Page 96 - Basic Statistics

91

The interpretation of is that 69.75 % of the variation in the dependent variable
is “ explained” by its linear relationship with the independent variable.

d. Testing of the coefficient  1

T-statistic testing on two-taild hypothesis is use to test partially

coefficient. Because of its simple linear regression there is only one coefficient

which tested then tested under these conditions, the t-statistic test the same as

F-statistical test has been done above.

Hypotheses:
H 0 :  1 = 0

H 1 :  1  0

ˆ
2
Variance: S = MS(Res) / (  X − (  X j ) 2 / ) n
β1
j
= 0.0384 / [10156.66 - (348.8) 2 / 12 ]

= 0.0459

ˆ
ˆ
t-value = (β –0) / S
1
β1

= 0.2250 / 0.0459 = 4.80

In the t distribution table obtained: t0.05/2;10 = 2.228

Test results:  t  > t/2;10., i.e. 4.80 > 2.228, then H0 is rejected at the 5 percent

significance level. This means that  1 is significantly different to zero. It was

concluded that the rate of car sales affect the increased consumption of .

gasoline.

~~* CHAPTER 5 LINEAR REGRESSION MODEL *~~