Normality Test Figure 4.1 Multicollinearity Test Autocorrelation test Table 4.6

13 F re q u e n c y Ex p e c te d C u m P ro b Table 4.3 Descriptive Statistics of All Variables during 2010--2012 Descriptive Statistics N Minimum Maximum Mean Std. Deviation PROF DER DVP MVC Valid N listwise 90 90 90 90 90 -0.19 -31.78 0.00 -93.49 0.42 40.37 365.00 39.47 0.1029 0.9630 23.4778 2.9281 0.11068 5.53641 47.31397 11.65168 Source: Secondary Data processed, 2014 C. Classical Assumption Test

1. Normality Test Figure 4.1

Histogram in Manufacturing Company Histogram Dependent Variable: MVC 25 20 15 10 5 -3 -2 -1 0 1 2 3 4 Mean = Regression Standardized Residual Source: Secondary data were processed, 2014 -3.47E-18 Std. Dev. =... Figure 4.2 Normal Probability Plot Manufacturing Company Normal P-P Plot of Regression Standardized Residual Dependent Variable: MVC 1.0 0.8 0.6 0.4 0.2 0.0 0.0 0.2 0.4 0.6 0.8 1.0 Observed Cum Prob Source: Secondary data were processed, 2014 14 Table 4.4 Normalities ManufacturingCompany One-Sample Kolmogorov-Smirnov Test Unstandardized Residual N Normal Mean Parametersa,b Std. Deviation Most Extreme Absolute Differences Positive Negative Kolmogorov-Smirnov Z Asymp. Sig. 2-tailed 90 0.0000000 2.32195453 0.071 0.053 -0.071 0.670 0.760 a Test distribution is Normal. b Calculated from data. Source: Secondary Data processed, 2014 Based on the results in Table 4.4 above, the data is normally distributed. This is indicated by the value of the Kolmogorov - Smirnov for 0.670 and 0.760 is significant at greater than 0.05. This means that the data is normally distributed residual, because the significance value is more than 0.05.

2. Multicollinearity Test

Multicollinearity in the regression can be seen from the value of Tolerance and Variance Inflation Factor VIF. Table 4.5 The Multicolinearity Test Result of Manufacturing Company Model Collinearity Statistics Tolerance VIF 1 Constant PROF 0.895 1.118 DER 0.987 1.013 15 DVP 0.906 1.104 a. Dependent Variable: MVC Source: Secondary data were processed, 2014 A regression model is free of multicollinearity problem if it has a value under 1 and VIF tolerance under 10. This show is not the case in the model multicollinearity.

3. Autocorrelation test Table 4.6

The Autocorrelation Test Result of Manufacturing Company Model Durbin-Watson 1 1.984 a Predictors: Constant, DVP, DER, PROF b Dependent Variable: MVC Source: Secondary Data processed, 2014 Based on the results of the regression analysis on the data value Manufacturing Company Durbin Watson DW of 1.984, DW-table size: dL outer boundary = 1.589; dU within limits = 1.726; 4-dU = 2.274, and 4-dL = 2.411. Because dU d 4-dU, 1.726 1.984 2.274 these results indicate that the regression model is there is no autocorrelation. R e g re s s io n

4. Heteroscedasticity