Result of multicolinearity test

commit to user 43 Factor Analysis CFA test used to test whether the construct have unidimentionality or the indicators can confirm the construct or variable. Table 5 Validity Result Variables Kaiser-Meyer- Olkin Measure of Sampling Adequacy Initial Eigen values Cumula tive Significant Status Need for achievement NA .723 63.701 .000 valid Work attitude WA .772 39.174 .000 valid Budgetary participation BP .757 59.526 .000 valid Job performance JP .821 47.638 .000 valid The result of CFA test, Kaiser-Meyer-Oklin Measure of Sampling Adequacy KMO MSA to each variable is more than 0.50 this is fulfilling assumption of factor analysis and reliable and also assess the Bartletts Test of Sphericity BTS by chi-square is significant of hence inferential that factor analysis can be continued. In conclusion the data of these research questionnaires were reliable and valid to be measured. If we have met the valid and reliable data, so we can continue the next step of this research which is measuring the hypotheses of this research.

D. Classic Assumption Analysis

1. Result of multicolinearity test

The goal of multicollinierity test is to test whether the regression model found the correlation between the independent variables. The good regression model must not have correlation between the independent variables. If the commit to user 44 independent variables have correlation, so the variables are not orthogonal. The result of multicolinearity test is summarized as follow: 1 The first regression model the dependent variable: budgetary participation Table 6 Multicollinearity test result Model Unstandardized Coefficients Standar dized Coeffici ents t Sig. Collinearity Statistics B Std. Error Beta Toler ance VIF Constant 13.627 4.948 2.754 .008 Need for achievement .378 .123 .340 3.078 .003 .982 1.018 Work attitude .086 .047 .201 1.823 .073 .982 1.018 Dependent variable: Budgetary Participation 2 The second regression model the dependent variable: job performance Table 7 Multicollinearity test result Model Unstandardized Coefficients Standar dized Coeffic ients t Sig. Collinearity Statistics B Std. Error Beta Toler ance VIF Constant 27.825 7.105 3.916 .000 Need for achievement .577 .179 .342 3.232 .002 .864 1.158 Work attitude .014 .066 .021 .210 .835 .937 1.067 Budgetary participation .543 .164 .359 3.312 .001 .826 1.211 Dependent variable: Job Performance The result multicollinearity test from the independent variables examinee of both regression model above, the correlation among independent variables is commit to user 45 not exceed boundary 95 Appendix III. Hence it can be told there is no multicolinearity. Result of calculation assess the tolerance seen that there is no independent variable owning value tolerance is less than 0.10 it means that there is no correlation between variable independent which more than 95. The calculation result of Variation Inflation Factor VIF from four independent variables of examinee, there is no VIF value which more than 10 Appendix III, hence it can be conclude that there are no multicollinearity between variable independents in regression model.

2. Result of heteroskedasticity test