previous experience in industry (V10), visibility of investment in local community (V11), acquisition of reputable brand (V12), preventing competitors to enter the B&H`s market (V13). Results of the analysis are given in the following text.
Table 5. below shows summary of regression model. R square amounts to 0,155 and indicates that predictive power of the model is 15,5%. Model`s strength is poor, but adjusted R square is lower than R square, so there is no need for introduction of other factors to explain the changes in dependent variable. Durbin Watson statistic is 1,983, which is close to value of 2 and indicates that there is no autocorrelation.
Table5: Model summary – Irrational predictors
Model
R
R Square
Adjusted
R Square …show more content…
Collinearity Statistics B Std. Error Beta Tolerance VIF
1 (Constant) 5,312 1,920 2,767 ,009 Reducing dependence from suppliers as a factor in FDI decision making -,043 ,272 -,028 -,159 ,874 ,845 1,184 Acquiring new technology as a factor in FDI decision making -,493 ,327 -,279 -1,505 ,142 ,786 1,272 Upgrade in value chain as a factor in FDI decision making -,415 ,383 -,200 -1,085 ,286 ,795 1,258 ROI as a factor in FDI decision making ,171 ,285 ,120 ,600 ,553 ,677 1,476 Feasibility analysis done by third, reputable party as a factor in FDI decision making ,094 ,257 ,069 ,365 ,718 ,749 1,334
a. Dependent Variable: An average annual amount of DI by company in last 3 years (mill BAM)
Source: Authors (SPSS)
By looking at unstandardized B coefficients another regression model is formed, this one with rational factors in FDI decision making. The model is given below.
(2)
Equation (2) shows contribution of each predictor variable (factor involved in FDI decision making based on standard economic theory) to average annual amount that company invests in foreign markets. Only two out of five included factors actually is related to higher amount of investment. These are ROI and feasibility analysis done by third reputable
Table 5. below shows summary of regression model. R square amounts to 0,155 and indicates that predictive power of the model is 15,5%. Model`s strength is poor, but adjusted R square is lower than R square, so there is no need for introduction of other factors to explain the changes in dependent variable. Durbin Watson statistic is 1,983, which is close to value of 2 and indicates that there is no autocorrelation.
Table5: Model summary – Irrational predictors
Model
R
R Square
Adjusted
R Square …show more content…
Collinearity Statistics B Std. Error Beta Tolerance VIF
1 (Constant) 5,312 1,920 2,767 ,009 Reducing dependence from suppliers as a factor in FDI decision making -,043 ,272 -,028 -,159 ,874 ,845 1,184 Acquiring new technology as a factor in FDI decision making -,493 ,327 -,279 -1,505 ,142 ,786 1,272 Upgrade in value chain as a factor in FDI decision making -,415 ,383 -,200 -1,085 ,286 ,795 1,258 ROI as a factor in FDI decision making ,171 ,285 ,120 ,600 ,553 ,677 1,476 Feasibility analysis done by third, reputable party as a factor in FDI decision making ,094 ,257 ,069 ,365 ,718 ,749 1,334
a. Dependent Variable: An average annual amount of DI by company in last 3 years (mill BAM)
Source: Authors (SPSS)
By looking at unstandardized B coefficients another regression model is formed, this one with rational factors in FDI decision making. The model is given below.
(2)
Equation (2) shows contribution of each predictor variable (factor involved in FDI decision making based on standard economic theory) to average annual amount that company invests in foreign markets. Only two out of five included factors actually is related to higher amount of investment. These are ROI and feasibility analysis done by third reputable