Forecasting Practice Questions
Q1. Which of the following statement about forecast is wrong?
A). Forecasts are rarely perfect
B). Forecasts are more accurate for shorter than longer time horizons
C). Forecasts are more accurate for individual items rather than for groups or families of items
D). The goal of forecasting is to generate good forecasts on the average over time and to keep
forecast errors as low as possible
Q2. If the correlation coefficient between two variables is 0.7 during the linear regression
forecasting,
A). The two variables have a weak positive relationship
B). The two variables have a strong positive relationship
C). The independent variable can be used effectively as a predictor of the dependent variable
D). None of the above
Q3.
The manager of a small health clinic would like to use exponential smoothing to forecast demand for
laboratory services in their facility. However, she is not sure whether to use a high or low value of α.
To make her decision, she would like to compare the forecast accuracy of a high and low α on
historical data. She has decided to use α =0.7 for the high value and α=0.1 for the low value. Given
the following historical data, which do you think would be better to use?
Week Demand (lab requirements)
1 330
2 350
3 320
4 370
5 368
6 343
Q4.
Hospitality Hotels forecasts monthly labor needs
A). Given the following monthly labor figures, make a forecasting for June using a 3-period
moving average and a 5-period moving average.
Month Actual Values
1 32
2 41
3 38
4 39
5 43
B). If actual labor figure for June turn out to be 41, what would be the forecast for July using
above 2 methods
C). Compare accuracy of these models using the MAD
Page 1 of 4
Q5.
Demand at Nature Trails Ski Resort has a seasonal pattern. Demand is highest during the winter, as
this is the peak ski season. However, there is some ski demand in the spring and even fall months.
The summer months can also be very busy as visitors often come for summer vacation to go hiking
on the mountain trails. The owner of Nature Trails would like to make a forecast for each season of
the next year total annual demand has been estimated at 4000 visitors. Given the last two years of
historical data, what is the forecast for each season of next year?
Visitors
Season Year 1 Year 2
Fall 200 230
Winter 1400 1600
Spring 520 580
Summer 720 831
Q6.
The number of patients coming to the Healthy Start maternity clinic has been increasing steadily over
the past eight months. Given the following data, use a linear trend line to forecast attendance for
month 9 and 10.
Month Clinic attendance (in
thousands)
1 3.4
2 3.9
3 4.5
4 5.0
5 5.8
6 5.9
7 6.5
8 6.7
Q7.
Pumpkin Pies Galore is trying to forecast sales of pies for the month of December. Demand for the
previous 3 month (9, 10, 11) has been 230, 304, 415 respectively. The company owner chooses to use
3 period weighted moving average to forecast sales. She chooses to weight September as 0.1,
October as 0.3 and November as 0.6.
1) What would her forecast for December will be?
2) What would her forecast be using the 3-period moving average method?
Page 2 of 4
Forecasting Practice Question (Answer)
Q1-Q2: C B
Q3
Forecasting using α=0.1: (for the first period, assume forecast = demand)
week Demand Exponential Absolute error
Smoothing
1 330
2 350 330 20
3 320 332 12
4 370 330.8 39.2
5 368 334.72 33.28
6 343 338.048 4.952
MAD 21.89
Forecasting using α=0.7
week Demand Exponential Absolute error
Smoothing
1 330
2 350 330 20
3 320 344 24
4 370 327.2 42.8
5 368 357.16 10.84
6 343 364.748 21.748
MAD 23.88
Using α=0.1 provides a better historical fit based on the MAD criterion
Q4:
a) 3 period moving average: F6=(A3+A4+A5)/3=(38+39+43)/3=40
5 period moving average: F6= (A1+A2+A3+A4+A5)/5= (32+41+38+39+43)/5=38.6
b) 3 period moving average: F7=(A4+A5+A6)/3=(39+43+41)/3=41
5 period moving average: F7=(A2+A3+A4+A5+A6)/5=(41+38+39+43+41)/5=40.4
c) Assuming the June value is to be used as known:
Month Actual 3-period Absolute 5-period Absolute
moving error moving error
average average
1 32
2 41
3 38
4 39 37 2
5 43 39.33 3.67
6 41 40 1 38.6 2.4
Page 3 of 4
∑ |Actual−Forecast|
MAD (3-Period moving average) = n
= (2+3.67+1)/3=2.22
∑ |Actual−Forecast|
MAD (5-Period moving average) = = 2.4/1=2.4
n
Q5. Note: The approach below is slightly different from what we discussed in
class, and is more commonly used. Either approach would be OK.
Step 1: average demand for each season:
Year 1: 2840/4=710; Year 2: 3241/4=810.25
Step 2: seasonal index for each season:
Season Year 1 Year 2
Fall 200/710=0.282 230/810.25=0.284
Winter 1400/710=1.972 1600/810.25=1.975
Spring 520/710=0.732 580/810.25=0.716
Summer 720/710=1.014 831/810.25=1.026
Step 3: average seasonal index for each season:
Fall 0.283
Winter 1.973
Spring 0.724
Summer 1.020
Step 4: average demand per season: 4000/4=1000
Step 5: multiply next year’s average seasonal demand by each seasonal index:
season Forecast
Fall 283
Winter 1973
Spring 724
summer 1020
Q6:
∑ xy = 208.2 ∑ x2 = 204 ∑ y2 = 227.61
∑ x = 36 ∑ y = 41.7
a = 3.011, b = 0.489 (these two parameters can also be found by running regression in Excel)
Regression model: Clinic attendance = 3.011+0.489 month
F9 = 3.011+0.489*9 =7.412 Attendees (in thousands)
F10 = 3.011 + 0.489 * 10 = 7.901 attendees (in thousands)
Q7.
1) Forecast using a weighted moving average: 230*(0.1)+304*(0.3)+415*(0.6) = 363.2
2) Forecast using naïve method: (230+304+415)/3 = 316.3
Page 4 of 4
