Mid semester test

2 hours Paper
Closed Book
40 MCQ with formulae sheet given

Topic covered: Chapter 1, 2 and 3

Scale of measurements: Nominal, Ordinal, Interval and Ratio scale

Difference between discrete and continuous variables

Descriptive and inferential statistics

Organization of data: Frequency distribution, relative frequency, Histogram, Ogive, Stem and leaf display,
box plot

Measures of central tendency: Mean, Median and Mode: calculation and interpretation

Measures of dispersion: Range, standard deviation and variance

Population variance and sample variance: Raw data and grouped data

Skewness: Identify skewness and justify with reasons

Coefficient of variation
Measurement Scale

Nominal scale: No Magnitude

Eg Male: 0 Female: 1

0 and 1 have no magnitude.

Cannot say that Female is better than male because 1 is more than 0

1 and 0 are for coding only

Ordinal scale: Has Magnitude but No equal sized Interval

Eg In a Miss Vietnam contest

Miss A - Champion 1
Miss B – First runner up 2
Miss c – Second runner up 3
A is more beautiful than B
B is more beautiful than C
A is more beautiful than C
A is twice more beautiful than C compared with B? This is wrong

Interval scale: Has magnitude and equal sized Interval but DO NOT have a true zero
Eg Temperature in Degree Celsius

0 deg C
10 Deg C
20 Deg C

At 0 deg C there is still heat and therefore it is not a true zero, it is an arbitrary zero

0 deg C has more heat than minus 10 deg C

Ratio scale: Has magnitude, Equal sized Interval and has True zero

Eg Distance in kilometer (km).

O km is a true zero because of absence of distance.

Time in minutes is ratio scale because 0 minute is a true zero

Nominal and Ordinal scale: Qualitative data. Use Non Parametric Test
Interval and Ratio: Quantitative data. Use a Parametric teat
Skewness

Skewness is the study of the effect of either high extreme values or extreme low values. Skewness can be
determined by the following:

If the data set have high extreme value, it is said to be positively skewed or is skewed to the right.
Eg. Data set: 1, 2, 9 is positively skewed because extreme high value, 9

i. Comparing the mean and median:

If the mean > median, then the distribution is positively skewed (affected by high extreme values).
If the median > mean, then the distribution is negatively skewed (affected by low extreme values).

ii In the stem and leaf display/ histogram, if the tail on the right is longer, then it is positively skewed
and if the tail on the left is longer, then it is negatively skewed.

iii By looking at the box plot.

Positively skewed if
- Right whisker is longer than the left whisker
- (Q3 – Q2) > (Q2 – Q1)

Negatively skewed if
- Left whisker is longer than the right whisker
- (Q2 – Q1) > (Q3 – Q2)

iv By looking at the “Skewness” value in Summary Statistics output.

If Skewness value is positive, then the distribution is positively skewed.
If Skewness value is negative, then the distribution is negatively skewed.
Chapter 1 – 3 MCQ

1. Under descriptive statistics, we study

A) the description of decision making tricks
B) the methods for organizing, displaying, and describing data
C) how to describe the probability distribution
D) samples to assist in decision making

2. Under inferential statistics, we study

A) the methods to make decisions about one or more populations based on sample results
B) how to make decisions about a mean, median, or mode
C) how a sample is taken from a population
D) tables composed of summary measures

3. In statistics, a population consists of:

A) all people living in a country
B) all people living in the area under study
C) all subjects or objects whose characteristics are being studied
D) a selection of a limited number of elements

4. In statistics, we define a sample as:

A) people living in one city only C) all items under investigation
B) the target population D) a portion of the population

5. In statistics, conducting a survey means:

A) collecting information from elements C) drawing pictures and graphs
B) making mathematical calculations D) none of these

6. In statistics, conducting a census means:

A) making decisions based on sample results
B) checking if a variable is qualitative or quantitative
C) collecting information from all members of the population
D) collecting a sample with replacement

7. In statistics, a representative sample is a sample that:

A) contains the characteristics of the population as closely as possible
B) represents the results of a sample exactly
C) contains all people living in an area
D) contains elements collected with replacement

8. A random sample is a sample drawn in such a way that:

A) each member of the population has a 0.10 chance of being included in the sample
B) all elements of a population are included
C) some members of the population have no chance of being included in the sample
D) each member of the population has some chance of being included in the sample
9. A simple random sample is a sample drawn in such a way that:
A) each member of the population has some chance of being included in the sample
B) every tenth element of an arranged population is included
C) each sample of the same size has an equal chance of being selected
D) each member of the population has a 0.10 chance for being included in the sample

10. A data set is a:

A) set of decisions made about the population
B) set of graphs and pictures
C) collection of observations on one or more variables
D) score collected from an element of the population

11. An observation is a:
A) graph observed for a data set
B) value of a variable for a single element
C) table prepared for a data set
D) sample observed from the population

12. A quantitative variable is the only type of variable that can:

A) assume numeric values for which arithmetic operations make sense
B) be graphed
C) be used to prepare tables
D) be used in inferential statistics

13. A discrete variable is a variable that can assume:

A) categorical values only C) an uncountable set of values
B) a countable set of values only D) non-numerical values

14. A continuous variable is a variable that can assume:

A) categorical values only C) an uncountable set of values
B) a countable set of values only D) non-numerical values

15. A qualitative variable is the only type of variable that:

A) can assume numerical values
B) cannot be graphed
C) can assume an uncountable set of values
D) cannot be measured numerically

16. Time-series data are collected:

A) on the same element for the same variable at different points in time
B) on a variable that involves time, e.g., minutes, hours, weeks, months, etc.
C) for a qualitative variable
D) on different elements for the same period of time
17. Cross-section data are collected:
A) on the same variable for the same variable at different points in time
B) on different elements at the same point in time
C) for a qualitative variable
D) on different elements for the same variable for different periods of time

18. Raw data are the data that:

A) are presented in the form of a frequency table
B) give information on each individual sample member separately
C) are arranged in increasing order
D) are arranged in a random order

19. We obtain the relative frequency of a category by:

A) dividing the frequency of that category by the sum of all frequencies
B) multiplying the frequency of that category by 100
C) dividing the frequency of that category by 100
D) dividing the sum of all frequencies by the frequency of that category

20. We obtain the percentage of a category by:

A) multiplying the frequency of that category by 100
B) multiplying the relative frequency of that category by 100
C) dividing the frequency of that category by 100
D) dividing the sum of all frequencies by the frequency of that category

21. A distribution curve that is right-skewed has:

A) both tails of the same length C) a shorter tail on the right side
B) a longer tail on the left side D) a longer tail on the right side

22. A symmetric distribution curve:

A) has a longer tail on the right side C) is identical on both sides of the mean
B) has a longer tail on the left side D) is triangular in shape

23. The procedure for obtaining the midpoint of a class is to:

A) add the lower limit to the upper limit of the previous class
B) subtract the lower limit from the upper limit
C) multiply the sum of the two class limits by 2
D) divide the sum of the two class limits by 2

24. In a frequency histogram, the frequency of a class is the:

A) height of the corresponding bar
B) width of the corresponding bar
C) height multiplied by the width of the corresponding bar
D) height divided by the width of the corresponding bar
25. The mean of a data set is the:
A) value of the middle term in a ranked data set
B) sum of all values divided by the number of values
C) difference between the maximum and minimum values
D) average of the deviations of values from the average

26. The median of a data set is the:

A) value of the middle term in a ranked data set
B) value that occurs with maximum frequency
C) sum of all values divided by the number of values
D) average of the deviations of values from the average

27. An outlier influences which of the following summary measures the most?
A) mean B) median C) mode D) median and mode

28. Which of the following is the only measure that can be calculated for qualitative data?
A) mean B) range C) mode D) median

29. If a data set is right-skewed with one peak in the histogram, then which of the following is true?
A) the values of the mean, median, and mode are the same
B) the mean is greater than the median, which is greater than the mode
C) the mean and median are equal, but the mode is different
D) the mode is greater than the median, which is greater than the mean

30. The mean income of all MBA degree holders working in Los Angeles is $65,000 per year and the
standard deviation of their incomes is $8,000 per year. According to Chebyshev's theorem, the
percentage of MBA degree holders, working in Los Angeles, with an annual income of $33,000
to $97,000 is at least:
A) 75
B) 93.75
C) 88.89
D) 84.39
Chapter 1

Consider the following six pairs of x and y values. Find the following values.

x y
8 10
11 16
15 20
5 7
20 28
21 21

1. The value of y is:

Ans: 102

2. The value of  xy is:

Ans: 1,592

3. The value of  xy 2 is:

Ans: 34,802

4. The value of x 2
y is:
Ans: 27,712

5. The value of x 2
is:
Ans: 1,276

6. The value of y 2
is:
Ans: 2,030

7. The value of  ( x − 2) 2
y is:
Ans: 21,752
Chapter 2 & 3

Question 1
The weekly food expenditures in US $ of a random sample of 40 students is shown below:
Weekly food expenditures (US $) of a random sample of 40 students
21 30 42 50 62 71 83 93
83 73 62 50 44 32 21 23
32 44 51 64 75 76 66 53
45 34 24 28 35 47 55 66
55 47 36 47 56 57 57 58

 x = 2048  x = 117836
2
Also given and
a. Calculate the sample mean, variance and standard deviation.
b. Construct the ordered stem and leaf display to sort the data.
c. Calculate the five-figure summary. Calculate the inner lower fence and the inner upper
fence and hence identify the presence of any outliers. Hence, construct the boxplot.
d. Fill in the values for the three columns in the frequency distribution below.
Weekly Sales(US$) Frequency Relative frequency Cumulative frequency
20 and less than 30
30 and less than 40
40 and less than 50
50 and less than 60
60 and less than 70
70 and less than 80
80 and less than 90
90 and less than 100
Total

e. From the frequency distribution in part (d), calculate the mean and standard deviation.
f. Giving 3 reasons, are the weekly food expenditures positively or negatively skewed?
Question 2
A statistician would like to study the distribution of monthly sales pattern of outlets for product X. He
selected a random sample of 30 outlets and recorded their monthly sales in $ million. The summary output
of the monthly sales of the 30 outlets is shown below. However, four data marked a, b, c and d are missing
in the summary output.

Summary output

Sales ($ Million)
Mean 29.77
Standard Error 2.75
Median 32
Mode 35
Standard Deviation 15.06
Sample Variance a
Kurtosis -0.91
Skewness d
Range b
Minimum 3
Maximum 52
Sum c
Count 30
First Quartile 19
Third Quartile 40

a. What are the values of the 3 missing data marked a, b and c?

b. Find the values of the three measures of central tendency and interpret their meanings.

c. From the summary statistics, is the value of d positive or negative? Justify your answer.

d. Compute the interval 𝑥̅ ± 1.5𝑠 , where 𝑥̅ and 𝑠 are the sample mean and standard deviation
respectively. According to Chebyshev’s theorem, how many percent of the monthly sales ($
million) are expected to be within this interval?
Question 3
The following table gives the frequency distribution of meal expenses ($) per month by 100 adults
selected from a city.

Expenses f Class Lower Upper Lower Upper Class size

midpoints Limit Limit Boundary boundary
301 to 400 20
401 to 500 15
501 to 600 18
601 to 700 34
701 to 800 13

a. Complete the table.

b. Find relative frequency, cumulative frequency, cumulative relative frequency, cumulative

percentage for table above.

c. Find mean and standard deviation for the table above.

Question 4
Given the stem and leaf display below for daily spending ($) of a sample group of 35 adults.

Stem Leaf
1 12
2 23478899 9
3 023346 7
4 123345
5 11345
6 0123
7 23
Legend: 1|1 means $11

a. Find the three measures of central tendency, first quartile and third quartile.

b. Giving 3 reasons, is the distribution positively or negatively skewed?

c. Construct a frequency distribution table of daily spending ($) using 10-19 as first class, 20-29 as
second class and so on.

d. Find the approximate value of the 60th percentile for the data.

e. Find the percentile rank for the adult who spends $29 per day.
Question 5
The work experiences (in years) of all the 14 employees of a company are

8 21 11 4 14 17 11 8 8 7 2 11 27 6

a. Find mean and variance.

b. Find the first, second and third quartile. (Answer: 7, 9.5, 14)

c. Find the approximate value of the 70th percentile for the data. (Ans: 11)

d. Find the approximate value of the 30th percentile for the data. (Ans: 7)

e. Find the percentile rank for the employee with 17 years of experience (Ans: 78.57)

f. Find the percentile rank for the employee with 8 years of experience (Ans: 28.57)