To Make sure Stochasic Time Series Analysis

13 considered in this paper is Autoregressive Integrated Moving Average ARIMA time series.

2. Exponential smoothing;

Exponential smoothing is probably the widely used class of procedures for smoothing discrete time series in order to forecast the immediate future. This popularity can be attributed to its simplicity, its computational efficiency, the ease of adjusting its responsiveness to changes in the process being forecast, and its reasonable accuracy. The idea of exponential smoothing is to smooth the original series the way the moving average does and to use the smoothed series in forecasting future values of the variable of interest. In exponential smoothing, however, it is need to allow the more recent values of the series to have greater influence on the forecast of future values than the more distant observations. Exponential smoothing is a simple and pragmatic approach to forecasting, whereby the forecast is constructed from an exponentially weighted average of past observations. The largest weight is given to the present observation, less weight to the immediately preceding observation, even less weight to the observation before that, and so on exponential decay of influence of past data Amlabu et al; 2013 . There are a variety of these methods, such as single exponential smoothing, Holt‟s linear method, and Holt-Winters‟ method and their variations. Although still used in several areas of business and eco-nomic forecasting, these are now supplemented by the other four methods mentioned previously. Ostertagová, K. et al. 2011 .

2.4.6. To Make sure Stochasic Time Series Analysis

Forecasting accuracy can be measured from the following values: 1. Mean Squared Error MSE, an average prediction error sum of squares . MSE =       n r t Y Yt n 1 1 2.2 perpustakaan.uns.ac.id commit to user 14 2. Mean Absolute Deviation MAD, is the average absolute value of forecast error . MAD =     n r t Y Yt n 1 1 2.3 Note : Yt = value of observation Yt = value estimates In the method of time series there are a few things to note, first of all is Stationer data, and second is the autocorrelation function and the last is partial autocorrelation function. Stationary time series is a condition where the generation process in determining a time series based on the inconstant mean value and constant variance. In a data, its possible to be non stationary data because of a constant mean, so to eliminate non-stationary data, the data can be made closer to be stationary by using the differencing distinction method. it can be stabilized by using transformations. perpustakaan.uns.ac.id commit to user 15

CHAPTER III RESEARCH METHODOLOGY

3. 1 Explanation of the research variables

The research variables are electricity demand factors. The electricity demand factors are production cost, generated power, consumption and population variables. The relevant research with this research, his done by Saravanan 2012 with the title “India‟s Electricity Demand Forecast Using Regression Analysis and Artificial Neural Networks Based On Principal Components”. The aim of this study deals with electricity consumption in India, to forecast future projection of demand for a period of 19 years from 2012-2030. The eleven input variables used amount of CO2 emission, Population, Per capita GDP, Per capita gross national income, Industry, Consumer price index, Imports, Exports and Per capita power consumption and production cost. Saravanan, 2012. Based on these studies, this study uses the variable production costs, power generated, consumption and population.

3.2 Research methology

In this research method describes the steps that will be done, as showed in figure 3.1. commit to user