Complete Test Bank Describing Relationships Correlation Ch6

MULTIPLE CHOICE TEST ITEMS

CHAPTER 6

DESCRIBING RELATIONSHIPS: CORRELATION

6.1 A single word that best describes the general notion of a relationship is

a) similarity.

b) dissimilarity.

c) regularity.

d) symmetry.

6.2 The intuitive approach to searching for a relationship becomes cumbersome and inexact when

a) there are more than a few pairs of observations.

b) little or no relationship is present.

c) the relationship is negative.

d) observations assume values with decimal points.

6.3 Without doing any calculations, describe the relationship for the following pairs of observations.

X Y

6 118

12 109

3 144

10 111

1 142

a) positive

b) negative

c) little or no relationship

d) impossible to describe

6.4 Which one of the following most likely describes a positive relationship?

a) automobile weight and gas mileage

b) test score and time to complete test

c) current age and remaining years of life expectancy

d) years of education and lifetime earnings

6.5 Scatterplots

a) depict relationships as dot clusters.

b) provide a preview of the fully measured relationship.

c) show any pronounced curvilinearity.

d) all of the above

6.6 A dot cluster that tilts from upper left to lower right reflects

a) little or no relationship.

b) a positive relationship.

c) a negative relationship.

d) a curvilinear relationship.

6.7 For the relationship between caloric intake and weight gain, the dot cluster should show

a) a tilt from the lower left to the upper right.

b) a tilt from the upper left to the lower right.

c) little or no tilt.

d) any of the above, depending on circumstances.

6.8 Given that the relationship between GPA and IQ is stronger in high school than in college, the dot cluster for high school (compared to that for college) should

a) less closely approximate a straight line.

b) more closely approximate a straight line.

c) define a straight line.

d) lack any apparent tilt.

6.9 Which one of the following relationships is perfect?

a) heights and weights of newborn infants

b) heights and weights of well‑trained athletes

c) heights of adults, each described twice--once in inches and once in centimeters

d) heights of twins

6.10 Which one of the following numbers couldn't possibly be a value of r?

a) 0.00

b) ‑1.00

c) 1.00

d) 1.03

6.11 If everyone paid taxes equal to 10 percent of their total annual income, the value of r for income and taxes would be nearest to

a) 0.00

b) -1.00

c) 1.00

d) none of the above

6.12 If it were impossible to predict taxes from annual income, the value of r for income and taxes would be nearest to

a) 0.00

b) -1.00

c) 1.00

d) none of the above.

6.13 You're told that, for a large group of students, an r of .23 describes the relationship between anxiety score and time to complete a problem‑solving task. This implies that there probably is

a) a slight tendency for more anxious students to be slower problem solvers.

b) a slight tendency for more anxious students to be faster problem solvers.

c) little or no relationship between anxiety and speed of problem solving.

d) a very strong relationship between anxiety and speed of problem solving.

6.14 For a strong (but imperfect) negative relationship, a z score of 2.34 will be paired with a z score

a) in the vicinity of -2.34.

b) in the vicinity of 2.34.

c) of 2.34.

d) of ‑2.34.

6.15 For little or no relationship, a z score of 2.34 will be paired with a z score in the vicinity of

a) 0.00.

b) 2.34.

c) ‑2.34.

d) some unpredictable value.

6.16 As the pattern among pairs of z scores becomes more apparent, the value of r tends toward

a) 0.00

b) 1.00.

c) ‑1.00.

d) either 1.00 or ‑1.00.

6.17 A positive r reflects the tendency for pairs of observations to occupy

a) similar locations in their respective distributions.

b) dissimilar and opposite locations in their respective distributions.

c) similar relative locations in their respective distributions.

d) dissimilar and opposite relative locations in their respective distributions.

6.18 The computation formula for r is preferred to the z score formula because the computation formula is more

a) understandable.

b) efficient.

c) general.

d) valid.

6.19 Although there are exceptions, a value of r in excess of .50, in either a positive or negative direction, would represent

a) an unimportant relationship in most areas of behavioral research.

b) a weak relationship in most areas of behavioral research.

c) a very strong relationship in most areas of behavioral research.

d) a virtually perfect relationship in most areas of behavioral research.

Ans; c

6.20 When the range of possible X and Y scores is restricted, the value of the correlation coefficient usually

a) increases.

b) decreases.

c) remains about the same.

d) changes unpredictably

6.21 The z score formula for r

a) enhances our understanding.

b) pinpoints the independence of r from the original units of measurement.

c) is not recommended for calculating r.

d) has all of the above properties.

6.22 Assume that r equals -.43 for the relationship between years of heavy smoking and life expectancy. This signifies that

a) heavy smokers tend to have longer life expectancies.

b) heavy smokers tend to have shorter life expectancies.

c) there is a cause‑effect relationship between heavy smoking and life expectancy.

d) there is a negative cause‑effect relationship between heavy smoking and life expectancy.

6.23 If there is a correlation between the age of schoolchildren and their reading comprehension, you could speculate about the basis for this relationship. Probably the most reasonable speculation is that

a) age causes reading comprehension.

b) age could cause reading comprehension, or both could be effects of some more basic cause.

c) some more basic combination of factors, such as intellectual maturation and educational background, causes the relationship.

d) none of the above

6.24 Although designed originally for use with quantitative data, the Pearson r has been extended to other kinds of situations, including those that involve

a) ranks.

b) ordered qualitative data.

c) ordered qualitative and quantitative data.

d) all of the above

6.25. Dots in scatterplots that deviate conspicuously from the main dot cluster are viewed as

a) errors.

b) more informative than other dots.

c) the same as any other dots.

d) potential outliers.

6.26. When outliers occur, the best strategy is to report

a) the values of r both with and without any outliers.

b) the value of r with any outliers.

c) the value of r without any outliers.

d) nothing whatsoever.

NOTE: 6.27 to 6.29 refer to the following correlation matrix based on data from 256 salaried employees of an electronic firm. The three variables are ANNUAL SALARY (in dollars), EDUCATIONAL LEVEL (in years) , and GENDER, where arbitrary numerical codes have been assigned to male (0) and female (1).

ANNUAL SALARY EDUCATIONAL LEVEL GENDER

ANNUAL SALARY r 1.000 .3657 -.2591

Sig. . .000 .000

N 256 256 256

EDUCATIONAL LEVEL r .3657 1.000 -.0539

Sig. .000 . .228

N 256 256 256

GENDER r -.2591 -.0539 1.000

Sig. .000 .228 .

N 256 256 256

6.27 (See note above.) After duplicate correlations have been discarded and trivial correlations have been ignored, there remain

a) two correlations.

b) three correlations.

c) six correlations.

d) nine correlations.

6.28 (See note above.) Only ____ of these correlations should be taken seriously.

a) one

b) two

c) three

d) an unknown number

6.29 (See note above.) It is reasonable to conclude that

a) annual salaries tend to increase with educational level, and salaries of males tend to be higher than those of females.

b) annual salaries tend to increase with educational level, and salaries of females tend to be higher than those of males.

c) annual salaries tend to decrease with educational level, and salaries of males tend to be lower than those of females.

d) annual salaries tend to decrease with educational level, and salaries of females tend to be lower than those of males.