Regression
Linear Regression
当x和y都是连续性变量时,使用回归模型。
y = β0 + β1x + ε
x: explanatory/predictor
y: response
ε: error, but always drop off since the model is focus on average outcome
Coefficient: Least Square Estimation,找到一条直线minimize the sum of the squared residuals.(SSE)
S(β0, β1) = [y- (β0+β1x)]^2, 求β0, β1偏导, 使值等于0,解方程可得Coefficient
Why Least Square Estimation?