Production Planning and Control Questions and Answers

Answer: A

Exponential smoothing is the forecasting model that gives more weight to recent data, with weights falling exponentially for older data, and it is used when a trend or pattern is present. The simple moving average gives equal weights to the data of the period, and the Delphi method is a qualitative method that takes expert opinion. The weighted moving average also gives more weight to recent data, but the key names exponential smoothing as the model with the pattern.

Answer: A

The method is the moving average method.

A simple moving average forecasts the next period as the arithmetic mean of the last m observations, so each of those m values gets the same weight, 1/m, and older data get none.

Exponential smoothing, in all its forms (with a linear trend, or triple smoothing for trend and seasonality), gives weights that decline geometrically with the age of the data, the most recent observation weighted most heavily. A Kalman filter is a recursive state estimator whose weighting (the Kalman gain) depends on the noise statistics, not an equal weighting.

Answer: B

The mean forecast error is 0.8 and the mean absolute deviation is 4.2: 0.8 and 4.2.

The errors (actual minus forecast) for periods 1 to 10 are \(-2, -7, 4, 8, 4, -2, 3, -2, -4, 6\).

\[ \begin{aligned} \text{MFE} &= \tfrac{8}{10} = 0.8 \\ \text{MAD} &= \tfrac{2+7+4+8+4+2+3+2+4+6}{10} = \tfrac{42}{10} = 4.2 \end{aligned} \]

42.0 is the sum of absolute errors before dividing by 10, and 8.0 the sum of errors; the other options use these totals in place of the means.