CHAPTER 1-2-3

TRUE/FALSE EXERCISES (KEY)

For questions: [email protected]

Chapter One:
1. _F_ Descriptive statistics is about drawing conclusions.
2. _T_ Inferential statistics uses data collected from a small group to draw conclusions
about a larger group.
3. _T_ Characterizing the data is an element of descriptive statistics.
4. _T_ Estimation is an element of inferential statistics.
5. _T_ Hypothesis testing is not an element of descriptive statistics.
6. _T_ A variable can have many different values named as the data.
7. _F_ A data point can be treated as a value for more than one variable.
8. _F_ Operational definitions need not have universally accepted meanings; it is
sufficient for them to have meanings that are understandable by the study group.
9. _F_ For a sample, the parameters and statistics have the same values.

Chapter Two:
10. _F_ Categorical variables can only have two values, either “yes” or “no”.
11. _T_ Monetary amounts should be considered as continuous variables.
12. _F_ Number of cars in a parking lot can be treated as a continuous variable if it is
astronomical such as 1,000,000,000.
13. _F_ Discrete variables are a subgroup of categorical variables.
14. _F_ An ordinal scale is an ordered array.
15. _T_ Nominal scale can be used to classify more than three categories.
X   A, A, C , C , E , B, F 
16. _T_ The dataset can be classified by using a nominal scale.
17. _T_ Height of people is measured with a ratio scale.
18. _F_ Number of students in a class is measured with an interval scale.
19. _F_ Profit level cannot be measured with a ratio scale since it can be negative,
indicating a loss.
20. _F_ If an employee estimates parameters by using data collected by the company she
works in, then she is using data provided by a primary source.
21. _T_ If a researcher uses data provided by a secondary source he cannot be the data
collector.
22. _T_ To organize data on one categorical variable we can use a summary table or a
contingency table.
23. _F_ Ordered array can be utilized to organize a variable that is measured by using an
ordinal scale, since it can be sorted in an ascending or descending order.
24. _F_ The number of classes in a frequency distribution must be determined according
to strict formal rules.
25. _F_ In a frequency distribution, frequencies in each class is a value for a categorical
variable.
26. _T_ Pareto Chart is used for distinguish between the vital few and the trivial many.
27. _T_ A Pareto Chart can be drawn for the following dataset

X   1,25,31,47, Doctor , Doctor

28. _F_ A stem and leaf display can be used to organize the following data set
X   47, Doctor
.
X   1,1
29. _T_ A stem and leaf display can be used to organize the following data set .
30. _F_ A scatter plot diagram can be drawn for two variables if they are measured with
an ordinal or interval scale.
31. _F_ The following is an example of time series data:
32. Month 33. October 34. February 35. December
36. Year 37. 2010 38. 2014 39. 2009

Chapter Three:
40. _T_ The data can be checked for variation by plotting a scatter diagram. (Possible but
not preferred.)
41. _T_ Central tendency of and variation in a dataset has a bearing on the shape of its
distribution.
42. _T_ We need to calculate the arithmetic mean to find the extreme values in a bell-
shaped distribution.

43. _T_ Median minimizes the value of  i

 x  median  .
44. _F_ The position and the value of the median cannot be the same.
45. _F_ If the median is included in the dataset, the mean is included too.
46. _T_ The mode is always included in the dataset.
47. _F_ The position of the mean must be an integer.
48. _T_ The mode is a measure of central tendency for a variable that is measured by a
nominal or ordinal scale.
X   1,2 X   1,1,2,2
49. _F_ The number of modes in the datasets and is the same.
50. _F_ Adding extreme values never changes the mode of a dataset, since mode is not
affected by extreme values.
51. _T_ In a dataset formed by consecutive numbers, there is no mode.
52. _T_ In a dataset formed by consecutive numbers the median equals the mean.
53. _F_ If the median and mean are both included in the dataset then the mode is not
included.
X 2  X1
 1  R1
54. _F_ The following equation always holds if X 1

 X1  X 2   X n 
1/ n
 X1
  1  R1    1  R2      1  Rn  
1/ n
1
X1

55. _T_ Range is affected by extreme values whereas interquartile range is not.
56. _F_ Variance is always greater than the standard deviation. (Counter example:

s 2  0.01  s 2  s 2 .)
2
57. _F_ Standard deviation s can be negative but the variance s is always positive. (
2
always returns the positive root of s .)
x   0,1
58. _F_ Coefficient of variation is always less than the standard deviation. (If it
is greater.)
59. _T_ Adding an observation equal to the mean does not change the variance of a
dataset.
60. _T_ Range is not sensitive to the median.
X   0.1,0.2,0.3,0.4,0.5,0.6,0.7
61. _T_ Adding 0.1 as an observation to the dataset
increases the standard deviation more than adding 0.6 as an observation.
62. _T_ Adding 4 as an observation to a dataset with mean 3, makes it less likely to
conclude that the maximum value in the dataset is an outlier by calculating the Z-
Score of the maximum value.
63. _T_ If mean is smaller than the median, the shape of a bell-shaped distribution is
always left-skewed.
64. _T_ The shape of a distribution gets flatter as its kurtosis decreases towards zero.
65. _T_ The sharp peak of a distribution indicates a high kurtosis value.
66. _F_ Interquartile range is always smaller than the range. (They are equal for the

dataset
 1,2,3 .)
67. _F_ A boxplot can be used to plot the distances between the measures of central
tendency.(Mode and median is not plotted.)
68. _F_ Parameters describe samples.
69. _F_ Population mean is always greater than the sample mean.
70. _F_ Population variance is always less than the sample standard deviation.
71. _T_ Population and sample variance is measured in the same units as the data.
72. _F_ The empirical rule is a violation of the Chebyshev rule.
73. _T_ Sample covariance can be zero between two datasets.
74. _F_ If Y increases one unit as X increases by the same amount, then we can conclude
that the changes in Y is caused by the changes in X and the two datasets have a
positve linear relationship. (Covariance does not imply the direction of causality.)
cov  X, Y   cov  X, Z 
75. _F_ If then the linear relationship between X and Y is
stronger than the linear relationship between X and Z.
cov  X , Y    1,1
76. _F_ It is always true that .
cov  X, Y   0.5 cov  X, Z   0.6
77. _F_ If and then the linear relationship between X
and Y is weaker than the linear relationship between X and Z.

78. _F_ If rXY  0.5 and rXZ  0.51 then the linear relationship between X and Y is
stronger than the linear relationship between X and Z.

79. _F_ If rXY  rXZ  0 then it is always true that rYZ  0 . (Counter example: if Y dataset is

a replication of Y it is possible to have rXY  rXZ  0 and rYZ  1 )

X   2,1,5,3,4 Y   202, 101, 505, 303, 404
80. _F_ Given the datasets and it

must be that rXY  0 .