock items situation by applying precaution initiatives such as time-series forecasting. This study is planned to employ 10 time-series forecasting methods such as moving average, exponential smoothing, regression analysis, Holt-Winters analysis, Seasonal analysis and Autoregressive Integrated Moving Average (ARIMA) using Risk Simulator Software. By simulating those methods, the most appropriate method is selected based on the forecasting accuracy measurement.
The changes on the vegetables oil trading environment might change the foundation of palm oil pricing and induce a structural change to the price model. Failing to take it account the structural change in a data series might lead to misspecification of the actual model. This study, however, showed that structural change was not present in the monthly, January 1983 to July 1995, palm oil price, but it was present on the unconditional variance. The underlying model of this series was ARIMA (3, 1, 0) with ARCH (1). The critical change of the unconditional variance took place in April 1989.
Perubahan dalam suasana perdagangan minyak sayuran boleh mengubah asas harga minyak kelapa sawit. Seterusnya ia merangsang perubahan dalam struktur model harga minyak tersebut. Kegagalan untuk mengambil kira perubahan struktur dalam siri data menjadikan model itu tidak menepati spesifikasi daripada model sebenar. Kajian ini mendapati bahawa perubahan struktur tidak berlaku bagi data harga minyak sawit dari Januari 1983 hingga Julai 1995. Tetapi perubahan berlaku pada varians tidak bersyaratnya. Model asas bagi siri ini adalah ARIMA (3,1,0) dengan ARCH(1). Didapati juga bahawa perubahan yang kritikal bagi varians tidak bersyarat berlaku pada bulan April 1989.
Time series analysis and forecasting has become a major tool in many applications in air pollution and environmental management fields. Among the most effective approaches for analyzing time series data is the model introduced by Box and Jenkins, ARIMA (Autoregressive Integrated Moving Average). In this study we used Box-Jenkins methodology to build ARIMA model for monthly ozone data taken from an Automatic Air Quality Monitoring System in Kemaman station for the period from 1996 to 2007 with a total of 144 readings. Parametric seasonally adjusted ARIMA (0,1,1) (1,1,2)12 model was successfully applied to predict the long-term trend of ozone concentration. The detection of a steady statistical significant upward trend for ozone concentration in Kemaman is quite alarming. This is likely due to sources of ozone precursors related to industrial activities from nearby areas and the increase in road traffic volume.
Combining forecast values based on simple univariate models may produce more favourable results than complex models. In this study, the results of combining the forecast values of Naïve model, Single Exponential Smoothing Model, The Autoregressive Moving Average (ARIMA) model, and Holt Method are shown to be superior to that of the Error Correction Model (ECM).Malaysia’s unemployment rates data are used in this study. The independent variable used in the ECM formulation is the industrial production index. Both data sets were collected for the months of January 2004 to December 2010. The selection criteria used to determine the best model, is the Mean Square Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). Initial findings showed that both time series data sets were not influenced by the seasonality effect.
Electricity is one of the most important resources and fundamental infrastructure for every nation. Its milestone shows a significant contribution to world development that brought forth new technological breakthroughs throughout the centuries. Electricity demand constantly fluctuates, which affects the supply. Suppliers need to generate more electrical energy when demand is high, and less when demand is low. It is a common practice in power markets to have a reserve margin for unexpected fluctuation of demand. This research paper investigates regression techniques: multiple linear regression (MLR) and vector autoregression (VAR) to forecast demand with predictors of economic growth, population growth, and climate change as well as the demand itself. Auto-Regressive Integrated Moving Average (Auto-ARIMA) was used in benchmarking the forecasting. The results from MLR and VAR (lag-values=20) and Auto-ARIMA are monitored for five months from June to October of 2019. Using the root mean square error (RMSE) as an indicator for accuracy, Auto-ARIMA has the lowest RMSE for four months except in June 2019. VAR (lag-values=20) shows good forecasting capabilities for all five months, considering it uses the same lag values (20) for each month. Three different techniques have been successfully examined in order to find the best model for the prediction of the demand.
Linear time series models are not able to capture the behaviour of many financial time series, as in the cases of exchange rates and stock market data. Some phenomena, such as volatility and structural breaks in time series data, cannot be modelled implicitly using linear time series models. Therefore, nonlinear time series models are typically designed to accommodate for such nonlinear features. In the present study, a nonlinearity test and a structural change test are used to detect the nonlinearity and the break date in three ASEAN currencies, namely the Indonesian Rupiah (IDR), the Malaysian Ringgit (MYR) and the Thai Baht (THB). The study finds that the null hypothesis of linearity is rejected and evidence of structural breaks exist in the exchange rates series. Therefore, the decision to use the self-exciting threshold autoregressive (SETAR) model in the present study is justified. The results showed that the SETAR model, as a regime switching model, can explain abrupt changes in a time series. To evaluate the prediction performance of SETAR model, an Autoregressive Integrated Moving Average (ARIMA) model used as a benchmark. In order to increase the accuracy of prediction, both models are combined with an exponential generalised autoregressive conditional heteroscedasticity (EGARCH) model. The prediction results showed that the construct model of SETAR-EGARCH performs better than that of the ARIMA model and the combined ARIMA and EGARCH model. The results indicated that nonlinear models give better fitting than linear models.
The conversions of forests and grass land to urban and farmland has exerted significant changes on terrestrial ecosystems. However, quantifying how these changes can affect the quality of water resources is still a challenge for hydrologists. Nitrate concentrations can be applied as an indicator to trace the link between land use changes and groundwater quality due to their solubility and easy transport from their source to the groundwater. In this study, 25year records (from 1989 to 2014) of nitrate concentrations are applied to show the impact of land use changes on the quality of groundwater in Northern Kelantan, Malaysia, where large scale deforestation in recent decades has occurred. The results from the integration of time series analysis and geospatial modelling revealed that nitrate (NO3-N) concentrations significantly increased with approximately 8.1% and 3.89% annually in agricultural and residential wells, respectively, over 25years. In 1989 only 1% of the total area had a nitrate value greater than 10mg/L; and this value increased sharply to 48% by 2014. The significant increase in nitrate was only observed in a shallow aquifer with a 3.74% annual nitrate increase. Based on the result of the Autoregressive Integrated Moving Average (ARIMA) model the nitrate contamination is expected to continue to rise by about 2.64% and 3.9% annually until 2030 in agricultural and residential areas. The present study develops techniques for detecting and predicting the impact of land use changes on environmental parameters as an essential step in land and water resource management strategy development.
Background: The intrinsic motivation behind the "need to complete" is more influential than external incentives. We introduced a novel progress-bar tool to motivate the completion of programs designed to treat stimulant and cannabis use disorders. We further examined the effectiveness of the progress bar's scoring approach in forecasting consistently negative urine tests. Methods: This study's participants included 568 patients with stimulant, amphetamine-type, and cannabis use disorders who were undergoing 12-month mandatory treatment programs at Taichung Veterans General Hospital in Taiwan. Patients were given scores of 1, -1, or 0 depending on whether they received negative, positive, or missing urinalysis reports, respectively. The autonomic progress bar generated weekly score totals. At the group level, scorei donated scores from all patients for a given week (i denoted the week). Scorei was standardized to adjusted scorei. We then conducted Autoregressive Integrated Moving Average (ARIMA) Model of time-series analyses for the adjusted scorei. Results: A total of 312 patients maintained treatment progress over the 12-month program. The autonomic score calculator totaled the shared achievements of these patients. The coefficients of the lag variables for mean (p), lag variables for residual error term (q), and number of orders for ensuring stationary (d) were estimated at p = 3, d = 4, and q = 7 for the first half of the treatment program, and were estimated at p = 2, d = 2, and q = 3 for the second half. Both models were stationary and tested as fit for prediction (p < 0.05). Sharply raised adjusted scores were predicted during the high-demand treatment phase. Discussion: This study's novel progress-bar tool effectively motivated treatment completion. It was also effective in forecasting continually negative urine tests. The tool's free open-source code makes it easy to implement among many substance-treatment services.
The objective of this study was to describe preliminary experience with moclobemide in the treatment of depressive disorders in the University outpatient clinic in Malaysia. Twenty patients who satisfied DSM III R criteria for depressive disorders and scored more than 16 on the Hamilton Rating Depression Score at the initial interview were recruited into this open study. The primary diagnosis of 4 patients was later ascertained to be panic disorder(2), schizophrenia(1) and social phobia(1). Patients rated themselves as improved by first follow up (7-14 days), and rated their depression as very mild to mild by the third follow up visit (ie at a mean of 46 days). Side effects were minimal and compliance good.
Study site: outpatient psychiatric clinic at the General Hospital, Kuala
Lumpur.