3. There are many measures that we use to determine how well two variables correlate. Pick one of these and discuss what it is. What range would we like the value to fall in to be comfortable using one variable to predict or estimate the value of another? Why?
The linear correlation coefficient
The coefficient of determination
The standard error
4. A line of best-fit can only be used to predict or estimate y-values for x-values within the domain of the data set from which the best-fit line was determined. Why is this so? For example, if the domain of the data set was 25 < x < 221 and we wanted to predict a y-value for an x- value of 250, why would the best-fit line return a meaningless result?
