click below
click below
Normal Size Small Size show me how
Exam 1 Part 4
Statistical Learning and Linear Regression
Question | Answer |
---|---|
What are the differences between population line and least squares line? | Population regression line is the least-squares regression line for all of the data, whereas least squares regression line is for the estimation of the population line. |
How to interpret R-squared value? | The closer R-squared is to 0, the worse the model is. We want the value to be at least 0.60, and as close to 1 as possible for most accurate model. |
There exists a horizontal regression line. What is the interpretation of this? | There is no relationship. |
How to interpret p-value? | alpha > 0.05, significant, fail to reject hypothesis. alpha <= 0.05, not significant, reject hypothesis. |
What is one-way ANOVA test? What to use it for? | Uses one independent variable to analyze the difference between the means of more than two groups. |
List assumptions for linear regression: | linear relationship, no or little multicollinearity, no auto-correlation, multivariate normal, and homoscedasticity |
What is multicollinearity? | This is when the independent variables are collinear with each other. They are strongly correlated with each other and not just with the dependent variable. |
When would there exist multiple lines in a linear regression problem? How to interpret these when they are not parallel? | Multiple lines considers the effect of more than one explanatory variable on the outcome. When not parallel, the explanatory variables affect the outcome variable differently. |