Audit Experience .911 1.097
(Source: Primary Data Processed, 2017) “
Based on the table above it can be seen that
tolerance number of independent variable has a
value greater than 0.1 which means that there is no
correlation between independent variables.”
4.5 Heteroscedasticity Test
The glesjer test results show that the
significance probability of the education level
variable is 0.016 (smaller than 5%) which means
that the regression model loosens heteroscedasticity.
The significance probability of the competency
variable is 0.498 (greater than 5%) which means that
the regression model does not preclude
heteroscedasticity. The significance probability of
the motivation variable is 0.855 (greater than 5%)
which means that the regression model does not
preclude heteroscedasticity. The significance
probability of the variable fee is 0.930 (greater than
5%) which means that the regression model does not
preclude heteroscedasticity. The probability of
significance of the professionalism variable is 0.097
(greater than 5%) which means that the regression
model does not preclude heteroscedasticity. The
significance probability of the audit experience
variable is 0.084 (greater than 5%) which means that
the regression model does not preclude
heteroscedasticity.
4.6 Autocorrelation Test
Based on the results of the above analysis shows that
Durbin Watson obtained 1.333 with a sample of 39,
the number of variables 6, then formulated “dl < dw
< 4-du ie 1.161 < 1.333 < 1.858“. The conclusion is
that du approaches number 2, so there is no
correlation in the regression model.
4.7 Multiple Regression Test
To facilitate reading the results of multiple
regression tests, the regression model equation will
be used. The following is a description of the results
of multiple regression testing and output of the test
table using the help of SPSS version 16 in the form
of output model summary, ANOVA (F test), and
coefficient (t test).
Y = 16,150 + 1,906 + 0,998 + 0,638 + 1,592 +
0,934 + 0,693 + e (1)
From the above equation, it can be interpreted
as follows:
Regression model listed constant value of
16,150 can be interpreted if the variables outside
the
model will still improve audit quality by 16,150
units. Variable X1 is the level of education with
unstandardized coefisients (B) value of 1.906 which
means that the education level has a positive effect
on audit quality. This shows that when the audit
quality has increased by a unit, then the level of
education will also experience an increase of 1,906
units. The X2 variable is the competence with
unstandardized coefisients (B) value of 0.998 which
means that competence has a positive effect on audit
quality. This shows that when audit quality has
increased by a unit, then competence will also
increase by 0.998 units. X3 variable is motivation
with unstandardized coefisients (B) value of 0.638
which means that motivation does not have a
positive effect on audit quality. The variable X4 is
the fee with unstandardized coefisients (B) value of
1.592 which means that the fee has a positive effect
on audit quality. This shows that when the audit
quality has increased by a unit, the fee will also
increase by 1,592 units. X5 variable is
professionalism with unstandardized coefisients (B)
value of 0.934 which means that professionalism
does not have a positive effect on audit quality. X6
variable is audit experience with unstandardized
coefisients (B) value of 0.693 which means that the
audit experience has no positive effect on audit
quality.
4.8 Simultan Test (F)
More precisely, the Fcount value is compared with
Ftable where if Fcount > Ftable, the independent
variables simultaneously have a significant effect on
the dependent variable. At the level of α = 0.05 with
the numerator's freedom degree / df1 (k) = 6 (the
number of independent variables) and the
denominator's degree of freedom / df2 (n-k-1) = 32,
the Ftable value is 2.40. Thus, the value of Fcount
30.592 is greater than the value of Ftable 2.40.
Based on the results of these calculations can be
interpreted that the variables level education,
competence, motivation, fee, professionalism and
audit experience together influence variables audit
quality.
4.9 Partial Test (t)
Based on the table above, the results of the t test on
education level state that the level of education