Module 3 - Quiz
#1 True or False The classical linear regression model minimizes squared deviations in order to
account for different variances among the data.
This statement is FALSE.
#2 True or False The disturbance terms the residuals are two different names for the same thing.
This statement is FALSE.
#3 True or False A regression coefficient β can be expressed as:
Correlation (Y , X )∗StDev ( X )∗StDev (Y )
β=
Var X
This statement is TRUE.
#4 True or False A critical result of the classical regression model is that the mean and
sum of the residuals is zero.
This statement is TRUE.
2
#5 True or False R is the Residual sum of squares which measure that portion of the sum of
squares that is not explained by the model.
This statement is FALSE.
#6 Moody’s Investor Services:
Year X 2018 2019 2020 2021 2022
X 0 1 2 3 4
$ Revenue Y 2.28 2.73 2.97 3.33 3.48
(a) Find the least squares line of best fit.
N X Y X2 X*Y
5 0 2.28 0 0
1 2.73 1 2.73
2 2.97 4 5.94
3 3.33 9 9.99
4 3.48 16 13.92
Total 10 14.79 30 32.58
From the table, we can have the normal equation as follows:
[ 5 b+10 m=14.79
10 b+30 m=32.58 ]
From the first equation, we get:
14.79
b=−2 m+
5
Substituting the expression for be into the second equation yields:
(
10 −2m+
14.79
5 )
+30 m=32.58
−20 m+29.58+30 m=32.58
m=0.3
Substituting m = 0.3 into the first equation yields:
14.79
b=−2 ( 0.3 ) + =2.358
5
Thus, the least squares line of best fit is:
y=0.3 x +2.358
(b) What does the line of best fit tell you about the average rate of change in % Share?
The line of best fit is as follows: y=0.3 x +2.358 , in which y represents the revenue in $, and x represents
the number of years since 2018. In the equation, the slope m = 0.3, and the y-intercept b = 2.358.
The slope m represents the average rate of change in revenue with respect to the years. In this case, the
revenue increases by 0.3 dollars per year on average.
The initial revenue in 2018, with x = 0, is:
y = 0.3(0) + 2.358 = 2.358,
so the average rate of change in % Share is: ( 2.358
0.3
) x 100 % = 12.72%
(c) What would be your estimate of revenues for 2025?
The year 2025 is 7 years after 2018, hence x=7. Substitute x =7 into the line of best fit:
y = 0.3(7) + 2.358 = 2.1 + 2.358 = 4.458
Therefore, the estimate of revenues for the year 2025 is 4.458 dollars.
()
#7 Consider the two variables below.
X 1 2 3 4 5 6
Y 1 3 3 2 2 1.8
(a) Find the least squares line of best fit.
To find the least squares line of best fit, we plot the matrix as follows:
[] [ ]
1 1 1
3 1 2
Y=
3
2
X=
1
1
3
4
β=
[ mb ]
2 1 5
1.8 1 6
Y = Xβ
' '
X Y=X X β
[] []
1 1 1
3 1 2
[ 11 1 1 1 1 1
2 3 4 5 6 ] 3
2 [
=
1 1 1 1 1 1
1 2 3 4 5 6 ] 1
1 []
3 b
4 m
2 1 5
1.8 1 6
[ 12.8
44.8 ] =[
21 91 ] [ m ]
6 21 b
[ 12.8
44.8 ] [21 b+ 91m ]
=
6 b+ 21 m
[ 44.8=21 b+91 m ]
12.8=6 b+21 m
12.8−21 m
From the first equation, we get b=
6
Substituting the expression for b in the second equation we get:
44.8=21 ( 12.8−21m
6 )+ 91m
44.8=44.8−73.5 m+91 m
17.5 m=0
m=0
Substituting m=0 into the first equation yields:
12.8=6 b+21 ( 0 ) b=2.133
Thus, the least squares line of best fit is:
y=0 x +2.133
¿ y=2.133
(b) Describe how the two variables listed are related to each other.
Compared the value to the value of m when calculating in RStudio with the following code and result:
> x <- c(1,2,3,4,5,6)
> y <- c(1,3,3,2,2,1.8)
> lm (y~x)
Call:
lm(formula = y ~ x)
Coefficients:
(Intercept) x
2.133e+00 -2.123e-16
To be exact, we can conclude that the value of m is close to zero and x does not significantly affect y, and
y is roughly constant and equal to the intercept at 2.133.
#8 Consider the following matrices
[ ] [ ]
−1 0 2 3 −2
C= 4 −3 1
−2 3 5
D= 0 −1
1 2
A=
[ 20 −1 3
4 −2 ]
Evaluate the following expression (D' D)−1
Transposing Matrix D yields Matrix D’ as follows:
'
D=
[−23 0 1
−1 2 ]
][ ]
3 −2
'
D D= [3 0 1
−2 −1 2
0 −1
1 2
D D=
'
[−410 −49 ]
[ ]
9 2
'
If D D=
10 −4
−4 9 [ '
] −1
, then( D D) =
1
10 ( 9 )−(−4 ) (−4 )
9 4
4 10
=
74 4 [
1 9 4
10
=
74
2 ] [ ] 37
5
37 37
#7 Consider the two variables below.
Xem xet tinh huong sau: Kinh nghiem thuc te chi ra rang co ton tai moi quan he tuyen tinh giua
Phong cach lanh dao chuyen dang (Transformational leadership) va Dong luc lam viec cua nhan vien
(Employee motivation). Anh chi hay lap gia thuyet va chung minh co hay khong moi quan he nay:
X 4 3 4 2 5 3
Y 5 3 4 1 5 4
The hypothesis is as follows: Y = βX
H 0 : β=0 : Khong ton tai moi quan he giua X va Y
H a : β ≠ 0 :Co ton tai moi quan he tuyen tinh giua X va Y
[] [ ]
5 1 4
3 1 3
Y=
4
1
X=
1
1
4
2
β=
[ mb ] '
X=
[ 14 1 1 1 1 1
3 4 2 5 3 ]
5 1 5
4 1 3
Y = Xβ
' '
X Y=X X β
[]
5
3
'
X Y= 1
[
1 1 1 1 1
4 3 4 2 5 3 1 ] [
4 = 1 ( 5 )+1 ( 3 ) +1 ( 4 ) +1 (1 )+1 ( 5 ) +1( 4) = 22
4 ( 5 ) +3 ( 3 ) + 4 ( 4 ) +2 (1 )+5 ( 5 )+3 (4) 84 ][ ]
5
4
[]
1 4
1 3
'
X X= 1 1
[1 1 1 1 1
4 3 4 2 5 3 1
1
] 2
5
[ ][
4 = 1 ( 1 ) +1 (1 )+1 ( 1 ) +1 ( 1 )+ 1 ( 1 ) +1(1) 1 ( 4 ) +1 ( 3 )+ 1 ( 4 ) +1 ( 2 ) +1 (5 )+ 1(3) = 6 21
4 (1 )+3 ( 1 ) + 4 ( 1 ) +2 ( 1 )+ 5 (1 )+3 (1) 4 ( 4 )+3 ( 3 )+ 4 ( 4 ) +2 ( 2 ) +5 ( 5 ) +3(3) 21 79
1 3
Therefore, the normal equation is as follows:
' '
X Y = X Xβ
[ 2284]=[216 2179][ mb ]
{21b
6 b+21 m=22
+79 m=84
{b=−0.787
m=1.272
The regression equation is: y=1.272 x−0.787
Thus, there is a positive relationship (mqh thuan chieu) between x and y. In other words, if the
transformational leadership increases by 1 unit, the employee motivation will increase by 1.272 units.
9. The Tech Company revenue is recorded over the years 2018-2022 as follows:
Year X 2018 2019 2020 2021 2022
X 0 1 2 3 4
M$ Y 2 2.5 2.8 3.2 3.5
Revenue
a. Write the regression equation (Viet phuong trinh hoi quy).
According to the financial record, we have the following hypotheses:
H o : β=0 :There is no relationship between the year∧the revenue of Tech Company
H a : β ≠ 0 :There is a relationship between the year∧the revenue of Tech Company
…..
The regression equation is: y=0.370 x +2.060
We accept the alternative hypothesis that there is a relationship between the year and the revenue of
Tech Company. The revenue increases by 0.370 million dollars after every year.
b. Estimate the revenue of Tech Company in the year 2027.
Based on the regression equation, we can calculate the revenue of the Tech Company in 2027. According
to the financial record, the year 2027 will resemblance/correspond to the x equalling to 9.
Therefore, the revenue of Tech Company in 2027 is: Revenue∈2027=0.370∗9+2.060=$ 5.390 M
