Exam Questions and CORRECT Answers
Least Squares Method - CORRECT ANSWER Uses sample data to estimate the regression
equation. Minimizes the sum of squared deviations between the observed values of variable yi
and the predicted variable yi-hat. For a good fit to the data, we want the differences between the
observed values and the predicted values to be small.
Simple Linear Regression - CORRECT ANSWER An equation estimating the relationship
between two variables, the variable being predicted (dependent variable) and the variable used to
predict (independent variable). Regression model: beta0 and beta1 are parameters and E is a
random variable called the error term. The error term accounts for the variability in y that cannot
be explained by the linear relationship between x and y.
SST - CORRECT ANSWER A measure of how well the observations cluster around the y-
bar line.
SSE - CORRECT ANSWER A measure of how well the observations cluster around the y-
hat (predicted) line.
SSR - CORRECT ANSWER A measure of how well the observations cluster around the
y-hat (predicted) line.
SSR: how much the y-hat values on the estimated regression line deviate from y-bar.
SSR/SST=1 - CORRECT ANSWER The regression line perfectly fits the sample data.
Coefficient of determination - CORRECT ANSWER r^2, equals SSR/SST. Evaluates the
goodness of the fit of the estimated regression equation. SSR=0, then SSR/SST=0
Correlation coefficient - CORRECT ANSWER Takes on values between -1 and 1. Equal
to r.