AUTOMOTIVE STUDY 2025 / Šaroch (ed.) et al.

Fig. 4.1: Relationship between value drivers and parameters used to calculate EVA based on the value spread

Following the analysis of EVA drivers, an investigation of the causes of EVA volatility in individual countries over time is also conducted. For this purpose, we use multivariate regression analysis, for which the „Data Analysis“ tool in MS Excel was used. e independent variables are the value drivers identi ed above (invested capital turnover, operating pro t margin, after-tax cost of debt, unlevered cost of equity, leverage of invested capital and investment dynamics). e objective is to identify the impact of each independent variable on EVA and to assess the statistical signi cance of these e ects using regression coe cients and corresponding p-values. e outputs of the analysis include the coe cients of the independent variables, the R-Squared values, and p-values, which are further interpreted in the economic and business context. e regression model is formulated as follows: EVA = β 1(turnover of invested capital) + β 2(operating pro t margin) + β 3(after tax cost of debt) + β 4(unlevered cost of equity) + β 5(leverage of invested capital) + β 6(investment dynamics) + ϵ where βi represents the regression coe cients for the independent variables and ε denotes the model error. e model speci cation excludes a constant term, aligning with the assumption that EVA = 0 when all independent variables are set to zero. is approach enables a direct assessment of the impact of the independent variables on the dependent variable EVA. e assumptions of the regression model, such as normality and homoskedasticity of residuals, are validated using residual plots generated in MS Excel. Although MS Excel lacks built-in tools for computing multicollinearity diagnostics such as Variance In ation Factor (VIF), the analysis focuses on interpreting statistical signi cance and overall model t.

100