16
FORECASTING
PROBLEMS
1. A manufacturing company has monthly demand for one of its products as follows:
MONTH DEMAND
January 520 Develop a three-period average forecast and a three
February 490 period weighted moving average forecast with weights
March 550 of 5, 3 and 2 for the most recent demand values, in that
April 580 order.
May 600 Indicate which forecast would seem to be most accurate
June 420 Make a forecast of september by using both approaches.
July 510
August 610
2. A computer software firm has experienced the following demand for its “Personal Finance”
software package.
Period Units
1 56
2 61 Develop an exponential smoothing forecast using
3 55 an alpha value of 0.40
4 70
5 66
6 65
7 72
8 75
3. The head of Business Department at EMU wants to forecast the number of students who will
enroll in production/operations management next semester in order to determine how many
sections to schedule. The department has accumulated the following enrollment data for the
past 8 semesters.
Semester Students enrolled in POM
1 80
2 90
3 70
4 84
5 100
6 115
7 98
8 130
a) compute a 3-semester moving average forecast for semester 4 through 8
b) Compute the exponentially smoothed forecast (alpha=0.20) for the
enrollment data.
17
c) Compare two forecasts and indicate the most accurate.
d) Make a forecast for the next semester (semester 9) with the most accurate
approach.
4. ABC Hardware handles spare parts for lawn-mowers. The following data were collected for
one week in April when replacement for lawn-mower blades were in high demand.
Day Demand
10 15
12 16
13 18
15 22
17 21
20 23
21 24
Simulate a forecast using simple smoothing for the week, starting with F = 15 and alpha=0.2.
Find also the forecast for the 8th day.
5. Fill in the blank places.
Quarter Quantity
2004 I 26
II 38
III 54
IV 34
__________________________ Moving Totals
2005 I 34 160
II 50 172
III 58 176
IV 38 180
2006 I ___ 190
II ___ 197.2
III ___ 204.4
IV ___ 211.6
18
6. Using total moving average method to forecast the quarterly values of 2007.
Years Quarters Sales (million bottles)
2004 I 18.2
II 29.2
III 22.2
IV 17.4
2005 I 19.2
II 30.8
III 24.2
IV 18.2
2006 I 21.6
II 33.2
III 26.2
IV 20.8
7. The general manager of a building materials production plant feels the demand for
plasterboard shipments may be related to the number of construction permits issued in the
municipality during the previous quarter. The manager has collected the data shown in the
accompanying table.
Construction Plasterboard
Permits Shipments
15 6 a. Find a regression forecasting equation
9 4 b. Determine a point estimate for plasterboard
40 16 shipments when the number of construction
20 6 permits is 30.
25 13 c. Given the data on permits and shipments,
25 9 compute the standard deviation of regression.
15 10 d. Find the prediction interval of 90%.(std.-t table)
35 16 e. Find the prediction interval of 95.5% (normal)
for the specific amount of shipments when the
permits number 30. (for this part assume your
regression equation has been derived from a
sufficiently large sample that the prediction
interval form equal to y+/-z.s may be used.)
f. Determine r and coefficient of determination and interpret them.
g. Test the correlation coefficient at 5% level of significance. Is the correlation
coefficient significant at the level 5%?
h. By using correlation coefficient analysis find the regression forecasting
equation, and explain why this equation is different than the one you found in (a).
19
8. ABC Hardware handles spare parts for lawn mowers. The following data were collected for
one week in April when replacement lawn-mower-blades were in high demand. The firm also
collected necessary data on the total sales dollars generated by the store. The manager of the
store would like to know if the total sales are a good predictor of lawn-mower-blade
sales.
Day Demand for Total sales
Lawn-mowers of the store(000$)
1 10 10
2 12 13
3 13 14
4 15 16
5 20 19
6 25 20
7 24 20
a) For the above data calculate the correlation coefficient between Demand
for lawn-mower blade and Total sales of the store, and interpret the
result.
b) What percentage of variation in lawn-mower blade sales can be
explained by total sales of the store?
c) Test the correlation coefficient at 5% level of significance.
d) Compute the forecast of 8th day total sales of the store.
e) Using the forecast of total sales you found at (d), find the forecasted
demand for lawn-mower blade sales for the same date with 90%
probability.
9. Ali and Arzu are planning to set up an ice-cream stand in Laguna/Gazimagusa. After six
months of operation, the observed sales of ice-cream (in MU) and the number of Laguna
visitors are
Month Ice-cream sales (MU) Laguna Visitors
1 200 800
2 300 900
3 400 1100
4 600 1400
5 700 1800
6 800 2000
a) Determine a regression equation treating ice-cream sales as the dependent
variable and Laguna visitors as the independent variable.
b) if you expect the Laguna visitors to peak out at about 3000 persons next month,
what would be the expected ice-cream sales?
c) express your forecast with 68.3% probability limits.
20
10. In a manufacturing process the assembly-line speed (meter/minute) was thought to affect the
number of defective parts found during the inspection process. To test this theory,
management devised a situation where the same batch (lot) of parts was inspected visually at
a variety of line speeds. The following data were collected.
# of defective Line
parts found speed
21 20
19 20
15 40
16 30
14 60
17 40
a. Develop the estimated Regression Equation that relates line speed to the number
of defective parts found.
b. Use the equation developed in part (a) to forecast the number of defective parts
found for a line speed of 50 meters per minute.
c. Express your forecast within 95.5% probability limits. (Assuming n is large)
11. Sergio’s Restaurants collected the following data on the relationship between advertising
and sales at a sample of five restaurants.
Advertising Sales
Expenditures (000 MU)
(000 MU)
1 19
4 44
6 40
10 52
14 55
a. Determine the strength of the causal relationship between advertising
expenditures and sales of the restaurants and interpret the result.
b. What is the coefficient of determination? What does it mean to you?
c. Test the correlation coefficient you found in (a) at 5% level of significance. Is the
correlation coefficient significant at this level?
d. Using correlation coefficient find regression forecasting equation.
21
12.
Year Quarter Demand (tons)
2004 I 105
II 150
III 93
IV 121
2005 I 140
II 170
III 105
IV 150
2006 I 150
II 170
III 110
IV 130
Use Moving Totals to forecast the quarterly demand for the year 2007.
13. The data shown in the accompanying table include the number of lost-time accidents for the
Izmir Lumber Company over the past 7 years. Some additional calculations are included to
help you answer the following questions. Manager of the company uses the number of
employees (in thousands) to predict the number of accidents.
YEAR NO. OF NO. OF
EMPLOYEES ACCIDENTS
(000)
1997 15 5 225 25 75
1998 12 20 144 400 240
1999 20 15 400 225 300
2000 26 18 676 324 468
2001 35 17 1225 289 595
2002 30 30 900 900 900
2003 37 35 1369 1225 1295
=175 =140 =4939 =3388 =3873
a. Use the normal equations to develop a linear regression equation for forecasting
the number of accidents on the basis of the number of employees. State the
equation. Use the equation to forecast the number of accidents when the number
of employees is 33(000).
b. Assuming n is large, calculate the 95.5 percent confidence limits for the number
of accidents when the number of employees is 33(000).
c. What is the correlation coefficient between number of employees and the number
of accidents? Interpret your result.
d. What percentage of the variation in the number of accidents is explained by the
employment level?
e. Is the correlation significant at the 5% level?
22
14. Kitchens of Tomorrow Inc. has collected the following data to learn if the number of building
permits might be a useful predictor of their cabinet sales.
BUILDING CABINET
PERMITS SALES
(00) (000 MU) a. Use the normal equations to derive a regression
forecasting equation.
2 3 b. Compute the standard deviation of regression
5 5 c. Assume your regression has been derived from a
1 5 sufficiently large sample that the interval estimate
2 6 form equal to Y ±Z.Syx may be used.
5 7 d. Establish a 99.7% prediction interval estimate for
4 6 the specific amount of cabinet sales (000 MU)when
3 5 permits number 4.4(00). Compute the coefficient of
4 5 correlation and explain the meaning of it.
1 3 e. Test the significance of r for 10% and n=9.
27 45
f. Use the correlation coefficient formula to derive a regression forecasting
equation.
g. Is there any difference between the two equations you derived at a. and f.
15. A company wants to develop a means to forecast its carpet sales. The store manager believes
that the store’s sales are directly related to the number of new housing starts in town. The
manager has gathered data from Chamber of Commerce records of monthly house
construction permits and from store records on monthly sales. These data as follows:
Monthly Construction Monthly Carpet
Permits Sales (000 metres)
42 20
70 40
20 16
24 12
32 32
18 8
82 48
30 44
36 36
52 56
a. Develop a linear Regression Model for these data and forecast carpet sales if
30 construction permits for new homes are filed.
b. Calculate the standard deviation of regression.
c. State your forecast in the confidence limits of 90%.
23
16. Demand for hockey skates at a local sports store for the past eight weeks has been
Week Demand
1 122
2 130
3 98
4 121
5 96
6 152
7 113
8 124
Use a simple exponential smoothing model with alpha=0.6. Assume the forecast for Period 1
was 120. Make a forecast for period 9.
17. A retail chain of eyewear specialist has been experimenting with sales price of contact lenses.
The following data have been obtained.
Average lenses Price per
per day_______ lens, MU
200 24
190 26
188 27
180 28
170 29
162 30
170 32
a. For the above data calculate the correlation coefficient between lens price and
lens sales and interpret the result.
b. What percentage of variation in lens sales can be explained by prices.
c. Test the correlation coefficient at 5% level of significance.
d. What is 95% confidence interval for demand at price 28 MU. (Hint: n=7)
18. Fill in the blank places
Year Quarters Demand(tons)
2004 I 105
II 150
III 95
IV 120
______________________________________Moving TOTALS
2005 I 150 515
II 200 565
III 125 595
IV 175 650
2006 I ____ 690
II ____ 733.5
III ____ 777
IV ____ 820.5
24
19. Compute a forecast for the demand in each of the quarters of the following years, 2007.
Year Quarter Demand
2005 1 92
2 82
3 84
4 92
2006 1 90
2 80
3 82
4 90
20. A company has collected the following data to learn if the number of building permits
might be a useful predictor of their kitchen cabinet demand.
Building permits Cabinet Sales
x y
($00) ($00)
2 6
5 10
1 10
2 12
5 14
4 12
3 10
4 10
1 6
a). Use the normal equations to derive a regression forecasting equation.
b). Compute the standard deviation of regression
c). Assume our regression equation has been derived from a
sufficiently large sample. Establish a 95.5% confidence limits
estimate for the specific amount of cabinet sales ($000) when
permits number is 4.4 (00).
d). Find the prediction interval of 90%, when permits number is 4.4
(00).
e). Determine r and interpret it.
f). Determine coefficient of determination and interpret it.
g). Test the correlation coefficient at 5% level of significance.
h). By using correlation coefficient analysis find the regression forecasting
equation, and explain why this equation is different than the one you
found in (a).
25
21. A company wants to develop a means to forecast its carpet sales. The store manager believes
that the store’s sales are directly related to the number of new housing starts in town. The
manager has gathered data from Chamber of Commerce records of monthly house
construction permits and from store records on monthly sales.
Monthly Construction Monthly Carpet
Permits Sales (000 metres)
42 10
70 20
20 8
24 6
32 16
18 4
82 24
30 22
36 18
52 28
a. Develop a linear Regression Model for this data and forecast carpet sales if 30
construction permits for new homes are filed.
a. Calculate the standard deviation of regression.
b. State your forecast in the confidence limits of 90%.
c. Determine r and interpret it
d. Determine the strength of the causal relationship between monthly sales and new
home construction using correlation.
e. Test the correlation coefficient at 5% level of significance.
22. Using total moving average method to forecast the quarterly values of 2007.
Years Quarters Sales (million bottles)
2004 I 91
II 146
III 111
IV 87
2005 I 96
II 154
III 121
IV 91
2006 I 108
II 166
III 131
IV 104
23. TT Construction Company renovates old homes in Magusa. Over time, the company has
found that its MU volume of renovation work is dependent on the Magusa area payroll. The
26
figures for TT’s revenues and the amount of money earned by wage earners in Magusa for
the past six years are presented in the table below.
Years Sales Payroll
(100.000MU) (100.000.000MU)
1997 2.0 1
1998 3.0 3
1999 2.5 4
2000 2.0 2
2001 2.0 1
2002 3.5 7
a. Using sales data above develop a regression equation.
b. Find correlation coefficient and determination coefficient and interpret them.
c. Test the correlation coefficient at 5% level of significance. Is the correlation
coefficient meaningful (significant) at this level?
d. Using correlation coefficient, find regression equation and explain the difference
between the two regression equations in (a) and (d).
e. Calculate standard deviation of the regression equation and express your forecast
within 90% probability limits, if the local chamber of commerce predicts the Magusa
area payroll will be 600 million MU next year.
f. Find the forecast of Magusa Area Payroll for the year 2003.
g. Find the regression equation using the forecast found in (f)
h. Assuming sample is large (n>30) find the confidence intervals for 65.5% probability.
24. In a manufacturing process the assembly-line speed (meter/minute) was thought to
affect the number of defective parts found during the inspection process. To test
this theory, management devised a situation where the same batch (lot) of parts was
inspected visually at a variety of line speeds. The following data were collected.
# of defective Line
parts found speed
22 20
20 20
18 40
18 30
15 60
18 40
a. Develop the estimated Regression Equation that relates
line speed to the number of defective parts found.
b. Use the equation developed in part (a) to forecast the
number of defective parts found for a line speed of 50
meters per minute.
c. Express your forecast within 99.7 % probability limits.
(assuming n is large)
27
25. Room registrations in the Magusa Plaza Hotel have been recorded for the past nine years.
Management would like to determine the mathematical trend of guest registration in
order to project future occupancy. This estimate would help the hotel management to
determine whether a future expansion will be needed. Given the following time-series
data, develop a trend equatin relating to registrations to time.
Then,
a) Forecast next year’s registrations.
b) Give your next year’s forecast with 95% probability (i.e. assuming the level
of significance is equal to 5%)
c) Assuming n is large (i.e. n≥30), show your confidence limits for the next
year with %95.5 probability.
Years Registrants(000)
1993 17
1994 16
1995 16
1996 21
1997 20
1998 20
1999 23
2000 25
2001 24
26. Time 1 2 3 4 5 6 7 8 9 10 11 12
Demand 10 14 19 26 31 35 39 44 51 55 61 54
a) Assume F1 = 8 and α = 0.3 . Use an exponential smoothing factor to
forecast demand in periods 2-13.
b) Find the mean absolute deviation of exponential smoothing. \
27.
Year Quarter Demand for
fertilizer (tons)
2004 I 50
II 73
III 45
IV 60
2005 I 71
II 85
III 50
IV 61
2006 I 71
II 80
III 55
IV 65
a. Compute a three-quarter moving average forecast. Compute also the
forecast error for each quarter.
28
b. Compute the quarterly forecasted demand for the year 2007.
28. The manager of Magusa Transport Co. wishes to forecast the number of miles
driven by his trucks for the coming three years.
Years Thousands of
______ Miles driven
2001 22
2002 24
2003 34
2004 30
2005 40
2006 50
a) Compute the forecast of miles driven for the next three years (2007, 2008 and 2009)
b) Give your forecast for the year 2007 with %95 probability (i.e. assuming the level of
significance is equal to %5)
c) Assuming n is large (i.e. n30), show your confidence limits for the year 2008 with
%68.3 probability.
29. November Demand
10 20
11 28
12 38
13 52
14 62
15 70
a) Use a simple 3-period moving average to demand for 13 November-15
November.
b) Find the average error for that period.
c) Assume that F1=24 and = 0.6. Use an exponential smoothing method
to forecast demand in periods 11 November-15 November. Find the
average error.
d) Compare the methods and state which one you prefer and why?
30. The monthly sales for Telco Batteries Inc., were as follows:
Month Sales Month Sales
January 20 October 20
February 21 November 21
March 15 December 23
April 14
May 13
June 16
July 17
August 18
September 20
Forecast past sales using each of the following;
a. A three-month moving average,
29
b. a 6-month weighted average using 1,1,1,2,2,2, and 3 with the heaviest
weights applied to the most recent months.
c. Exponential smoothing using an α = 0.3 and a January forecast of 20.
d. Which method you prefer and why?
e. using the method you chose, forecast January sales of the coming
year.
31. Dr. Alev Yakar, a Magusa psychologist, specializes in treating patients who are
agoraphic (afraid to leave their homes). The following table indicates how many patients
Dr. Yakar has seen each year for the past 10 years.
Year No.of Patients
1997 36
1998 33
1999 40
2000 41
2001 40
2002 55
2003 60
2004 54
2005 58
2006 61
a.Using trend analysis, predict the number of patients Dr. Yakar will see in years
2007 and 2008.
b.What is the standard error of the forecasts?
c. Forecast number of patients in 2007 at 5% level of significance.
d.Assuming sample is large (i.e. n>30), state your forecast of 2007 within
95.5%confidence interval.
32. Data collected on the yearly demand for 50-kg bags of fertilizer at Ilhandir Garden
Supply are shown in the table below.
DEMAND FOR
FERTILIZER
YEAR (000 of BAGS)
1 4
2 6
3 4
4 5
5 10
6 8
7 7
8 9
9 12
10 14
11 15
a. Develop a three-year moving average to forecast sales.
b. Develop a four-year moving average for demand for fertilizer.
c. Estimate demand again with weighted three-year moving average in which sales in the
30
most recent year are given a weight of 2 and sales in other two years are each given a
weight of 1.
d. Three different forecasts were developed for the demand for fertilizer. These three
forecasts are a three-year moving average, four-year moving average and a weighted
moving average. Which one would you use and explain why?
e. Use exponential smoothing with a smoothing constant of 0.3 to forecast the demand
for fertilizer. Assume that last period’s (year’s) sales forecast for year 1 is 5 000 bags
to begin the procedure.
f. Would you prefer to use the exponential smoothing model or one of the above models.
Explain your choice. And according to your choice forecast the year 12.
33. Girne Manufacturing Company’s demand for electrical generators over the period
2000 - 2006 is shown in table below.
Electrical
Year Generators
Sold
2000 74
2001 79
2002 80
2003 90
2004 105
2005 142
2006 122
a. Develop a linear trend line by using the least squares method.
b. Estimate the demand in 2007 and 2008.
c. Calculate the standard error of the past record.
d. Give your forecast for the year 2008 at 5% level of significance.
e. Assume n is large (n>30), give your forecast for the year 2007 within 95.5%
confidence interval.
34. The following gives the number of pints of type O (Rh+) blood used at Nalbantoglu
Hospital in the past 6 weeks:
Week of Pints Used
August 4 360
August 11 389
August 18 410
August 25 381
September 1 368
September 8 374
a. Forecast the demand for the week of September 15 using a 3-week moving average.
b. Use a 3-week-weighted moving average, with weights of 1,3, and 6, using 6 for the
most recent week. Forecast demand for the week September 15.
c. Compute the forecast for the above data using exponential smoothing with a forecast for
August 4 of 360 and α =0.2. Forecast the demand for the week of September15.
(Show all your calculations and errors in tabular form.)
35. The manager of the Petroco Service Station wants to forecast the demand for unleaded
31
gasoline next month so that the proper number of gallons can be ordered from the
distributor. The owner has accumulated the following data on demand for unleaded
gasoline from sales during the past 10 months.
MONTH Gasoline
Demanded (gallons)
November 800 a. Compute an exponentially smoothed forecast
December 725 using α = 0.3 and F1 = 700.
January 630 b. Compute the error of each month and find the
February 500 average error for the past record.
March 645 c. Forecast the demand for the coming month
April 690 September.
May 730
June 810
July 1200
August 980
36. Quarterly data for the failures of certain aircraft engines at a local military base during the last
two years are
Quarters Engine failures
1 200
2 250
3 175
4 186
5 225
6 285
7 305
8 190
a) Determine one-step-ahead forecasts for periods 4 and 8 using
three-period moving averages method.
b) Let us assume that the forecast for period 1 was 200. Also
suppose that = 0.1. Determine one-step-ahead forecasts for
periods 2 and 8.
c) Compare the above mentioned methods for the periods 4 and 8.
Based on this comparison conclude which method is a superior
method for the given series.
37. Bicycle sales at TT’s Bikes are shown below.
Actual
Week Bicycle Sales
1 8
2 10
3 9
4 11
5 10
6 13
32
a) Use 3-week moving average for forecasting week 4, week 5, week 6 and week 7.
b) If
Weights
Applied Period
3 last week
2 2 weeks ago
1 3 weeks ago
Forecast the weeks 4, 5, 6 and 7.
c) Which method would you prefer and why?
d) Use exponential smoothing to forecast bike sales. Assume that the forecast for
Week 1 was 9 and α = 0.7.
38. The sales manager of a large apartment rental complex feels the demand for apartments
may be related to the number of newspaper ads placed during the previous month. She
has collected the data shown in the accompanying table.
Ads Purchased Apartments leased
15 6
9 4
40 16
20 6
25 13
25 9
15 10
35 16
a. Find the mathematical equation by using the least squares regression
approach.
b. If the number of ads is 30, estimate the number of apartments leased.
c. Given the data on ads and apartment rentals as above, compute the
standard deviation of regression (Syx).
d. Compute the correlation coefficient and interpret.
e. Compute the determination coefficient and interpret.
f. Test the hypothesis, i.e. r = 0 , at 5% level of significance
39. Given below are 2 years of quarterly demand data for a particular model of personal
computer from a local computer store.
Year Quarter Demand
2005 I 40
II 46
III 39
IV 42
2006 I 44
II 57
III 43
IV 45
33
a) Deseasonalize the data with a moving total and compute a linear equation for
the trend in demand.
b) Using the trend you have developed, compute a forecast for the demand in
each quarters of the following year.
40. Bus and subway ridership for the summer month in London, England, is believed to be
tied heavily to the number of tourists visiting the city. During the past 12 years, the
following data have been obtained.
YEAR NO. OF RIDERSHIP
TOURISTS (in millions)
(in millions)
-________
1991 7 1.5 49 2.25 10.5
1992 2 1.0 4 1.00 2.0
1993 6 1.3 36 1.69 7.8
1994 4 1.5 16 2.25 6.0
1995 14 2.5 196 6.25 35.0
1996 15 2.7 225 7.29 40.5
1997 16 2.4 256 5.76 38.4
1998 12 2.0 144 4.00 24.0
1999 14 2.7 196 7.29 37.8
2000 20 4.4 400 19.36 88.0
2001 15 3.4 225 11.56 51.0
2002 7 1.7 49 2.89 11.9
TOTALS 132 27.1 1796 71.59 352.9
a. Use the normal equations to develop a linear regression equation for forecasting
the number of ridership on the basis of the number of tourists. State the equation.
b. Use the equation to forecast the number of ridership when the number of tourists
visit London in a year is 10 million.
c. Explain the predicted ridership if there are no tourists at all.
d. Assuming n is large, calculate the 95.5 percent confidence limits for the number
of ridership when the number of tourists is 10 million.
e. What is the correlation coefficient between number of ridership and the number
of tourists? Interpret your result.
f. What percentage of the variation in the number of ridership is explained by the
tourist level?
g. Is the correlation significant at the 5% level?
41. Sales of Volkswagen’s Beetle have grown steadily at auto dealership in Istanbul during
the past 5 years (see the table below).
Year Sales
1999 450
2000 495
2001 518
2002 563
2003 584
34
a) The sales manager had predicted in 1998 that 1999 sales (F1) would be 410
VWS. Using exponential smoothing with a weight of α = 0.30, develop forecast
for 2000 through 2004.
b) Use a 3-year moving average to forecast the sales of VW beetles in Istanbul
through 2004.
c) Which method you would use, exponential smoothing with α = 0.3 or a 3-year
moving average. (Use average errors)
d) According to the method you have chosen, forecast 2004 sales.
42. Year Quarter Demand (Units)
2005 I 92
II 82
III 84
IV 92
2006 I 90
II 80
III 82
IV 94
Compute a forecast for the demand in each of the quarters of the following year, 2007.
43. Following are the actual tabulated demands for an item for a nine-month period, from
January through September. Your supervisor wants to test three forecasting methods to
see which method was better over this period.
Month Actual Demand
January 110
February 130
March 150
April 170
May 160
June 180
July 140
August 130
September 140
a. Forecast April through September using a 3-month simple moving
average.
b. Using a weighted moving average with weights 6, 3, 1 from recent to
oldest, forecast April through September.
c. Use simple exponential smoothing to estimate April through September
(α = 0.3) and assume that the forecast for March was 130.
d. Use absolute errors to decide which method produced be better forecast
over the six-month period.
44. Dumlupinar Sports Club wants to develop its budget for the coming year using a forecast
for football attendance. Football attendance accounts for the largest portion of its
revenues, and the Vice Director Mr. T. Turgay believes attendance is directly related to
35
the number of wins by the team. The Vice Director has accumulated total attendance
figures for the last eight months.
WINS ATTENDANCE
4 3 630
6 4 010
6 4 120
8 5 300
6 4 400
7 4 560
5 3 900
7 4 750
a) Develop a simple regression equation.
b) Forecast attendance for at least 7 wins next year.
c) If “ r = 0.948 “, what is the coefficient of determination. Interpret both.
d) Test the correlation coefficient at 5 % level of significance. Is the
correlation coefficient significant (meaningful) at this level?
e) Using correlation coefficient find regression equation and explain the
difference between two regression equations you have calculated.
f) Calculate standard deviation of regression equation.