Sei sulla pagina 1di 6

SMMD: Practice Problem Set 6

Topic: The Simple Regression Model


1. Which of the following statements is TRUE?
A. The Simple Regression Model (SRM) requires that a histogram
of the response should look like a normal distribution.
B. The SRM assumes that observations of the explanatory
variable are independent of one another.
C. The assumption of a normal distribution for the errors in a
regression model is critical for the confidence interval for the
slope.
D. None of the above
2. Suppose a company ran a regression to discover relation between
sales (response) and level of advertisement (explanatory). The
company used this regression details to make prediction about the
sales. However, it was found that the sales fell way below the lower
limit of the prediction interval. Which of the following could be an
explanation?
A. There is always a finite probability that actual sales would turn
out to be less than lower limit of the prediction interval.
B. The regression may itself no longer be applicable, since the
company may have new competitors.
C. None of (A) and (B)
D. Both of (A) and (B)
3. A measure of how well the regression line fits the data is the:
A.
B.
C.
D.

Slope of the regression line


Root mean square error
Standard error of the regression slope
None of the above

4. 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:

The regression output is given in the following table:

Do these data provide sufficient evidence that package value is related


to package weight (assume = 0.05)?
A.
B.
C.
D.

No, because H0: 1 = 0 cannot be rejected at = 0.05


No, because H0: 0 = 0 cannot be rejected at = 0.05
Yes, because H0: 1 = 0 can be rejected at = 0.05
Yes, because H0: 0 = 0 can be rejected at = 0.05

5. An estimator of standard deviation of errors is:

A.
B.
C.
D.

SSE
RMSE
SE(b0)
SE(b1)

(Q6 Q7) 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. The regression output is
also given.

Source

SS

df

MS

Model
Residual

.607903646
.020846299

1 .607903646
4 .005211575

Total

.628749945

5 .125749989

GPA

Coef.

GMAT
_cons

.0029121
1.79907

6. What is the RMSE.


A.
B.
C.
D.

0.0722
0.2764
0.1529
0.0539

Std. Err.
.0002696
.1534036

t
10.80
11.73

Number of obs
F( 1,
4)
Prob > F
R-squared
Adj R-squared
Root MSE

=
=
=
=
=
=

6
116.64
0.0004
0.9668
0.9586
.07219

P>|t|

[95% Conf. Interval]

0.000
0.000

.0021635
1.373153

.0036607
2.224987

7. The exact 95% prediction interval of GPA for a candidate who scores
400 in GMAT is _____ than the prediction interval of GPA for a
candidate who scores 580 in GMAT.
A.
B.
C.
D.

longer
shorter
equal
we cannot say

(Q8 - Q9) The manager of a used-car dealership is very interested in


the resale price of used cars. The manager feels that the age of the
car is important in determining the resale value. He collects data on
the age and resale value of 15 cars and runs a regression analysis with
the value of the car (in thousands of dollars) as the dependent variable
and the age of the car (in years) as the independent variable. The
regression output is given below:
Coefficients
Intercept
Age

A
B

Standard
Error
3.835
0.640

t Stat
5.988
-1.776

8. What are the values of A and B?


A.
B.
C.
D.
9.

9.35, 1.136
3.06, 0.278
9.82, -0.278
22.96, -1.136

What is the 95% confidence interval of the coefficient of age?


A.
B.
C.
D.

(-1.325 to 1.0435)
(-3.5434 to 1.1985)
(-2.5184 to 0.2464)
(0.1874 to 2.0044)

10. Each worker at an assembly plant that produces clock radios is


responsible for the entire assembly of each unit they work on. The
plant manager has collected data from a sample of workers: the
number of years (YRS) of experience at the plant, and the number
of hours per unit time (TIME) required for the assembly. The
scatterplot of TIME versus YRS is shown below.

Estimated hours per unit = 13.676 3.776 * YRS


R-square = 0.769 and Se = 1.824
Based on the scatterplot, does it appear appropriate to fit a regression
line to this data? Why or why not?
A. Yes, it is appropriate
B. No, it is not appropriate
C. It is appropriate only for part of the dataset
D. None of the above
11. The manager has decided to transform the response variable
from TIME (hours/unit) to 1/TIME (units/ hour). Note that this is a
reciprocal transformation. The scatterplot of 1/TIME versus YRS is
shown below. Using the fitted line below provided with the data,
determine the prediction of the number of hours per unit required
on average for a worker with experience 1.75 years. Remember to
convert back to TIME in hours per unit.

A.
B.
C.
D.
12.

Estimated units per hour = 0.015 + 0.096 * YRS


R-squared = 0.897 and Se = 0.029
6.28
4.34
5.46
7.82

Which one of the following statements is FALSE?


A. To identify the presence of curvature, one can fit a line and
make a residual plot
B. Transformations in regression affect the R2 of the fitted model
C. The R2 of the fitted model after transformation must be higher
than the R2 of the fitted model before transformation
D. The R2 of the fitted model after transformation must be lower
than the R2 of the fitted model before transformation

Potrebbero piacerti anche