Regression Analysis: FamIncome_00 versus HomeValue_00, Education_Yr, ...
Y=α+β1X1+ β2X2 + β3X3 + ………..+βkXk + ε
Y=α+β1X1+ β2X2 + β3X3 + β4X4+β5X5 + ε
y= a +b1x1+ b2x2+ b3x3 + b4x4+ b5x5 + e
Regression Analysis: FamIncome_00 versus HomeValue_00, Education_Yr, ...
The regression equation is
FamIncome_000$ = 70.6 + 0.0717 HomeValue_000$ + 1.624 Education_Yrs
- 0.122 Age_Yrs - 0.00101 Mortgage + 1.81 Gender
Interpretation:
a=70.6 (y-intercept)
b1=0.0717: an increase of $1000 in the value of home suggests an increase of $72
in family income.
b2=1.62: an increase of 1 year of education increases income by $1624
b3:-0.122: one year older reduces income by 122 dollars.
b4: -001: an increase of $1000 in the mortgage, reduces income by $1
b5: 1.81: there is positive impact of gender on income.
Predictor Coef SE Coef T P
Constant 70.606 7.464 9.46 0.000
HomeValue_000$ 0.07167 0.01242 5.77 0.000
Education_Yrs 1.6242 0.6031 2.69 0.014
Age_Yrs -0.12238 0.07814 -1.57 0.134
Mortgage -0.001012 0.003172 -0.32 0.753
Gender 1.8066 0.6228 2.90 0.009
If p<α, H0 is rejected (p<0.10, weak, p<0.05, strong, p<0.01, very strong,
p<0.001, extremely strong evidence)
Evaluate individual regression coefficients:
Y=α+β1X1+ β2X2 + β3X3 + β4X4+β5X5 + ε
P=0.000<0. P=0.000<0. P=0.014 P=0.134>0.10P= P=0
H0 is accepted
01, Ho is 001, H0 is <0.05, Age is NOT 0.7 .00
rejected rejected Ho is important 5> 9<0
rejected predictor to0.1 .05,
predict family
i.e.educa income 0, Ho
tion is an H0 is
importan is reje
t factor acc cte
for ept d
income ed
H0: α=0 H0: β1=0 H0: β2=0 H0: β3=0 H0: H0:
H1: α≠0 H1: β1≠0 H1: β2≠0 H1: β3≠0 β4 β5=
=0 0
H1: H1:
β4 β5≠
≠0 0
Decision rule: If t (cal)>t(tab), H0 is rejected.
Alternative decision rule: If p<α, H0 is rejected.
S = 1.47779 (units of income) R-Sq = 75.0% R-Sq(adj) = 68.4%
Analysis of Variance
Source DF SS MS F P
Regression 5 124.322 24.864 11.39 0.000
Residual Error 19 41.494 2.184
Y=α+β1X1+ β2X2 + β3X3 + β4X4+β5X5 + ε
Tot Global Test/MLR Model Test/Overall Significance Test
H0: β1=β2= β3=β4= β5=0
H1: Not all are equal to zero (at least two of them are not equal to zero).
Alternative formulation of hypotheses for global test:
H0: R2=0 vs H1: R2≠0
P=0.000<0.001,H0 is rejected. Ie. The model is useful, the model is well fitted.
p-value is the probability value. p-value is the probability of observing
a sample value as extreme as, or more extreme than, the value
observed, given that the nyll hhyothesis is true. If p<level of
significance (α), then the H0 is rejected .
Interpretation:
If the p-value is less than
(a) 10%, we have some/weak evidence that H0is rejected.
(p<0.10)
(b)5%, we have strong evidence that H0is rejected. (p<0.05)
(c) 1%, we have very strong evidence that H0is rejected.
(p<0.01)
(d)0.1%, we have extremely strong evidence that H0is rejected.
(p<0.001)
Correlations: FamIncome_00, HomeValue_00, Education_Yr, Age_Yrs,
Mortgage, ...
FamIncome_000$ HomeValue_000$ Education_Yrs Age_Yrs
HomeValue_000$ 0.720
0.000
Education_Yrs 0.188 -0.144
0.368 0.493
Age_Yrs 0.243 0.220 0.621
0.243 0.292 0.001
Mortgage 0.116 0.358 -0.210 -0.038
0.582 0.079 0.313 0.857
Gender 0.486 0.184 0.062 0.156
0.014 0.378 0.769 0.457
Mortgage
Gender -0.129
0.539
Cell Contents: Pearson correlation
P-Value
The regression equation is
FamIncome_000$ = 70.6 + 0.0717 HomeValue_000$ + 1.62 Education_Yrs
- 0.122 Age_Yrs - 0.00101 Mortgage + 1.81 Gender
Predictor Coef SE Coef T P
Constant 70.606 7.464 9.46 0.000
HomeValue_000$ 0.07167 0.01242 5.77 0.000
Education_Yrs 1.6242 0.6031 2.69 0.014
Age_Yrs -0.12238 0.07814 -1.57 0.134
Mortgage -0.001012 0.003172 -0.32 0.753
Gender 1.8066 0.6228 2.90 0.009
Multiple coefficients of determination:
2 SSR Explained variation
R= =
SSTotal Total variation
Multiple Standard Error (SE) is given by
S=
S = 1.47779
√ ∑ ( y− ^y )2
n−(k +1)
R-Sq = 75.0%
=
√ SSE
n−(k +1)
=√ MSE
R-Sq(adj) = 68.4%
b− β
t= ~ tα, n-(k+1)
sb
Analysis of Variance
Source DF SS MS F P
Regression 5 124.322 24.864 11.39 0.000
Residual Error 19 41.494 2.184
Total 24 165.815
Correlations: FamIncome_00, HomeValue_00, Education_Yr, Age_Yrs,
Mortgage, ...
FamIncome_000$ HomeValue_000$ Education_Yrs Age_Yrs
HomeValue_000$ 0.720
0.000
Education_Yrs 0.188 -0.144
0.368 0.493
Age_Yrs 0.243 0.220 0.621
0.243 0.292 0.001
Mortgage 0.116 0.358 -0.210 -0.038
0.582 0.079 0.313 0.857
Gender 0.486 0.184 0.062 0.156
0.014 0.378 0.769 0.457
Mortgage
Gender -0.129
0.539
Cell Contents: Pearson correlation
P-Value
