Scribd
Upload
3 views9 pages

Multiple Regression Analysis Overview

The document presents a multiple regression analysis involving one dependent variable and two independent variables, detailing the regression equation and the analysis of variance (ANOVA). The regression equation derived is y = -18.3683 + 2.010185x1 + 4.737812x2, and the hypothesis testing shows a significant relationship among the variables with a p-value of 0.000113, leading to the rejection of the null hypothesis. The ANOVA results indicate that the regression model is statistically significant with an F-value of 43.4957.

Uploaded by

alfredpennyworth865
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views9 pages

Multiple Regression Analysis Overview

The document presents a multiple regression analysis involving one dependent variable and two independent variables, detailing the regression equation and the analysis of variance (ANOVA). The regression equation derived is y = -18.3683 + 2.010185x1 + 4.737812x2, and the hypothesis testing shows a significant relationship among the variables with a p-value of 0.000113, leading to the rejection of the null hypothesis. The ANOVA results indicate that the regression model is statistically significant with an F-value of 43.4957.

Uploaded by

alfredpennyworth865
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

MULTIPLE REGRESSION

REGRESSION EQUATION AND ANALYSIS OF VARIANCE


TWO INDEPENDENT VARIABLE AND ONE
DEPENDENT VARIABLE
• Consider the following data for a dependent variable 𝑦 and two
independent variables, 𝑥1 and 𝑥2 .
ESTABLISHING MULTIPLE REGRESSION
EQUATION

yi   0  1 x1i   2 x2i   i ; i  1, 2,..., n


E  yi    0  1 x1i   2 x2i
Y  X
 X X  X Y
1
T T
SYSTEMS OF EQUATIONS OF DATA
 0  301  12 2  94 1 30 12  94 
1 10  108 
 0  47 1  10 2  108  47  
 0  251  17  2  112 1 25 17  112 
   
 0  511  16 2  178 1 51 16 
 0  
178 
1 40 5    94 
 0  401  5 2  94    1    
1 51 19   175 
 0  511  19 2  175 1 
  2 
170 
74 7
 0  741  7  2  170    
1 36 12  117 
 0  361  12 2  117 1 59 13 142 
   
 0  591  13 2  142 1 76 16   211
 0  761  16 2  211 X Y
SOLUTION OF SYSTEM
 0 
 
 
1
  X X X Y ;    1 
T T

 
 2
  0   18.3683
   
   1    2.010185
    4.737812 
 2  
Regression equation: y  18.3683  2.010185 x1  4.737812 x2
HYPOTHESIS TESTING

Null hypothesis: 𝐻0 : 𝛽1 = 𝛽2 = 0

Alternative hypothesis 𝐻1 : 𝛽1 𝑎𝑛𝑑/𝑜𝑟𝛽2 ≠ 0

Level of significance, 𝛼 = 0.05

Critical value, 𝐶𝑉 = 4.7374


ANOVA CALCULATIONS
𝒚 = −𝟏𝟖. 𝟑𝟔𝟖𝟑 + 𝟐. 𝟎𝟏𝟎𝟏𝟖𝟓𝒙𝟏 + 𝟒. 𝟕𝟑𝟕𝟖𝟏𝟐𝒙𝟐
𝑦 𝑦ො 𝑦 − 𝑦ത 𝑦 − 𝑦ത 2 𝑦 − 𝑦ො 𝑦 − 𝑦ො 2
94 98.79103 -46.1 2125.21 -4.79103 22.95398
108 123.4886 -32.1 1030.41 -15.4886 239.8954
112 112.4292 -28.1 789.61 -0.42916 0.184182
178 159.9562 37.9 1436.41 18.04383 325.5799
94 85.7282 -46.1 2125.21 8.2718 68.42267
175 174.1696 34.9 1218.01 0.830397 0.689558
170 163.5501 29.9 894.01 6.449878 41.60093
117 110.8521 -23.1 533.61 6.147858 37.79615
142 161.8242 1.9 3.61 -19.8242 392.9995
211 210.2108 70.9 5026.81 0.789201 0.622839
TOTAL TOTAL TOTAL TOTAL TOTAL TOTAL
1401 1401 0 15182.9 0 1130.745
REGRESSION EQUATION AND ANOVA TABLE

ANOVA

df SS MS F Significance 𝐹𝑐
F (p-value)
Regression 2 14052.15 7026.077 43.4957 0.000113 4.7374
Residual 7 1130.745 161.535
Total 9 15182.9

y  18.3683  2.010185x1  4.737812 x2


CONCLUSION

The p-value, 0.000113 is less than the significance level, 0.05;


therefore, the null hypothesis is rejected. We conclude that the
regression coefficient is not equal to 0 and that there is indeed a
relationship among 𝑦, 𝑥1 𝑎𝑛𝑑 𝑥2 .

You might also like