Linear Regression Flashcards
b subset 0
the intercept
b subset 1
slope coefficient
slope coefficient equation
Cov(Y,X)/Var(X)
covariance equation
sum of the cross products, divided by n-1
cross product equation
(x-xbar)*(y-ybar)
variance equation
sum of the squared deviations, divided by n-1
coefficient of determination measures…
the fraction of the total variation in the dependent variable that is explained by the independent variable
coefficient of determination formula
(total variation-unexplained variation)/total variation
sample correlation coefficient formula
Cov/(sdX*sdY)
Total variation (TSS) is
the sum of SSE and RSS
SSE
the sum of squared errors or residuals aka the residual sum of squares
RSS
the regression sum of square. it is the amount of total variation in Y that is explained in the regression equation
correlation in a linear regression with only 1 independent variable..
absolute value of correlation equals the square root of the coefficient of determination (R-squared). the correlation will have the same sign as the slope coefficient
standard error computation
square root of (unexplained variation/n-2)
sample variance computation
total variation/n-1
sample standard deviation computation
square root of (total variation/n-1)
