16. In a perfect positive correlation: (1) Y will increase if X will increase. (2) Y-intercept will increase if X will increase.

A. 2 only

B. both 1 and 2

C. 1 only

D. neither 1 nor 2

17. In a perfect negative correlation: (1) forecasted value is equal to the actual value. (2) Y decreases as X increases.

A. 1 only

B. 2 only

C. both 1 and 2

D. neither 1 nor 2

18. In a perfect negative correlation: (1) the slope is negative. (2) SST is equal to SSE.

A. 1 only

B. neither 1 nor 2

C. both 1 and 2

D. 2 only

19. In a perfect negative correlation: (1) the y-intercept is negative. (2) SST is equal to SSR.

A. both 1 and 2

B. 1 only

C. neither 1 nor 2

D. 2 only

20. In a perfect negative correlation: (1) correlation coefficient is either positive or negative. (2) SSE is zero.

A. both 1 and 2

B. neither 1 nor 2

C. 2 only

D. 1 only

21. In a perfect negative correlation: (1) coefficient of determination is less than 1. (2) SSR is less than 1.

A. 2 only

B. 1 only

C. neither 1 nor 2

D. both 1 and 2

22. In a perfect negative correlation: (1) Y is equal to Y-intercept. (2) SSE is equal to zero.

A. neither 1 nor 2

B. both 1 and 2

C. 1 only

D. 2 only

23. In a perfect negative correlation

A. the forecast is higher than the actual value.

B. the y-intercept is negative.

C. SST is equal to SSR.

D. the forecast is lower than the actual value.

24. No correlation

A. means that X affects the value of Y if regression model is use to make a forecast.

B. means that if regression model will be used to predict the value of Y, the dependent variable will increase or decrease for every change in the value of X.

C. means the chosen X is not a good predictor of Y.

D. means that X affects the value of Y if mean of Y is use to make a forecast.

25. The sum of the squares total (SST): (1) is the sum of the squared errors assuming the mean of Y is use to predict or forecast the value of Y. (2) is the sum of the squared errors if the regression model is used to predict or forecast the value of Y.

A. 2 only

B. neither 1 nor 2

C. 1 only

D. both 1 and 2

26. The sum of squares regression (SSR): (1) is the sum of squared errors that are minimized or eliminated by using the regression model to make a forecast of Y. (2) is the sum of squared errors that are unexplained or not eliminated by using the regression model to make a forecast of Y.

A. both 1 and 2

B. neither 1 nor 2

C. 1 only

D. 2 only

27. The y-intercept

A. is the value of Y when X is negative.

B. is not the function of X to predict the value of Y.

C. may be related to X that affects the forecasted value of Y.

D. can be a function of X to predict the value of Y.

28. A regression line

A. has a negative slope if the direction is upward sloping and a positive slope if the direction is downward sloping.

B. may or may not be a perfect straight line because sometimes X has no correlation to dependent variable.

C. is a line that represents the actual values of the dependent variable because the coefficient of determination is equal to 1 and therefore no forecast errors that occurred.

D. is a perfect straight line.

29. SSE

A. is the total variability in dependent variable about the mean of that dependent variable.

B. may be equal to SST.

C. cannot be zero both in concepts and in real world situations.

D. represents the ratio of how effective the independent variable to forecast the dependent variable.

30. SSR

A. represents the ratio of how effective the independent variable to forecast the dependent variable.

B. is also the coefficient of determination.

C. can be zero.

D. is the explained variability in dependent variable after using the mean of X to forecast Y.