Page 34 - JOJAPS_VOL15

Table 3: Multicollinearity Test

Model Collinearity Statistics
Tolerance VIF
(Constant)
1 DER .605 1.652
SALES .532 1.880
CS .449 2.227

4.3.3 Heteroscedasticity Test
This test is made by looking at the scatterplot graphs. Based on the results of testing as shown in figure 4.1, it can be seen that
the plot distribution does not form a specific pattern and is spread above and below the number 0 on the Y-axis. It can be concluded
that all variables in this study are free from the heterocedasticity assumption.

Picture 4.1 Heteroscedasticity Test

4.3.4 Hypothesis Test

4.3.4.1 Analysis of the Coefficient of Determination
If we see from table 4, we know the value of R Square is 0.577. It means that DER, SALES and CS can explain external factors of
the research variable explain 5.77% of the variable GPM and the remaining 94.23%.

b
Table 4 Model Summary
Model R R Square Adjusted R Std. Error of the
Square Estimate
a
1 .760 .577 -.692 .01961
a. Predictors: (Constant), CS, DER, SALES
b. Dependent Variable: ABS

4.3.4.2 Effect of Liquidity, Capital Structure and Sales on Gross Profit Margin Partially at PTPN III (Persero) Medan in
2012-2016
a
Table 5 Coefficients
Model Unstandardized Coefficients Standardized t Sig.
Coefficients
B Std. Error Beta
(Constant) -57.879 8.438 -6.859 .092
1 DER .524 .043 .621 12.285 .052
SALES 3.886 .526 .398 7.385 .086
CS -.563 .059 -.558 -9.515 .067
a. Dependent Variable: GPM

27 | V O L 15