I got part 1 but need help with parts 2 and 3! (Questions 4-7)

4. Your team of analysts has determined a seasonal index for each event. Use the decompoisition method to forecast attendane for the next several years. Below, select the choice that best approximates the trend line you used in your forecast.

Spring Fling 1.032 Mountain Mayhem 0.999 Forks & Fireworks 1.164 FreeFalling 1.093 Winter Wheels 0.712

a. 4.2x + 323 b. 3.5x + 334 c. 4.6x + 318 d. 3.9x + 363

5. Using the decomposition method, what is the forecasted attendance for that event/year in which park capacity will first be exceeded? Round your answer to the nearest integer.

6. Suppose that four of the years five events are complete and you have actual attendance data for those events. Use the MAD metric to determine which of your forecasting models is most appropriate.

2023 Attendance (so far) Spring Fling = 466 Mountain Mayhem = 415 Forks & Fireworks = 544 FreeFalling = 505

Using the MAD metric for forecast accuracy, which forecasting method is best for this data set?

a. Segregation of events with event-specific trend lines b. Decomposition

7. Using the method indicated in the previous quesiton (per the MAD metric) to forecast Winter Wheels attendance for 2023. Select the closest match below.

a. 335 b. 612 c. 369 d. 603

Instant Answer:

Part 2: Forecasting with Decomposition First, we need to find the trend line equation for the overall attendance. To do this, we can average the attendance for each year and then find the best-fitting linear equation. Yearly Average Attendance: 2017: (351+339+390+379+222)/5 = 336.2 2018: (362+359+422+391+253)/5 = 357.4 2019: (380+373+443+419+279)/5 = 378.8 2020: (405+399+455+439+301)/5 = 399.8 2021: (418+411+482+455+321)/5 = 417.4 2022: (443+420+515+466+342)/5 = 437.2 Now, let's find the best-fitting linear equation for these average attendances. Using a linear regression calculator, we get the equation: y = 20.3x + 315.9 (approximately) Now, we can use the seasonal indices to forecast attendance for each event in the upcoming years. We'll do this by multiplying the trend line value by the seasonal index for each event. For example, for Spring Fling in 2023 (x=7), the trend line value is: y = 20.3(7) + 315.9 = 456.0 Now, we multiply this by the seasonal index for Spring Fling (1.032): Forecasted attendance for Spring Fling in 2023 = 456.0 * 1.032 = 470.6 We can do this for all events in the upcoming years until we find the first event/year where the forecasted attendance exceeds the park capacity of 600. Part 3: Forecast Accuracy To determine which forecasting model is most appropriate using the MAD metric, we need to calculate the Mean Absolute Deviation for both the trendline and decomposition methods. First, let's calculate the forecasted attendance for each event in 2023 using the trendline method (from Part 1). Then, we'll calculate the absolute deviation for each event using the actual attendance data provided.

Next, we'll do the same for the decomposition method using the forecasted attendance values we calculated in Part 2.

Finally, we'll compare the Mean Absolute Deviation for both methods and choose the one with the lowest MAD value. Once we've determined the most appropriate forecasting method, we can use that method to forecast Winter Wheels attendance for 2023.