MVS250-regression

What is the equation for a regression line with two variables in a linear relationship? What do the variables in the equation mean?

What is another name for a regression line? what does it do?

the line of best fit

• balances the data so that the total vertical distance between each point above and below the line are balanced.

• average distance below = average distance above

What is the vertical distance from the line called?

residual; amount of variability in y/ measures the distance between regression line and actual data.

what is the formula for the residuals? what do the variables mean?

What are the calculations?

What is the goal of the least squares solution?

to find a line that minimizes the values of residuals (most accurately describes the relationship between x and y)

What is the equation for total squared error?

What is the formula to calculate b (slope) for the least squared solution? what does it mean?

how to find the y-intercept?

What are the issues with extrapolating?

What are the regression assumptions?

1. each observation is independent of each other

2. at each value of X, the Y scores are normally distributed

3. across all values of X, the residuals (e_i) are normally distributed (homoscedasticity)

Independence

Normal distribution of Y at each X

Homoscedasticity

Confidence in predicted estimates

Confidence in predicted estimates