Forecasting is the process of making statements about events whose actual outcomes (typically) have not yet been observed. A commonplace example might be estimation of some variable of interest at some specified future date. Prediction is a similar, but more general term. Both might refer to formal statistical methods employing time series, cross-sectional or longitudinal data, or alternatively to less formal judgemental methods. Usage can differ between areas of application: for example, in hydrology, the terms "forecast" and "forecasting" are sometimes reserved for estimates of values at certain specific future times, while the term "prediction" is used for more general estimates, such as the number of times floods will occur over a long period. Risk and uncertainty are central to forecasting and prediction; it is generally considered good practice to indicate the degree of uncertainty attaching to forecasts. In any case, the data must be up to date in order for the forecast to be as accurate as possible. Although quantitative analysis can be very precise, it is not always appropriate. Some experts in the field of forecasting have advised against the use of mean square error to compare forecasting methods. Forecasting involves the use of information at hand to make statements about the likely course of future events. In technical terms, conditional on what one knows, what can one say about the future? Forecasting techniques include uni-variant, multi-variant, and qualitative analysis. Time series used to forecast future trends include exponential smoothing, ARIMA (Autoregressive Integrated Moving Average) and trend analysis. Multi-variant prediction methods include multi regression model, econometrics, and state space. Delphi marketing research, situational analysis, and historical analogue belong to qualitative methodologies. These forecasting methods forecast trends over different time horizons. There are significant differences in time length being considered when using these forecasting methods. Basically, uni variant methods in short-term forecasting usually generate higher accuracy than those of multi variants (Box et al., 1994).
Forecasting techniques can be categorized in two broad categories: quantitative and qualitative. The techniques in the quantitative category include mathematical models such as moving average, straight-line projection, exponential smoothing, regression, trend-line analysis, simulation, life-cycle analysis, decomposition, Box-Jenkins, expert systems, and neural network. The techniques in the qualitative category include subjective or intuitive models such as jury or executive opinion, sales force composite, and customer expectations (Kress, 1985; Mentzer & Kahn, 1995). Along with qualitative and quantitative, forecasting models can be categorized as time-series, causal, and judgmental. A time-series model uses past data as the basis for estimating future results. The models that fall into this category include decomposition, moving average, exponential smoothing, and Box-Jenkins. The premise of a causal model is that a particular outcome is directly influenced by some other predictable factor. These techniques include regression models. Judgmental techniques are often called subjective because they rely on intuition, opinions, and probability to derive the forecast. These techniques include expert opinion, Delphi, sales force composite, customer expectations (customer surveys), and simulation (Kress, 1985; Wilson & Keating, 1994). Typically, the two forms of forecasting error measures used to judge forecasting performance are mean absolute deviation (MAD) and mean absolute percentage error (MAPE). For both MAD and MAPE, a lower absolute value is preferred to a higher absolute value. MAD is the difference between the actual sales and the forecast sales, absolute values are calculated over a period of time, and the mean is derived from these absolute...
Please join StudyMode to read the full document