You would need to use the Trend method to make the forecasts here. You would build a unique trend line for each of the games and then project/ forecast. None of the other time series methods would work, given the data. One cannot assume an exponential smoothing constant and a seed value for forecasting to make use of ES method.
Added by Lauren R.
Step 1
Step 1: **Collect Data** Gather historical data for each game, including the number of players, scores, or any other relevant metrics over a specific time period. Show more…
Show all steps
Close
Your feedback will help us improve your experience
Adi S and 92 other Intro Stats / AP Statistics educators are ready to help you.
Ask a new question
Labs
Want to see this concept in action?
Explore this concept interactively to see how it behaves as you change inputs.
Key Concepts
Recommended Videos
1. For a time series with horizontal pattern, methods that are generally used for forecasting are: a. Simple linear regression and multiple regression b. Holt's linear exponential smoothing c. Moving average, weighted moving average and exponential smoothing d. Multiple linear regression with dummy variables 2. For a time series that have only a long time linear trend, methods that are generally used for forecasting are: a. Weighted moving average b. Multiple linear regression c. Simple time series regression d. NaĂŻve method 3. For a time series with curvilinear or non linear trend, methods that are generally used for forecasting are: a. Multiple regression with dummy variables b. Simple time series regression c. Exponential Smoothing d. Multiple regression with quadratic trend equation 4. For a time series with a seasonal pattern, methods that are generally used for forecasting are: a. Multiple regression with dummy variables b. Simple time series regression c. Exponential Smoothing d. Multiple regression with quadratic trend equation Exhibit 1: Dishwasher Detergent The weekly demand (in cases) for a particular brand of automatic dishwasher detergent for a chain of grocery stores located in Columbus, Ohio, follows. Week Demand Week Demand 1 22 6 24 2 18 7 20 3 23 8 19 4 21 9 18 5 17 10 21 5. Refer to Exhibit 1. Construct a time series plot. What type of pattern exists in the data? a. Horizontal b. Trend c. Seasonal d. Seasonal & Trend 6. Refer to Exhibit 1. Use a 3 week moving average to develop a forecast for week 11. a. 20.33 b. 21.00 c. 19.00 d. 19.33
Adi S.
Rashmi S.
4. (50 points) Forecasting Using Time Series Techniques a) What forecasting technique(s) would be best suited to forecast the sales? Why? Split the data into two: 2013-15 (for forecast model building or calibration) and 2016-18 (for forecast model validation or testing) b) Use data for years 2013-15 for building the forecast models • Moving Average of 3 data points • Linear Regression • Decomposition technique • Single Exponential Smoothing i. Generate forecasts using alpha = 0.2 • Double Exponential Smoothing i. Generate forecasts using alpha = 0.2, beta = 0.1 • Triple Exponential Smoothing i. Generate forecasts using alpha = 0.2, beta = 0.1, gamma = 0.3 c) Forecast for years 2013-15 as well as 2016-18 d) Plot actual data versus forecasts in graphs e) Test the accuracy of the model for years separately for 2013-15 and 2016-18, using the mean-squared error (MSE) and mean-absolute deviation (MAD) metrics. • How does the accuracy compare for the 2013-15 model building periods versus 2016-18 (model validation) periods? Explain why? • Which forecasting technique is performing better? Why? f) Why did we split the data into two parts for this analysis? What would happen if we did not split? Discuss the pros and cons of splitting the data into two as calibration and validation data? g) For the exponential smoothing, imagine you were not given alpha, beta and gamma parameters. What would you do to complete the analysis? How would you make sure that your recommendations are robust?
Sri K.
Recommended Textbooks
Elementary Statistics a Step by Step Approach
The Practice of Statistics for AP
Introductory Statistics
Transcript
Watch the video solution with this free unlock.
EMAIL
PASSWORD