Deck 10: Descriptive Statistics

Question 1

The maximum possible correspondence or correlation between two variables is represented by a Pearson
Product-moment coefficient of:

A) -1.00
B) .00
C) .90
D) 200

Answer 1

-1.00

Question 2

Which of the following sets of scores has the largest standard deviation?

A) 312,312,312,312,312
B) 44,45,46,46
C) 530,531,532,533,533
D) 6,11,38,55,68

Answer 2

6,11,38,55,68

Question 3

Which one of these correlation coefficients has the least predictive value?

A) .87
B) 53
C)19
D) -28

Answer 3

19

Question 4

The kind of graph on which one would determine the frequency of a given score by noting the height of the line is called a(n):

A) histogram
B) abscissa
C) frequency polygon
D) frequency table

Question 5

Which of the following statements is correct?

A) The mean is a point in a distribution below and above which 50% of the cases lie.
B) The mode is the least-used measure of central tendency.
C) The median is equal to the sum of the scores divided by the number of scores.
D) The median is the same value as the 25^th percentile.

Question 6

If there are only a few very high scores and a large number of closely bunched low scores in a distribution:

A) the mean will be higher than the median
B) the median will be higher than the mean
C) the median and the mean will be the same
D) none of the above is correct

Question 7

A test was given to two sections of a course. The results were:
Section I:
Mean: 51; Standard Deviation: 7
Section II:
Mean: 51; Standard deviation: 13
Which of the following conclusions is correct?

A) Section I did better on the test than Section II.
B) Section I is more homogeneous than Section II.
C) Section I has more bright students than Section II.
D) The students in Section I performed less consistently than those in Section II.

Question 8

When scores are grouped in constructing a frequency polygon or scatterplot:

A) all intervals must be the same size
B) individual scores (within intervals) are plotted
C) there should be at least 30 intervals
D) each interval should contain 5-10 scores

Question 9

A z-score is obtained by:

A) dividing the score by the standard deviation and subtracting from the mean
B) adding the score to the standard deviation and dividing by the mean
C) dividing the score by the mean and subtracting from the standard deviation
D) subtracting the mean from the score and dividing by the standard deviation

Question 10

In a normal distribution, ± 1 z-score includes about:

A) 30% of the scores
B) 50% of the scores
C) 70% of the scores
D) 90% of the scores

Question 11

The median is equal to:

A) the mean
B) the mode
C) the 25^th percentile
D) the 50^th percentile

Question 12

What is commonly known as the "average is more correctly called the:

A) median
B) arithmetic mean
C) geometric mean
D) mode

Question 13

The primary value of frequency polygons is that they:

A) are easy to construct
B) contain all the information in the original scores
C) are easy to interpret
D) can be used with categorical data

Question 14

The standard deviation tells how:

A) much the scores in a distribution are spread out
B) one group compares in level of performance to another
C) highly one variable is related to another
D) an individual compares to a group

Question 15

An advantage of z-scores is that:

A) persons will score higher on a z-score than on other scores
B) they are easier to obtain than percentile ranks
C) they have higher reliability than other types of scores
D) scores on different instruments can be compared

Question 16

A correspondence exists between z-scores and percentile ranks if:

A) the calculations are done correctly
B) the mean equals the median
C) the scores are valid
D) the data approximate the normal distribution

Question 17

In constructing a scatterplot:

A) the range of scores must be the same on each axis
B) each individual is plotted once
C) the X axis must be the dependent variable
D) the number of cases must be at least 50

Question 18

Scatterplots are another way of showing the information given in:

A) means
B) standard deviations
C) correlation coefficients
D) crossbreak tables

Question 19

A scatterplot can be used only when:

A) both variables are quantitative
B) both variables are categorical
C) one variable is categorical; the other is quantitative
D) any of the above

Question 20

Whether a particular correlation coefficient is "good depends on:

A) the situation to which it is applied
B) whether it exceeds .80
C) whether the sample to which it applies was randomly selected
D) the average on each variable to which it applies

Question 21

A high correlation coefficient would be obtained from a scatterplot whose points:

A) can be described as encompassing a square
B) cluster around a horizontal line
C) cluster around a vertical line
D) cluster around a line drawn from upper left to lower right

Question 22

Calculation of the Pearson Product-Moment Correlation Coefficient:

A) requires only the ability to add, subtract, multiply, and divide
B) requires the ability to add, subtract, multiply, divide, and take a square root
C) requires the ability to solve algebraic equations
D) requires the ability to perform simple calculus operations

Question 23

Eta should be used when:

A) one variable is categorical
B) there are extreme scores on one (or both) variables
C) the relationship between variables is best described by a straight line
D) the relationship between variables is best described by a curve

Question 24

Crossbreak tables are used when:

A) both variables are categorical
B) both variables are quantitative
C) one variable is categorical, the other is quantitative
D) all of the above

Question 25

In a crossbreak table, expected frequency is:

A) the actual frequency in each cell
B) the value that is anticipated in each cell
C) the frequency in the margin of the dependent variable
D) none of the above

Question 26

A relationship is shown in a crossbreak table by:

A) the size of expected frequencies
B) the number of categories on each variable
C) a large discrepancy between actual and expected frequencies
D) an increase in actual frequencies from lower left to upper right

Question 27

The contingency coefficient:

A) is analogous to the correlation coefficient
B) is used only with crossbreak tables
C) can be less than 1.00
D) is all of the above

Question 28

Matching

-Quantitative data

A) Sample
B) Population
C) Interest in math
D) Teaching methods

Question 29

Matching

-Parameters

A) Sample
B) Population
C) Interest in math
D) Teaching methods

Question 30

Matching

-Statistics

A) Sample
B) Population
C) Interest in math
D) Teaching methods

Question 31

Matching

-Categorical data

A) Sample
B) Population
C) Interest in math
D) Teaching methods

Question 32

In a negatively skewed polygon, the tail of the distribution trails off to the left, in the direction of the lower scores.

Question 33

The standard deviation is calculated by 95% of all the scores in a distribution.

Question 34

A strong correlation between two variables implies causation.