This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: t = estimate - hypothesized value [mean] / standard error of the estimate In a regression setting, if you don’t reject H0 you will actually accept it Different than in hypothesis testing when you do not accept H0 R^2 tells you the proportion of total variability explained by your linear regression model F test is to test is B1=0 or not testing the overall usefulness of the model credit scores → log(x+1) because some people have 0 savings so you cannot do log(0) but log(1) = 0 *** btwn -% and .1% error ** btwn .1% and 1% error * btwn 1% and 5% error . btwn 5% and 10% The lower p value, the better degrees of freedom n - 2 → simple regression n-k-1 → multiple regression; k = number of variables...
View Full Document
- Fall '13
- Regression Analysis, 10%, 1%, 5%, Errors and residuals in statistics, abline