相関係数r の見方 0.7<|r|≦1 相関が強い 0.4<|r|<0.7 中間の強さ 0.2<|r|<0.4 相関が弱い 0≦|r|<0.2 相関がない
\(\normalsize\ e{\tiny -}Exponential\ regression\\ (1)\ mean:\ \bar{x}={\large \frac{{\small \sum}{x_i}}{n}},\hspace{10px}\overline{\ln y}={\large \frac{{\small \sum}{\ln y_i}}{n}},\hspace{10px}n={\small \sum}f_i\\ (2)\ trend\ line:\ y=Ae^{Bx},\hspace{10px} B={\large\frac{Sxy}{Sxx}},\hspace{10px} A=\exp({\overline{\ln y}-B\bar{x}})\\ \\ (3)\ correlation\ coefficient:\ r=\frac{\normalsize S_{xy}}{\normalsize \sqrt{S_{xx}}\sqrt{S_{yy}}}\\ \hspace{20px}S_{xx}={{\small \sum}(x_i-\bar{x})^2 f_i}={{\small \sum} x_i^2 f_i}-n \cdot \bar{x}^2\\ \hspace{20px}S_{yy}={{\small \sum}(\ln y_i-\overline{\ln y})^2 f_i}={{\small \sum} \ln y_i^2 f_i}-n \cdot \overline{\ln y}^2\\ \hspace{20px}S_{xy}={{\small \sum}(x_i-\bar{x})(\ln y_i-\overline{\ln y}) f_i}={{\small \sum} x_i \ln y_i f_i}-n \cdot \bar{x}\overline{\ln y}\\ \) |
|