EC 233 Fall 2017

Team member names and ID’s:

Last Name First Name ID

1. Çınar Şerif Kaya 2015300111

Assignment I for EC 233.01/02

(due by Thursday, October 12 2017 at 23:55)

 This assignment is to be completed by teams of one, two or three students.

 You will use the data we gathered in the class questionnaire to answer the questions. The Excel file
with the data will be available on Moodle.
 The answers must be typed in the spaces below between the questions, not handwritten. Insert any
chart/graphic object from Excel to Word using “Copy and Paste/Paste Special”. You can adjust the
amount of space between the questions to fit your answers. Do not attach Excel or other printouts or
hand-written material. You must only submit the Word document, and in Word format, to Moodle.
 Moodle has a 1MB size limit for students uploads (such as assignments). In order to reduce file size,
you can use the "Reduce File Size" in the File menu of Powerpoint/Word/Excel.
 E-mailed assignments will not be accepted.
 Please use Excel to find the answers. Please consult the graphical methods section in your book, the
“Hints” section at the end of the questions, and other extra material for help.
 Carry out the necessary calculations and report the final results (so write 4 instead of 2x2).
 Use at least 2 decimal places.

Questionnaire
1. Gender: Female___ Male___
2. Month of birth: ___
3. Age: ____
4. Height: ____ 5. GPA: _____
6. How many books have you read during summer? _____
7. How many TV series/movies have you seen during summer? _____
8. Approximately how much time (in hours per week e.g 1.5 hours for 90 minutes or 0.75 hours for 45 minutes) do
you spend studying?____
9. Where are you staying in Istanbul?
BU dormitory Ucaksavar Superdorm Rented house With own family Other
10. Do you like pets? Yes/No
11. Do you believe that you will be in a position that you wish to be in five years after graduation?
5: Definetly yes 4: probably 3: not sure 2: no 1: definitely no

QUESTIONS AND ANSWERS

1
 EC 233 Fall 2017

1) Choose 2 random variables in the dataset (from Q1 to Q10).

a) Report the type of data you selected in terms of categorial and numerical (discrete vs.
continuous).

Answer

I have chosen Height and Months of births as my random variables. Height is a discrete numerical
variable but month of births is a categorical variable.

b) Use an appropriate graphical representation method to provide information regarding class

distribution for both variables. Make sure that you have all graph titles and labels in place.
You are free to choose from different options as long as the graph is suitable fort the data type.

Answer

2
 EC 233 Fall 2017

Distribution of Month of Births

18 16
16
14 13
12 12
12 11 11
Number of Students

10 9
8 8
8 7
6 5 5 Total
4
2
0
ril st er ry ry
Ju
ly ne ch ay ber ber be
r
Ap ugu mb brua nua Ju
M
ar M m cto m
A ce Fe Ja ve e
De
O pt
No Se

Months

2) Filter in Excel (using filtering tool) either all males or all females in the data. Your random
variable, X, is height of all male (or female) students in Fall 2017 EC 233 class. Note: Assume
that this data represents the entire male/female population of Fall 2017 EC 233 students.

a. First, create a histogram showing the distribution of your (female/male) population. You
need to make your own judgement regarding the intervals/bins.

Answer

3
 EC 233 Fall 2017

b. Then, calculate the following summary statistics for your population in (a) (reporting
with two decimal places is enough):

 Number of observations (N)

 Maximum value in the population

 Minimum value in the population

 Range

 Mean

 Median

 Variance

 Standard deviation

Answer

4
 EC 233 Fall 2017

Count 50
Maximum 177
Minimum 150
Range 27
Mean 164.26
Median 164
Population Variance 30.6324

Standard Deviation 5.53465446

c. Finally, does your population look symmetric according to the mean and the median, and
according to the histogram?

Answer

Yes, it does look symmetric. Since the mean is 164.26 cm and the median is 164 cm, we can say that it
is a symmetric population.

3) Select three random samples of 10 from this population (N=total population size; n 1=10, and
n2=10).

5
 EC 233 Fall 2017

Answer

Table 1 You see the index of the each random student

First Random Sample Second Random Sample Third Random Sample

48 32 9

106 62 20

78 50 115

65 69 3

115 99 65

62 89 59

105 59 109

109 47 117

56 108 89

24 49 21

4) List the two sample values and then answer 4a and 4b.

Answer

6
 EC 233 Fall 2017

Index Of First Random Sample GPA Of First Random Sample

48 3.13

106 3.1

78 2.7

64 3.86

115 2.3

62 2.18

105 3.41

109 2.4

56 2.98

24 3.62

Index Of Second Random Sample GPA of Second Random Sample

32 3

62 2.18

50 3.34

7
 EC 233 Fall 2017

69 3.12

99 2.57

89 3.9

59 2.25

47 2.62

108 2.31

49 3.11

4a) What’s the mean GPA of the first sample? The mean GPA of the second sample? Are they the
same? Are these two sample statistics different than the population mean (the corresponding
parameter)? Does it make sense? Explain in two-three sentences.

Answer

Mean GPA of the first sample is 2.96.

Mean GPA of the second sample is 2.84.

Mean GPA of population is 2.81.

Yes, these two statistics are different from the population mean. There are couple of reasons for
that. Fist, we have an extreme value “0”. This value brings the population mean down. In the first
sample we have the valu of 3.86. This also brings the sample’s GPA up to 2.96. We count the
same value in the population GPA as well but since there are 5 times more values in the
population this high extreme value affects mean GPA of population less.

4b) What’s the sample standard deviation of the first sample? the sample standard deviation of the
second sample? Are they the same? Are these two sample statistics different than the population
standard deviation? Explain in two-three sentences.

8
 EC 233 Fall 2017

Standard deviation of the first sample is 0.5697.

Standard deviation of the second sample is 0.5514.

Standard deviation of the population is 0.6963.

No, the first and the second samples’ deviations are different from each other since the first
sample has more extreme values like 3.86, 3.62.

These two sample statistics are different than the population standard deviation because their
formulas are different. Denominator in the population deviation is N, on the other hand
denominator of the sample deviation is n-1.

HINTS:

 You may want to use “Data Analysis” under the “Data” tab in Excel. You can use the
“Histogram” and “Descriptive Statistics” options here. If “Data Analysis” does not appear
under the “Data” tab, use Excel “Add-ins” under “Options” to install it using “Analysis
ToolPak”. If you are using Mac, this option is not available. You can install StatPlus instead.
For descriptive statistics simple commands like AVERAGE() are sufficient, though. Also,
note that Excel has different variance (and standard deviation) formulae for samples (VAR.S
()) and for populations (VAR.P()). “Descriptive Statistics” may not yield the variance/standard
deviation you need.
 For random sampling:
o Use the =RANDBETWEEN(1,N) command to generate a random integer and use the
fill handle so you have 10 random integers. These numbers correspond to the numbers
(#) of the observations you should pick. You may have some numbers repeated since
any data value can be selected more than once (“sampling with replacement”).
o Note that the “randbetween” command output changes every time you hit “enter” for
whatever reason. In order to avoid this problem, “copy” the random numbers and then
“paste special” them by selecting “values”.
o Repeat this process for second sample you want to draw.