Unlock document.
This document is partially blurred.
Unlock all pages and 1 million more documents.
Get Access
Chapter_14 Interpreting_Data
True / False
1. Empirical research is first a logical rather than a mathematical operation.
a. True
b. False
2. When reporting marginals for univariate analysis, the presentation must be in raw numbers and cannot be reported in
percentages.
a. True
b. False
3. In univariate analysis, missing data can be reported in several different ways.
a. True
b. False
4. Summary statistics, or measures of central tendency, include the mode, mean and median.
a. True
b. False
5. The range is a measure of central tendency.
a. True
b. False
6. Because extremes in a distribution (a very large or very small number) can impact the mean, it is usually important to
examine measures of dispersion about the mean.
a. True
b. False
7. Univariate analysis and subgroup comparisons focus on describing variables while bivariate analysis focuses upon
people.
a. True
b. False
8. Bivariate analyses typically have an explanatory purpose.
a. True
b. False
9. While the linear regression model is important for descriptive purposes, its predictive value is limited.
a. True
b. False
10. Tests of statistical significance should only be used when the relationships observed in data collected come from the
whole population.
a. True
b. False
Chapter_14 Interpreting_Data
Multiple Choice
11. Which of the following is not accurate concerning empirical research?
a. empirical research is a logical rather than a mathematical operation
b. mathematics is a convenient and efficient language
c. statistics is the applied branch of mathematics
d. empirical research is free of validity problems
12. Which of the following would represent a distribution of those arrested on a holiday weekend?
a. the exact number of persons arrested for violation of specific statute numbers
b. a list of persons arrested with the corresponding statute number they allegedly violated
c. the number of persons arrested for violent crimes, the number of persons arrested for property crimes and the
number of persons arrested for public order crimes
d. all of the above
13. Measures of central tendency include all except:
a. standard deviation
b. median
c. mean
d. mode
14. Dr. Jones wanted to display the findings of the sentences given in his local courthouse on one summer day. If the
sentences, displayed in months, were 10, 18, 24, 36, 18, 70, 30, then which of the following measures of central
tendency is accurate?
a. the mean is 24
b. the median is 24
c. the mode is 24
d. mean, median, and mode are the same
15. Of the three measures of central tendency which one is affected by extreme values?
a. mode
b. median
c. mean
d. neither mode, median, or mean are affected by extreme values
16. To calculate the mean for grouped data, which of the following steps should not be completed?
a. multiply the number of subjects within each category by the value of that category
b. total the results of the multiplication
c. divide by the number of categories
d. divide by the number of subjects
17. Which of the following measures of central tendency are the easiest to calculate?
a. mean
b. mode
c. standard deviation
d. median
18. Which of the following do not represent measures of dispersion?
a. ranges
b. means
c. standard deviations
d. variation in groups
19. With respect to standard deviation, which of the following statements is correct?
a. it is based on the squared deviations from the mean
b. it is the square of the variance
c. it is always a negative number
d. all of the above
20. With respect to standard deviation, which of the following statements is not correct?
a. the total deviation is zero
b. the average deviation is zero
c. the value can range from negative 1 to positive 1
d. the sum of the deviations from the mean will always be zero
21. Which of the following is an accurate statement?
a. if the mean is much higher than the mode, it indicates that there are extreme cases
b. if the standard deviation is high, it indicates that there is little variability
c. if the mean is equal to the median and mode, the elements in the population are all the same number
d. the degree of variability can be determined by using the mean
22. In a distribution of sentence lengths in months like the following – 6, 12, 10, 18, 240, 360 – which statistic would a
researcher not want to report?
a. standard deviation
b. mean
c. range
d. raw numbers
23. Measures of dispersion are appropriate for which types of variables?
a. nominal
b. ratio
c. ordinal
d. discrete
24. Which of the following represent a continuous interval/ratio variable?
a. gender
b. race
c. age
d. religious affiliation
25. Which of the following represent discrete nominal or ordinal variables?
a. age
b. race
c. speed limit
d. ranks in a police department
26. Which of the following would be an inappropriate manner to report findings on the variable gender?
a. median
b. mode
c. raw numbers
d. percentages
27. The use of rates in the reporting of criminal justice data allow the researcher to:
a. standardize by the data
b. compare groups of differing size
c. make the data valid
d. make the data reliable
28. Calculating rates is really pretty simple, what is not so simple in determining rates is deciding the:
a. numerator and denominator
b. arithmetic
c. mean
d. average
29. When reading a table for bivariate analysis that displays percentages of some attributes, what is the rule of thumb for
reading the table?
a. if it adds up to 100% the statistics are accurate
b. if the table is percentaged down, read across and if the table is percentaged across, read down
c. if the table is percentaged down, read down and if the table is percentaged across, read across
d. none of the above
30. Which of the following is not accurate concerning the construction of explanatory bivariate tables?
a. the cases are divided into groups according to attributes of the independent variable
b. each of the subgroups is then described in terms of attributes of the dependent variable
c. the table is read by comparing the independent variable subgroups with one another in terms of a given
attribute of the dependent variable
d. if the table is percentaged down, read down and if the table is percentaged across, read across
31. Which of the following is not a guideline for the presentation of tabular data?
a. there is no need to display information about missing data, include only that information which pertains to the
independent and dependent variables
b. when using percentages in a table, the base on which the percentages are computed should be indicated
c. a heading or title for the table should be given that succinctly describes what is contained in the table
d. the attributes of each variable should be clearly indicated
32. Which of the following is not true concerning the use of multivariate tables?
a. they are constructed in the same manner as bivariate tables
b. they include only one independent variable
c. the dependent variable is explained in terms of more than one independent variable
d. they include more than one independent variable
33. The appropriate measure of association when using nominal variables is:
a. regression
b. lambda
c. correlation
d. standard deviation
34. With respect to lambda, which of the following is not true?
a. lambda represents the reduction in errors as a proportion of the errors that would have been made on the
basis of the overall distribution
b. lambda is appropriate for ratio level variables
c. lambda measures the statistical association between two nominal variables
d. lambda is based on the ability to guess values on one of the variables by having knowledge of values on the
other variables
35. Ordinal variables use which of the following as the appropriate measure of association?
a. gamma
b. lambda
c. regression
d. correlation
36. On which of the following variables is it appropriate to use a Pearson’s product-moment correlation as a means of
measuring association?
a. gender
b. number of arrests
c. race
d. all of the above
37. With the use of regression analysis the researcher is able to:
a. offer a graphic picture of the association between two variables
b. summarize the association between two variables
c. predict other sets of values
d. all of the above
38. The formula “Y is a function of X” means:
a. values of X can be explained through variations in Y
b. X and Y are independent of each other
c. values of Y can be explained in terms of variations in the values of X
d. Y and X are equal
39. Any straight line on a graph can be represented by
a. Y = a + bX
b. X = a + bX
c. Y = a + bY
d. straight lines are not possible in a graph
40. When using inferential statistics all of the following assumptions are accurate except:
a. the sample must be drawn from the population about which inferences are being made
b. the inferential statistics assume simple random sampling
c. as long as the sample is drawn from a population that resembles the one about which inferences are to be
made, the resulting statistic has value
d. inferential statistics are addressed to sampling error only, they do not consider non-sampling errors
41. In the logic of statistical significance the elements include:
a. assumptions regarding the independence of two variables in the population study
b. assumptions regarding the representativeness of samples selected through conventional probability sampling
procedures
c. the observed joint distribution of sample elements in terms of the two variables
d. all of the above
42. Which of the following is a test of statistical significance?
a. regression
b. chi square
c. gamma
d. lambda
43. If the standard deviation is zero, we can conclude that:
a. there is dispersion in the data
b. the mean is a good measure of the average
c. the data are heterogeneous
d. the mean will be zero
44. High dispersion of a variable could result in:
a. a small standard deviation
b. the values of the mean and the median being quite different
c. a range is small
d. a variance is small
45. The standard deviation is the:
a. square root of the variance
b. square root of the range
c. the sum of the squared variance
d. none of the above.
46. The number of counts on an indictment is an example of what type of variable?
a. nominal
b. discrete
c. continuous
d. ordinal
47. The mean can be a misleading measure of central tendency when:
a. the distribution is very close together
b. the distribution is very spread apart
c. the mean, median and mode equal zero
d. none of the above, the mean is never misleading
48. The type of weapon used in a crime is what type of variable?
a. interval
b. ratio
c. discrete
d. continuous
49. A friend of yours assigned a code of 1 to “male” and a code of 2 to “female” on the variable gender. Your friend
asked the computer to compute the average score on gender. The computer printout contained the following
information: mean = 1.38, standard deviation = .432, median = 1.4 and mode = 1.0. You advise your friend that the
best measure of central tendency to report is the:
a. mean
b. standard deviation
c. median
d. mode
50. Please refer to the below scenario:
A friend of yours assigned a code of 1 to “male” and a code of 2 to “female” on the variable gender. Your
friend asked the computer to compute the average score on gender. The computer printout contained the
following information: mean = 1.38, standard deviation = .432, median = 1.4 and mode = 1.0.
What is your friend’s problem with the computer information?
a. asking for measures of central tendency on continuous variables
b. asking for measures of central tendency and dispersion on nominal variables
c. asking for the mode and the standard deviation in the same report
d. asking for measures of dispersion on continuous variables
51. When calculating the mean the researcher should use data measured at which level?
a. nominal
b. ordinal
c. interval
d. discrete
52. Bivariate and multivariate analyses are aimed primarily at:
a. description
b. exploration
c. explanation
d. application
53. Professor White asked his students to put the number of hours each studied for the final exam on a piece of paper
and turn that paper in with the exam. The pieces of paper indicate that students studied 10, 3, 4, 25, 1, 4, 4, 12, 6, 8
and 10 hours. What is the modal number of hours studied?
a. 10
b. 25
c. 4
d. 1
54. In #43 above, what is the median number of hours studied?
a. 4
b. 6
c. 5
d. 10
55. In #43 above, what is the range of the number of hours studied?
a. 24
b. 4
c. 10
d. 25
56. In #43 above, what is the mean number of hours students studied?
a. 10
b. 7.9
c. 7
d. 6
57. Crime rates are:
a. descriptive
b. explanatory
c. inferential
d. exploratory
58. The total variation is calculated in much the same way as the:
a. mean
b. mode
c. chi square
d. standard deviation
59. Lambda values vary from:
a. -1 - 1
b. -1 - 0
c. 1 -2
d. 0 - 1
60. When we generalize from samples to a larger population, which type of statistics are used?
a. descriptive
b. inferential
c. influential
d. bivariate
61. Which of the following statistical techniques relies upon testing in the null hypothesis?
a. mean
b. chi square
c. range
d. median
62. The authors of your text caution when using reports of significance tests that the researcher should be aware of
which of the following?
a. that these do not represent tests of substantive significance
b. that significance tests always show the relationship between the variables of interest
c. that there is no relationship between the size of the sample and the results of the significance tests
d. all of the above
63. When you have a population that does not allow for probability sampling, one way of stating your findings that is
what?
a. say that your findings are statistically significant
b. say that your findings are significant but not random
c. say that your findings represent a statistically discernible difference
d. say that your findings are as significant as if you have been able to use randomization
64. When using multivariate analysis, what are you able to state with confidence?
a. that you have looked at one variable and can analyze it
b. that you have looked at two unrelated variables
c. that you looked at the simultaneous relationships among several variables but this does not lead to interpreting
their causal relationship
d. that you looked at the simultaneous relationships among several variables and that as a result you can more
fully understand the relationships between them
65. Which of the following statements is usually true with respect to reading and interpreting a bivariate percentage
table?
a. percentages are listed across the top and along the sides are the subgroup comparisons
b. the researcher has the right to arrange a bivariate percentage table in any manner he or she chooses
c. percentages can only be used going down the side of the table
d. subgroup comparisons can only be used going across the top of the bivariate percentage table
66. In a table, if we have two rows and two columns, how many degrees of freedom are there?
a. 4
b. 2
c. 1
d. 0
67. Which of the following is not one of the levels of significance typically used in social science research reports?
a. .05
b. .10
c. .01
d. .001
68. Which of the following is not one of the assumptions of making inferences about a larger population when using
univariate tests?
a. the sample must be drawn from the population about which the inference is being made
b. there is an assumption of a non-probability sampling technique
c. when using inferential statistics we assume simple random sampling even when that is not possible
d. inferences only apply to sampling error, not other types of error that may be present
69. When we find any discrepancy between the assumed independence of variables in a population and the observed
distribution of sample elements, we can explain that discrepancy how?
a. we attribute the discrepancy to the nonprobability sample alone
b. the discrepancy can be the result of poor data collection
c. we attribute the discrepancy to an unrepresentative sample causing us to reject the assumption of
independence
d. we attribute the discrepancy to poor sample selection and to poor operational definitions of the main variables
70. When we use regression analysis, we are finding the regression equation that represents the geometrical line that
comes closest to the distribution of points. This can be illustrated in which of the following?
a. the regression equation Y = a + bX allows us to infer values of X when we know the value of Y
b. the regression equation Y = a + bX allows us to infer values of Y when we know the value of X
c. the regression equation requires that we know the values of X, Y, a and b when we begin doing the analysis
d. the regression equation has little, if anything, to do with the understanding of the distribution of points in a data
set
Chapter_14 Interpreting_Data
Completion
71. Statistics that summarize data in manageable forms are known as statistics.
72. statistics help researchers form conclusions from their observations usually forming
conclusions about a population from the study of a sample drawn from it.
73. Murder rates and arrest rates are common examples in which the is a relatively
straightforward count.
74. Frequency distributions of grouped data, known as , will allow for a manageable format
but with some loss of detail.
75. When reporting findings, the choice of the , or the total number of cases, depends entirely
on the purposes of the analysis.
76. The most frequent attribute, the can be reported from either grouped or ungrouped data.
77. The middle attribute, or the , is the measure that divides the distribution so that half the
scores are higher and half are lower.
78. As a measure of dispersion, is described as the average amount of variation about the
mean.
79. The standard deviation is the square root of the .
80. A(n) indicates what percentage of cases that fall at or below some value.
81. If there is a great amount of variation in a distribution it is known as being .
82. Tables where the values of the dependent variable are based on values of the independent variable are known as
____________________ tables.
83. In order to guess values on one variable when two variables are related the model of is
employed which suggests the stronger the relationship, the greater the reduction of error.
84. When discussing regression analysis, the is the difference between the total variation and
the unexplained variation.
85. When we generalize from samples to larger populations we use statistics to test the
significance of an observed relationship.
86. Discuss the different tests of statistical significance, comparing and contrasting each. Be sure to highlight the
strengths and weaknesses of each of the types of tests of statistical significance as well.
87. Compare and contrast the primary measures of central tendency (Mode, Median, Mean). What do each of these
measures tell us about data?
88. Compare and contrast bivariate analysis and multivariate analysis. Be sure to highlight the strengths and
weaknesses of each.
89. Discuss in detail the various levels of measurement. Are their certain circumstances when some levels of
measurement are more appropriate than others? Be sure to defend your answer.
90. Compare and contrast the primary differences between inferential and descriptive statistics. Be sure to highlight
the strengths and weaknesses of each.
