How is MAPE calculated?

• A. MAPE = ∑ ((|A - F|)/ F) / n
• B. MAPE = ∑ ((A - F)/ A) / n
• C. MAPE = ∑ (|A - F|) / A
• D. MAPE = ∑ ((|A - F|)/ A) / n

Answer: (D)

MAPE measures the average percent error between what was forecast and what actually happened. For each observation, you take the absolute difference between the actual value and the forecast, then scale that by the actual value to get a percentage error: |A − F| / A. After computing this for all observations, you average them by dividing the sum by the number of observations. So the formula is the mean of those absolute percentage errors across the data: (1/n) Σ |A − F| / A. This approach keeps the error in a true percentage form relative to the actual value. Using the forecast in the denominator, omitting the absolute value, or not averaging across observations would shift the meaning away from the standard mean absolute percentage error.