Ch7 Regression Exam Prep

MULTIPLE‑CHOICE TEST ITEMS

CHAPTER 7

REGRESSION

7.1 There is a negative correlation between years of heavy smoking and life expectancy. Therefore, for someone who has smoked heavily for many years, you would predict a life expectancy that is

a) short.

b) long.

c) relatively short.

d) relatively long.

7.2 When using a scatterplot, the customary direction of prediction is from

a) X to Y.

b) Y to X.

c) either X or Y depending on the perspective of the investigator.

d) either X or Y depending on which is more important.

7.3 Placement of the regression line in a scatterplot is inexact when

a) dots define a single straight line.

b) dots are scarce.

c) graphic techniques are used exclusively.

d) mathematical techniques are used exclusively.

7.4 In a scatterplot, predictive errors are associated with

a) discrepancies between dots and the regression line.

b) vertical discrepancies between dots and the regression line.

c) horizontal discrepancies between dots and the regression line.

d) either vertical or horizontal discrepancies between dots and the regression line.

7.5 Predictive errors are squared in order to

a) eliminate negative predictive errors.

b) exaggerate large predictive errors.

c) emphasize the importance of predictive errors.

d) evaluate the linearity of all predictive errors.

7.6 Given Y' = .005(X) + .40 for predicting college GPA from SAT critical reading scores, the coefficient of X (.005) indicates that the correlation between college GPAs and SAT I scores is a) weak.

b) strong.

c) negative.

d) positive.

7.7 Given Y' = .005(X) + .40 for predicting college GPA from SAT critical reading scores, the predicted GPA for a student with an SAT score of 600 would be

a) 0.70

b) 3.00

c) 3.40

d) 4.00

7.8 A student concentrates on raising his SAT score in order to raise his college GPA. This strategy is questionable because it assumes that the relationship between SAT scores and college GPAs is

a) reliable.

b) strong.

c) positive.

d) cause‑effect.

7.9 You might construct a graph showing the regression line for the purpose of

a) prediction.

b) description.

c) greater accuracy.

d) efficiency.

7.10 A predicted college GPA is unlikely to coincide with a student's true GPA because the relationship between SAT score and college GPAs is

a) weak.

b) imperfect.

c) negative.

d) curvilinear.

7.11 The least squares regression equation minimizes

a) predictive errors.

b) squared predictive errors.

c) the total of all predictive errors.

d) the total of all squared predictive errors.

7.12 If a least squares equation predicts annual income from years of education, as a college student you would prefer that the value of b, the slope of the equation, equal

a) .40

b) .80

c) 1.2

d) 1.6

7.13 If you were attempting to predict annual income from years of education, the standard error of estimate would be expressed in units of

a) dollars.

b) years.

c) squared dollars.

d) squared years.

7.14 Which one of the following numbers would be preferable for the standard error of estimate?

a) 20

b) 40

c) 100

d) 500

7.15 Before attempting to predict performance on a high stress job from anxiety scores, you should first establish that the underlying correlation is

a) positive.

b) negative.

c) strong.

d) non‑zero.

7.16 The greater the value of the sum of squares for predictive error, the smaller the

a) correlation coefficient.

b) standard error of estimate.

c) standard deviation of Y.

d) range of Y.

7.17 Use of the standard error of estimate assumes that

a) the underlying relationship is linear.

b) for any given X score, the corresponding distribution of Y scores is normal.

c) the scatterplot contains many dots.

d) dots are about equally dispersed about the regression line.

7.18 Assume that the equation for predicting the rate of inflation from the percent of unemployed workers is as follows:

.90(X) + 11

If the unemployment rate equals 10 percent, the inflation rate should equal

a) 2 percent.

b) 4 percent.

c) 15 percent.

d) 20 percent.

7.19 To achieve as much accuracy as possible, serious predictive efforts often base predictions on

a) only the mean.

b) a single predictor or X variable.

c) several predictors or X variables.

d) hundreds of predictor or X variables.

7.20 Significant regression toward the mean that occurs after a spectacular “rookie” performance is often referred to as

a) bad luck.

b) a move toward mediocrity.

c) the sophomore jinx.

d) none of the above.

7.21 Insofar as regression toward the mean occurs, a student who made the lowest score on the first statistics exam would be expected to score

a) more poorly on the second exam.

b) less poorly on the second exam.

c) about the same on the second exam.

d) any of the above, depending on circumstances.

7.22 The regression fallacy is committed whenever regression toward the mean is interpreted as an effect that is

a) real.

b) due to chance.

c) real but not important.

d) due to chance but important.

7.23 To avoid the regression fallacy, use

a) large numbers of subjects.

b) a second group of subjects that reflects just the effect of chance.

c) only subjects with extreme scores.

d) long intervals of time between successive measurements.

7.24 Watch out for the regression fallacy when working with

a) small children.

b) a general population.

c) underachievers.

d) college students.