Chapter 10 Simple Linear Regression and Correlation
True/False Questions
1. In linear regression the dependent variable is denoted by y.
Answer: True Type: Concept Difficulty: Easy
2. b0 is used to denote the population slope.
Answer: False Type: Concept Difficulty: Easy
3. An assumption in linear regression is that the error terms are normally distributed with
mean zero and constant variance.
Answer: True Type: Concept Difficulty: Medium
4. The statistic used to construct confidence intervals on the population parameters b0
and b1 is the F distribution.
Answer: False Type: Concept Difficulty: Medium
5. The correlation coefficient, r, measures the degree of any relationship between two
variables.
Answer: False Type: Concept Difficulty: Easy
6. The population coefficient, rho, can take on any value between -1 and 1.
Answer: True Type: Concept Difficulty: Easy
7. An r value of 0.21 indicates a very high level of linear correlation.
Answer: False Type: Concept Difficulty: Easy
8. The coefficient of determination measures the proportion of the variation in Y that is
explained by the regression relationship of Y with X.
Answer: True Type: Concept Difficulty: Medium
9. The total deviation of any observed y value from the mean can be expressed as the
sum of the deviation explained by the regression and the unexplained deviation, or
error.
Aczel, Complete Business Statistics, Sixth Edition 1
Chapter 10 Simple Linear Regression and Correlation
Answer: True Type: Concept Difficulty: Medium
2 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
10. An r value of -.98 indicates almost perfect direct linear correlation.
Answer: False Type: Concept Difficulty: Easy
11. The slope of the regression equation and r carry the same sign.
Answer: True Type: Concept Difficulty: Medium
12. The prediction interval for a given x-value and the confidence interval for the mean y
for the same given x are the same.
Answer: False Type: Concept Difficulty: Medium
13. In a significant correlation you can assume causation between the independent and
dependent variables.
Answer: False Type: Concept Difficulty: Easy
14. A linear relationship assumes a straight line relationship.
Answer: True Type: Concept Difficulty: Easy
Multiple Choice Questions
Use the following to answer questions 15-18:
The following is the annual advertising expenditure and sales (in thousands of dollars) of
firms in a particular industry:
Advertising: 72, 39, 51, 7, 22, 11, 53, 56
Sales: 1,089, 627, 954, 116, 334, 304, 828, 83
15. Calculate the value of SSX
A) 3,814.875
B) 311
C) 15,905
D) 855,909.5
E) none of the above
Answer: A Type: Computation Difficulty: Medium
Aczel, Complete Business Statistics, Sixth Edition 3
Chapter 10 Simple Linear Regression and Correlation
16. Calculate the value of SSY.
A) 4,094,422
B) 5,090
C) 1,050,038.9
D) 55,957.25
E) none of the above
Answer: C Type: Computation Difficulty: Medium
17. Calculate the value of SSXY.
A) 224.361
B) 1,582,990
C) 253,831
D) 43,027.9
E) none of the above
Answer: D Type: Computation Difficulty: Medium
18. Compute the value of b0.
A) 14.668
B) 103.405
C) 224.361
D) -9,293.64
E) none of the above
Answer: B Type: Computation Difficulty: Hard
Use the following to answer questions 19-22:
A car dealer is interested in the relationship between the amount of money (X) people spend
on maintenance of their cars, and the number of miles the car runs (Y) before a breakdown. A
random sample of 25 car owners gives the following results:
X 1,066 Y 79,425
SSX = 4,296.4 SSXY = 514,028
4 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
19. Give the least squares estimate of the regression slope.
A) 74.508
B) 4.7856
C) 119.64
D) 0.00835
E) none of the above
Answer: C Type: Computation Difficulty: Medium
20. Give the least squares estimate of the regression intercept parameter.
A) 42.64 - (b1)(3,177)
B) 3,177 - (b1)(42.64)
C) 514,028 - (b1)(4,296.4)
D) 3,177 - (b1)(4,296.4/42.64)
E) none of the above
Answer: B Type: Computation Difficulty: Medium
21. The relationship between X and Y is:
A) a direct linear relationship
B) an indirect, or negative, linear relationship
C) a vertical line
D) not linear
E) none of the above
Answer: A Type: Concept Difficulty: Medium
22. Compute the value of r, if the SSY = 70,000,000
A) between -0.40 and 0.40
B) between -0.60 and -0.80
C) between 0.60 and 0.80
D) between 0.80 and 1.00
E) between -0.80 and -1.00
Answer: D Type: Computation Difficulty: Hard
Aczel, Complete Business Statistics, Sixth Edition 5
Chapter 10 Simple Linear Regression and Correlation
23. A regression equation is given as: y = 2.5x - 0.85. Compute the predicted value of y
when x is 10.
A) 24.15
B) 16.5
C) 1.65
D) insufficient information to determine
E) none of the above
Answer: A Type: Computation Difficulty: Easy
Use the following to answer questions 24-27:
A telemarketing company wants to know if the sales go up as they call more people per day
but spend less time per call. The following is the data of nine randomly selected days, giving
the number of calls the salesperson makes in a day and the total amount of sales made (in
thousands of dollars).
C a lls 25 29 33 37 43 48 52 55 67
S a le s 3 .5 3 .8 4 .4 4 .4 4 .6 4 .8 4 .7 4 .9 5 .5
24. Calculate the value of b1.
A) .0451
B) .0415
C) .0541
D) .0514
E) none of the above
Answer: B Type: Computation Difficulty: Medium
25. Compute the correlation coefficient.
A) .9475
B) .9754
C) .9530
D) .9503
Answer: C Type: Computation Difficulty: Hard
6 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
26. Construct a 95% confidence interval for b0:
A) 2.71759 .53159
B) 2.71759 .35159
C) 2.17759 .53159
D) 2.17759 .35159
E) none of the above
Answer: A Type: Computation Difficulty: Hard
27. Calculate the coefficient of determination.
A) .9530
B) .9350
C) .9802
D) .9082
E) none of the above
Answer: D Type: Computation Difficulty: Hard
28. An unbiased estimator of s2 is:
A) SSE
B) MSE
C) s(b0)
D) s
E) s(b1)
Answer: B Type: Concept Difficulty: Medium
29. An r value of -0.95 indicates:
A) no linear correlation
B) almost perfect direct linear correlation
C) almost perfect indirect linear correlation
D) a non-linear relationship
E) none of the above
Answer: C Type: Concept Difficulty: Medium
Aczel, Complete Business Statistics, Sixth Edition 7
Chapter 10 Simple Linear Regression and Correlation
30. The estimate for the true population slope, bl, is the ratio of which two values?
A) SSX /SSY
B) SSXY/SSX
C) SSX/SSXY
D) SSXY/SSX
E) none of the above
Answer: B Type: Concept Difficulty: Medium
31. When there is no linear correlation between two variables, what will the value of r be?
A) -1
B) +1
C) 0
D) a very small negative number
E) none of the above
Answer: C Type: Concept Difficulty: Easy
32. The coefficient of determination, r2, has which one of the following properties?
A) is always negative
B) applies to any relationship between x and y
C) is a ratio of unexplained variation to explained variation
D) has the same sign as the slope of the regression line
E) ranges from zero to one
Answer: E Type: Concept Difficulty: Medium
33. What is the slope of the line y = -3.4x - 2.5?
A) -2.5
B) 2.5
C) -3.4
D) 3.4
E) none of the above
Answer: C Type: Concept Difficulty: Easy
8 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
34. An insurance company wants to predict sales from the amount of money they spend
on advertising. Which would be the independent variable?
A) sales
B) advertising
C) insufficient information to decide
Answer: B Type: Concept Difficulty: Medium
35. Observed errors, which represent information from the data which is not explained by
the model, are called?
A) marginal values
B) residuals
C) mean square errors
D) standard errors
E) none of the above
Answer: B Type: Concept Difficulty: Medium
36. When testing H0: b1 = 0, against H1: b1 0, failing to reject the null hypothesis means
what?
A) the slope of the regression line is not zero
B) there is evidence of a relationship between x and y, but it is not linear
C) the relationship between x and y is an inverse one
D) there is not a linear relationship between x and y
E) there is a linear relationship between x and y
Answer: D Type: Concept Difficulty: Medium
Use the following to answer questions 37-38:
Test the hypothesis that the population slope of the regression line, b1 is zero against the
alternative that it is not equal to zero. The regression equation is: y = 4x - 5 and the standard
error of b1 is 1.6.
37. What is the test statistic?
A) 4.0
B) 0.4
C) 2.5
D) -0.4
E) -2.5
Answer: C Type: Computation Difficulty: Medium
Aczel, Complete Business Statistics, Sixth Edition 9
Chapter 10 Simple Linear Regression and Correlation
10 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
38. If the decision is to reject the null hypothesis, what is the conclusion?
A) no linear relationship
B) the true population slope is zero
C) there is a relationship between x and y, but it is not linear
D) there is evidence of a linear relationship between x and y
E) none of the above
Answer: D Type: Concept Difficulty: Medium
39. The assumptions of the simple linear regression model include:
A) the errors are normally distributed
B) the error terms have a constant variance
C) the errors have a mean of zero
D) a and b
E) a, b, and c
Answer: E Type: Concept Difficulty: Medium
Use the following to answer questions 40-41:
The following data gives the monthly sales (in thousands) for different advertising
expenditures and sales commission percentages.
S a le s 245 138 352 322 228 275 560 366
A d v e rtis in g 1 6 .5 1 8 .5 2 2 .3 1 7 .4 1 9 .0 2 0 .0 3 2 .0 1 8 .6
y = -103.367 + 20.238
40. Compute a 90% confidence interval for the average sales given advertising of 25,000.
A) 402.58 (1.943)(s)(0.4934)
B) 402.58 (1.943)(s)(1.115)
C) 402.58 (1.895)(s)(0.4934)
D) 402.58 (1.895)(s)(1.115)
E) none of the above
Answer: A Type: Computation Difficulty: Hard
Aczel, Complete Business Statistics, Sixth Edition 11
Chapter 10 Simple Linear Regression and Correlation
41. Compute a 95% prediction interval for sales when advertising is $22,000.
A) 341.87 (2.365)(s)(0.372)
B) 341.87 (2.447)(s)(0.372)
C) 341.87 (2.447)(s)(1.067)
D) 341.87 (2.365)(s)(1.067)
E) 341.87 (1.943)(s)(0.372)
Answer: C Type: Computation Difficulty: Hard
42. How much sales are expected, if $30,750 is spent on advertising?
A) 514,921
B) 518.95
C) 507,040
D) cannot determine from information given
E) none of the above
Answer: B Type: Computation Difficulty: Hard
Use the following to answer questions 43-47:
The following are the GMAT scores and the GPAs of a random sample of 6 students in a
graduate school. This graduate school wants to try to predict GPA based on GMAT score.
G M A T G PA
610 3 .6
470 3 .2 5
590 3 .5
520 3 .2
410 3 .0
750 4 .0
43. Compute the value of SSx:
A) 71,683.3334
B) 1,942,100
C) 3,350
D) 0.62875
E) 11,682.5
Answer: A Type: Computation Difficulty: Medium
12 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
44. Compute the value of SSxy:
A) 68,842.5
B) 71,683.3334
C) 11,682.50
D) 208.75
E) none of the above
Answer: D Type: Computation Difficulty: Medium
45. Compute the estimate for the population slope.
A) 1.8
B) 343.39
C) 0.0029
D) 332.008
E) none of the above
Answer: C Type: Computation Difficulty: Medium
46. Compute the correlation coefficient.
A) 0.78
B) a negative number
C) a number very close to zero
D) 0.09
E) 0.98
Answer: E Type: Computation Difficulty: Hard
47. Compute the MSE.
A) 0.005212
B) 0.0764
C) 0.023375
D) 0.0029
E) none of the above
Answer: A Type: Computation Difficulty: Hard
Aczel, Complete Business Statistics, Sixth Edition 13
Chapter 10 Simple Linear Regression and Correlation
48. An r value of 0.80 indicates:
A) no linear correlation at all
B) perfect linear correlation
C) correlation, but not linear
D) some linear correlation
E) negative linear correlation
Answer: D Type: Concept Difficulty: Medium
49. An unbiased estimator for s2, the variance of the population regression errors, is:
A) MSE
B) SSE
C) s(bl)
D) s(b0)
E) SSxy
Answer: A Type: Concept Difficulty: Medium
50. The measure of how well the regression line fits the data is the:
A) coefficient of determination
B) slope of the regression line
C) mean square error
D) standard error of the regression coefficient
E) s(b0)
Answer: A Type: Concept Difficulty: Medium
51. The deviation which is explained by the regression line can be expressed as:
A) the difference between each actual y value and the mean of the y's
B) the difference between each residual and the corresponding y value
C) the difference between each predicted y value and the mean of the y's
D) the difference between each actual y value and the predicted y value
E) the difference between each x value and each y value
Answer: C Type: Concept Difficulty: Medium
14 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
52. The correlation coefficient, r, can take on any value within what range?
A) r 1
B) 0 r 1
C) -1 r
D) -1 r 1
E) any value that the slope of the regression equation can take on
Answer: D Type: Concept Difficulty: Medium
53. My estimated regression line is Y = 17 + 4X. The intercept is equal to:
A) 17
B) 4
C) 21
D) 13
E) None of the above
Answer: A Type: Concept Difficulty: Easy
54. In regression, my estimated slope is equal to -3.2 and the standard deviataion of the
slope is 0.5 (sample size is large, over 100). Is there statistical evidence of a linear
relationship between X and Y?
A) No evidence
B) Some evidence
C) Strong evidence
D) Can't tell
Answer: C Type: Concept Difficulty: Easy
55. In regression analysis, I get a z (or t) statistic value of 18.9 (the sample size is very
large). Is there evidence of a relationship between X and Y?
A) No evidence
B) Some evidence
C) Strong evidence
D) Can't tell
Answer: C Type: Concept Difficulty: Easy
Aczel, Complete Business Statistics, Sixth Edition 15
Chapter 10 Simple Linear Regression and Correlation
56. In regression, if the estimated slope is greater than 1.96 (with a large sample), is there
evidence of a relationship between X and Y?
A) No evidence
B) Some evidence
C) Strong evidence
D) Can't tell
Answer: D Type: Concept Difficulty: Easy
57. A regression with R-square equal to 5% is classified, for prediction purposes as:
A) Poor
B) Fair
C) Good
D) Excellent
E) Can't tell
Answer: A Type: Concept Difficulty: Easy
58. What information does correlation provide?
A) The strength of the relationship between two variables.
B) The direction of the relationship between two variables.
C) The strength and direction of the relationship between two variables.
D) The strength and direction of the relationship between two or more variables.
Answer: D Type: Concept Difficulty: Easy
59. What is the difference between a positive and a negative correlation?
A) A positive correlation is from 0 to 1.00 and is stronger than a negative correlation.
B) A negative correlation is from -1.00 to 0 and is weaker than a negative correlation.
C) Both A and B, above.
D) In a positive correlation, as the independent variable increases, the dependent
variable decreases.
E) In a negative correlation, as the independent variable increases, the dependent
variable decreases.
F) Both D and E, above.
Answer: E Type: Concept Difficulty: Easy
16 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
60. As the relationship deteriorates from a perfect correlation, what happens to the points
on a scatter diagram?
A) They become more scattered.
B) The slope changes.
C) The y-intercept changes.
D) Both B and C, above.
E) None of the above.
Answer: A Type: Concept Difficulty: Easy
61. If two variables have a correlation coefficient of .30, what percentage of one variable
is accounted for by the other variable?
A) 30%
B) 70%
C) 10%
D) 9%
Answer: D Type: Computation Difficulty: Easy
62. If you have 20 pairs of subjects what would be the degrees of freedom for a test of
correlation between the groups of scores?
A) 22
B) 21
C) 20
D) 19
E) 18
Answer: E Type: Computation Difficulty: Easy
Aczel, Complete Business Statistics, Sixth Edition 17
Chapter 10 Simple Linear Regression and Correlation
Use the following to answer questions 63-67:
A shipping company offers customers the opportunity to purchase damage insurance for
shipped packages. The shipping company is interested in whether or not a simple predictive
model for package value can be constructed based on the package weight.
Eight packages have been randomly sampled, and their weight and value recorded in the
following table:
W e ig h t (X ) V a lu e (Y )
5 1 .6 7 3 4 .2 2
1 0 6 .0 8 7 8 .4 8
8 6 .2 8 4 5 .8 6
9 3 .7 4 5 1 .0 3
9 4 .4 6 4 6 .0 6
9 8 .9 6 6 0 .3 4
7 4 .7 6 4 1 .0 6
8 1 .3 8 4 7 .4 4
63. Compute the value of SSX in this situation.
A) 2,082.09
B) 2,028.90
C) 1,824.27
D) 1,284.72
E) 1,333.78
Answer: B Type: Computation Difficulty: Medium
64. Compute the value of SSXY in this situation.
A) 2,082.09
B) 2,028.90
C) 1,824.27
D) 1,284.72
E) 1,333.78
Answer: D Type: Computation Difficulty: Medium
18 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
65. Which of the following pairs provide the correct least squares estimates for 0 and 1
in this situation?
A) b0 = -5.919; b1 = 0.657
B) b0 = 5.919; b1 = -0.657
C) b0 = 0.657; b1 = -5.919
D) b0 = -0.657; b1 = 5.919
E) b0 = -5.919; b1 = -0.657
Answer: A Type: Computation Difficulty: Hard
66. Given least squares estimates for b0 and b1 in this situation, what proportion of
variation in package value is being explained by the linear model?
A) 0.286
B) 0.354
C) 0.534
D) 0.682
E) 0.863
Answer: D Type: Computation Difficulty: Hard
67. Do these data provide sufficient evidence that package value is related to package
weight (assume a = 0.05)?
A) No, because FOBSERVED = 5.99 < FCRITICAL = 12.89; therefore, H0: b1 = 0 cannot
be rejected at a = 0.05
B) No, because FOBSERVED = 12.89 > FCRITICAL = 5.99; therefore, H0: b1 = 0 cannot
be rejected at a = 0.05
C) Yes, because FOBSERVED = 12.89 > FCRITICAL = 5.99; therefore, H0: b1 = 0 can be
rejected at a = 0.05
D) Yes, because FOBSERVED = 5.99 < FCRITICAL = 12.89; therefore, H0: b0 = 0 can be
rejected at a = 0.05
Answer: C Type: Computation Difficulty: Hard
Aczel, Complete Business Statistics, Sixth Edition 19
Chapter 10 Simple Linear Regression and Correlation
Use the following to answer questions 68-70:
Twenty mutual funds specializing in technology-intensive stocks were randomly selected for a
study involving the effect of fund manager's experience on fund performance. Summary data
from the random sample are as follows:
V a ria b le A v erag e SS
E x p e rie n c e (X ) 1 9 .5 2 ,8 4 5
P e rfo rm a n c e (Y ) 1 0 .5 6 ,5 8 3
X *Y - 2 ,9 1 3
68. Which of the following pairs provide the correct least squares estimates for b0 and b1
in this situation?
A) b0 = -1.0239; b1 = -30.4661
B) b0 = 1.0239; b1 = -30.4661
C) b0 = -1.0239; b1 = 30.4661
D) b0 = -30.4661; b1 = 1.0239
E) b0 = 30.4661; b1 = -1.0239
Answer: E Type: Computation Difficulty: Hard
69. Which of the following is the correct estimate for the population correlation
coefficient between experience and performance?
A) 0.76133
B) -0.67311
C) 0.54803
D) -0.45308
E) 0.34508
Answer: B Type: Computation Difficulty: Hard
70. Because the estimate for the slope coefficient, b1, is ___________ in this instance, we
would expect ___________ fund performance with ___________ manager experience.
A) Negative; higher; lower
B) Negative; lower; lower
C) Negative; lower; higher
D) Positive; higher; higher
E) Both A and C are correct
Answer: E Type: Concept Difficulty: Easy
20 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
Short Answer Questions
71. The covariance of returns of investments A and B is -65.32. The standard deviation of
returns from investment A is 11.4, and the standard deviation of returns from
investment B is 18.1. If a linear regression model were formulated with A as the
independent variable and B as the dependent variable, what percentage of variability
in investment B would be explained by the model?
Answer: Approximately 10%. The correlation between investments A and B is
approximately -.317 = -65.32/[11.4 * 18.1]. The coefficient of determination in a
regression model would therefore be -.3172 = 0.10.
72. Director's insurance is a means by which corporate firms protect members of their
boards of directors from financial liability in lawsuits from disgruntled investors. It
has been suggested that more experienced boards tend to be sued less, and when they
are sued the losses tend to be lower. Data on collective experience and cumulative
legal losses were gathered on eight boards randomly selected for study. The data are as
follows:
C o lle c tiv e L egal L oss
E x p . (Y rs) ($ 0 0 0 s)
1 2 0 .0 6 - 2 8 6 .0 6
7 6 .3 1 - 1 3 5 .2 8
8 5 .7 6 - 1 4 5 .6 2
9 9 .2 7 - 1 4 0 .9 8
9 9 .2 6 - 1 4 4 .4 2
7 5 .9 8 - 1 2 2 .6 3
9 7 .8 9 -9 3 .7 0
1 2 2 .2 6 - 2 4 6 .1 7
A) Formulate the least squares regression model with estimates for b0 and b1.
B) Test formally whether board experience is a significant predictor of legal losses
C) Provide a 90% interval for the average losses expected when the board has a
collective experience of 95 years.
Answer: A) Estimates for b0 and b1 are, respectively, 121.149 and -2.940
B) FOBSERVED = 9.77 > FCRITICAL = 5.99, therefore reject H0: b1 = 0; experience
appears to be significantly related to legal losses
C) A 90% interval for the average losses expected when the board has a collective
experience of 95 years is -$188,580 to -$127,790.
Aczel, Complete Business Statistics, Sixth Edition 21
Chapter 10 Simple Linear Regression and Correlation
73. If, after the formulation of a least squares regression model, the 95% confidence
interval for b1 is [-1.43; 2.62], what should be true about the overall F-test for a
regression relationship?
Answer: Since the 95% confidence interval for b1 includes zero, we would not be able
to reject H0: b1 = 0 without incurring a substantial risk of making a Type I error. This
particular independent variable is most likely unrelated to the dependent variable of
interest.
74. Your company is interested in the effect of the amount they spend on advertising on
sales. Given the following monthly advertising/sales data for the last two years (in
thousands of dollars), what would be your conclusion?
1.2/180; 1.3/240; 1.4/200; 1.6/251; 1.8/233; 2.0/230; 2.1/301; 2.2/338; 2.4/309;
2.4/369; 2.6/337; 2.8/399; 3.0/355; 3.2/469; 3.4/424; 3.6/529; 3.8/480; 4.0/514;
4.2/573; 4.4/642; 4.5/605; 4.8/642; 5.0/632; 5.2/702.
What would you predict that the sales would be if the company spends $5,000 on
advertising?
Answer: R = .9808, R2 is .962, and P < .000. Sales = 29.2 + 126.93 (Advertising),
therefore, if the company spends $5,000 in advertising, they can expect $634,673 in
sales.
75. You are interested your employee's opinion of a training class. Specifically, you want
to know if their experience level is a factor in how they perceive the value of the
training. What are the null and alternate hypotheses?
Answer: Null Hypothesis: Experience has no effect on an employees' opinion.
Alternate Hypothesis: Experience has an effect on an employee's opinion.
22 Aczel, Complete Business Statistics, Sixth Edition
Chapter 10 Simple Linear Regression and Correlation
76. As the Human Resources manager for a large company you suspect that there is a
relationship between productivity and the employees' perception of how they are
treated. For five years, you measure employee perception of how they are treated and
their productivity and arrive at the following indexes.
P e r c e p tio n o f
T r e a tm e n t Y ear P r o d u c tiv ity
2 1 .3
4 2 .6
3 3 .5
6 4 .7
7 5 .8
Assuming an interval scale of measurement for both variables:
A) Test to see if there is a relationship between the two variables t the 95% confidence
level.
B) If a relationship exists, what proportion of the variation in productivity can be
accounted for by the workers' perception of how they are treated?
C) If the index for perception of treatment is 5, what would you predict the workers'
index for productivity to be if the slope of the regression line is .0895 and the y-
intercept is .186?
r = .97 r x r = .93 y =.186 x.0895x
Answer: A) Yes, r = .97 and it is significant at the .05 level.
B) 93%
C) 0.6337
Aczel, Complete Business Statistics, Sixth Edition 23
