Forecasting

Judgmental forecasts rely on subjective inputs from various sources. Time-Series forecasts projects patterns identified in recent time-series observations. A time-series is a time-ordered sequence of observations taken at regular time intervals. Associative models are based on the development of an equation that summarizes the effects of predictor variables. Predictor variables are used to predict values of the variable of our interest.

It is important to know how to calculate a forecast error: Error = Actual - Forecast. There are three ways of measuring the accuracy of forecasts: MAD, MSE, and MAPE. MAD weighs all errors evenly. MSE weighs errors according to their squared values. Lastly, MAPE weighs according to relative error.

Qualitative forecasting is subjective, while quantitative forecasting involves projecting historical data, or developing associative models. Judgmental forecasts are qualitative, while time-series forecasts and associative models are both quantitative. Quantitative forecasting methods include the Naïve forecasting method, the moving average method, the weighted average method, and the exponential smoothing method. Forecasts are never 100% accurate; hence, there is always room for improvement. 

Chapter 3 introduced different kinds of forecasting techniques; however no single technique works best in every situation. Random variation is always present within forecasts and there will always be a degree of residual error within forecasts. Forecasts are the basis for an organization's schedule, and therefore the accuracy of these forecasts will dictate how many resources must be used, the output production, and the timing of a production schedule.The higher the accuracy the higher the cost, therefore the best forecast is generated from some combination of accuracy and cost. The availability of historical data, computer software, as well as the time needed to gather and analyze data must be taken into consideration when selecting a...