In Excel regression output, the coefficient labeled “Intercept” provides:

Multiple regression includes one dependent variable and two or more independent variables.

Given a regression model Loyalty=4.290+1.095(Price)+1.637(SR) If price increases by 0.20 and SR is unchanged, what is the predicted change in loyalty? (enter a number value with 3 decimals)

Why can Multiple R be deceptive in simple regression?

Loyalty=0.40856+7.601(Quality)−1.451(NegInfo) Holding quality constant, if NegInfo decreases by 0.25, what is the predicted change in loyalty? (enter a number value with 3 decimals)

In Module 8, p-values are described as being similar to alpha values, but with an important difference. Which statement best captures that difference?

A correlation value can normally fall outside the range from -1 to +1.​

A regression model has a lower standard error than another otherwise similar model. Based on Module 8’s interpretation, this generally suggests:

Module 8 compares standard error in regression to which familiar statistical idea?

If a regression model has an R-square = 0.697, what percent of variation in the model is not explained? (answer as percent with 1 decimal, e.g., 46.5%, and include % sign)