Scribd
Upload
65 views5 pages

Regression Analysis and Predictions

This document provides solutions to 5 questions related to linear regression analysis. For each question, the document computes relevant regression statistics such as the slope (b1), y-intercept (b0), sum of squared errors (SSE), total sum of squares (SST), and regression sum of squares (SSR). Hypothesis tests including the t-test and F-test are used to evaluate the significance of the regression results. Computations are shown to estimate the regression equation, goodness of fit, correlation, standard errors, and test hypotheses about the slope of the regression line.

Uploaded by

Gerardin
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
65 views5 pages

Regression Analysis and Predictions

This document provides solutions to 5 questions related to linear regression analysis. For each question, the document computes relevant regression statistics such as the slope (b1), y-intercept (b0), sum of squared errors (SSE), total sum of squares (SST), and regression sum of squares (SSR). Hypothesis tests including the t-test and F-test are used to evaluate the significance of the regression results. Computations are shown to estimate the regression equation, goodness of fit, correlation, standard errors, and test hypotheses about the slope of the regression line.

Uploaded by

Gerardin
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd

Solution to Extra Questions

Question 1

Given are five observations for two variables, x and y.

xi 1 2 3 4 5

yi 3 7 5 11 14

a) Develop a scatter diagram for these data


b) What does the scatter diagram developed in part (a) indicate about the relationship
between the two variables?
c) Try to approximate the relationship between x and y by drawing a straight line
through the data.
d) Develop the estimated regression equation by computing the values of b0 and
b1 .
e) Use the estimated regression equation to predict the value of y when x = 4.

Solution 2

a)

16

14

12
10

8 Series1

4
2

0
0 1 2 3 4 5 6

b) There appear to be a linear relationship between x and y.

c) Mnany straight lines could be drawn to approximate the relationship between x and y;
in part d) we will determine the equation of a straight line that best represents the
relationship according to the least squares criterion.
d. Summation needed to compute the slope and y-intercept:

x y  x  x  y i  y  = 26,  x  x  = 10
2
i  15 i = 40, i i

b1 
  x  x  y  y   26  26
i i

 x  x 2
i
10

b0  y  b1 x  8  ( 2.6)(3)  0.2

yˆ  0.2  2.6 x

e) yˆ  0.2  2.6(4)  10.6

Question 2

Given are five observations for two variables, x and y.

xi 2 3 5 1 8

yi 25 25 20 30 16

f) Develop a scatter diagram for these data


g) What does the scatter diagram developed in part (a) indicate about the relationship
between the two variables?
h) Try to approximate the relationship between x and y by drawing a straight line
through the data.
i) Develop the estimated regression equation by computing the values of b0 and
b1 .
j) Use the estimated regression equation to predict te value of y when x = 6.

Solution 2

a)
35

30

25
Series1
20 Series2
15 Series3
Series4
10

0
0 2 4 6 8 10

b) There appear to be a linear relationship between x and y.

c) Mnany straight lines could be drawn to approximate the relationship between x and y;
in part d) we will determine the equation of a straight line that best represents the
relationship according to the least squares criterion.

d. Regression equation:

yˆ  30.33  1.88 x

e) 26.566

Question 3

The data from Exercise 1 follow:

xi 1 2 3 4 5

yi 3 7 5 11 14

The estimated regression for these data is yˆ  0.2  2.6 x

a) Compute SSE, SST, and SSR


b) Compute the coefficient of determination r 2 . Comment on the goodness of fit.
c) Compute the sample correlation coefficient.

Solution 3
a) ˆ  0 .2  2 .6 x
y and y  8

xi yi

yi  yi  y i   yi  y i  2  yi  y   yi  y  2

1 3 2.8 0.2 0.04 -5 25


2 7 5.4 1.6 2.56 -1 1
3 5 8.0 -3.0 9.00 -3 9
4 11 10.6 0.4 0.16 3 9
5 14 13.2 0.8 0.64 6 36

SSE = 12.4 SST = 80

SSR = SST – SSE = 80 – 12.4 = 67.6

SSR 67.6
b) r 2    0.845
SST 80

The least squares line provided a good fit: 84.5% of the variability in y has been
explained by the least squares line

c) r 0.845  0.9192

Question 4.

Data from exercise 1 follow

xi 1 2 3 4 5

yi 3 7 5 11 14

a) Compute the mean square error.


b) Compute the estimate of  .
c) Compute the estimated standard deviation of b1 .
H 0 : 1  0
d) Use the t test to test the following hypotheses (   0.05 ):
Ha :  1  0
e) Use the F test to test the hypotheses in (d) at a 0.05 level of significance.

Solution 4

SSE 12.4
a) s 2  MSE    4.133
n2 3
b) s MSE  4.133  2.033
s 2.033
c)  x i  x   10
2 sb1 
 x i  x
2

10
 0.643
b1  1 2.6  0
d) t    4.04
sb1 0.643
t 0.025 = 3.182 (3 degrees of freedom)

SSR
f) MSR =  67.6
1
MSR 67.6
F    16.36
MSE 4.133
F0.05 = 10.13 (1 degree of freedom numerator and 3 denominator)
Because F = 16.36 > F0.05 = 10.13, we reject H 0 :  1  0 .

Question 5
Data from question 2 follow:

xi 2 3 5 1 8

yi 25 25 20 30 16

a) Compute the mean square error.


b) Compute the estimate of  .
c) Compute the estimated standard deviation of b1 .
H 0 : 1  0
d) Use the t test to test the following hypotheses (   0.05 ):
Ha :  1  0
e) Use the F test to test the hypotheses in (d) at a 0.05 level of significance.

Solution 5

a) 2.11
b) 1.453
c) 0.262
d) Significant

SSE = 6.33 SST= 114.5 SSR = SST – SSE = 108.47

F = MSR/MSE = 108.47 / 2 .1 = 51.7

You might also like