Quantitative Methods for Business:

Problem Statements

Group - 9
Members Name:

Unnati Chandane:- 2021CT21501

Harshita Kasaundhan:- 2021CT21527
Shubham Gasone:- 2021CT21528
pg. 1 Abhishek Patil:- 2021CT21555
Members Details:

• Unnati Chandane: (Technical Lead-I)

(Experience – 7 years) Expertise in .Net Technologies,
Microservices and Azure cloud computing.

• Harshita Kasaundhan: (Senior Software Engineer)

(Experience – 5+ years) Expertise in QA Automation and
domain knowledge of Healthcare and Oil & gas.

• Shubham Singh Gasone: (Technical Lead-I)

(Experience – 5+ years) Expertise in .Net, SQL, BI, SSIS,
SSRS, Power BI, Tableau. Healthcare domain knowledge in
RCM, Claims Denials, HEDIS.

• Abhishek Patil: (Senior Software Engineer)

(Experience – 5+ years) Expertise in QA Functional / Non-
Functional testing and requirement analysis.

pg. 2
CONTENTS:

1. Abstract………………………………………………………………………………4
2. Problem Statements………………………………………………………………..5
3. Data Related Problems…………………………………………………………… 6
4. Proposed Questions………………………………………………………………..7
5. References…………………………………………………………………………35

pg. 3
Abstract:

Money Control- moneycontrol is India's No 1 Financial and Business portal. With in-
depth market coverage, analysis, expert opinions and a gamut of financial tools,
moneycontrol.com has been the premier destination for consumers and market
watchers. A part of Network18, moneycontrol.com is the most influential destination
for stock market news and advice, business news and news about the Indian and
global economy.

NIFTY 50- The NIFTY 50 is a benchmark Indian stock market index that represents
the weighted average of 50 of the largest Indian companies listed on the National
Stock Exchange. It is one of the two main stock indices used in India, the other being
the BSE SENSEX.

NSE- Powered by millions of dreams, hopes and aspirations, India today is brimming
with potential. At NSE, we are driven by this ambition that makes India charge ahead
and take a more prominent place on the global stage.

We aim to catalyse India's growth story by creating investment opportunities,

enabling access and empowering our stakeholders. We work harder, smarter and
faster to deliver impact across the investment ecosystem. In a world that changes
shape by the second, we constantly reinvent ourselves to redefine the future.

Our ambition gives us direction. It pivots, and propels us. It is the leap we take from
today, towards a brighter tomorrow.

NIFTY PSU Bank- NIFTY PSU Bank Index is computed using free float market
capitalization method, wherein the level of the index reflects the total free float
market value of all the stocks in the index relative to particular base market
capitalization value

The NIFTY PSU Bank Index is designed to reflect the performance of the
public sector banks.

Problem Statements:

pg. 4
 Problem 1-

1. Data Source
1. Go to https://www.moneycontrol.com/ (Links to an external
site.)
2. Go to Market and chose Indian Indices, Chose NIFTY 50
3. Choose your company, scroll down to the financials heading
( for example for Adani port, financials are given
at https://www.moneycontrol.com/india/stockpricequote/infrastr
ucture-general/adaniportsspecialeconomiczone/
MPS#financials (Links to an external site.)).
4. Download/copy five-year quarterly data (total 20 data points)
of:
1. Total Income from Operations
2. Employee cost
3. Depreciation
4. Other Income
5. Other Expenses
5. Test
1. Is there any difference between total income from
Operations and total cost (Employee cost+
depreciation+ other expenses) at a 90% confidence
interval?
1. Chose a suitable statistical tool for it.
2. Frame null and alternate hypothesis
3. Test using the data if you have to reject the null
hypothesis using the critical value approach.
2. Is “other income” greater than the “total income from
operations”. Test at 95% confidence interval.
3. Is there any relationship between the “income form
operation” and “Employee cost”?
1. What are the collinearity coefficient and
coefficient of determination?
0. Show your calculations.
2. Test if income from operations is independent of
Employee cost at a 90% confidence interval.
4. Find the trend of the total income from operation with
respect to time.
1. State all your assumptions if any for all the
questions.

pg. 5
Problem 2 –

1. Go to
www1.nseindia.com/products/content/equities/indices/historical_index_dat
a.htm
2. Choose your indices
3. Download one-year data of
1. Open
2. Close
3. High
4. Low
4. Test
1. If open and high values are the same
2. Close and low values are the same
3. Open and close values are the same
4. Low and high values are the same
0. At 90% confidence interval.
5. Write a descriptive report using the information gained by the
analysis in not more than 500 words

2. Provide your recommendations to an investor based

on your analysis in problems 1 and 2.

pg. 6
 Problem 1

Q1. Is there any difference between total income from Operations and total
cost (Employee cost+ depreciation+ other expenses) at a 90% confidence
interval?
1. Chose a suitable statistical tool for it.
2. Frame null and alternate hypothesis
3. Test using the data if you have to reject the null hypothesis using the
critical value approach.

Difference between (Total Income

Quaterly Data Total Income from operations Total cost from Operations - Total Cost )
Mar '22 5,739.72 2558.65 3,181.07
Dec '21 5494.94 2465.28 3,029.66
Sep '21 5463.06 2321.14 3,141.92
Jun '21 5297.53 2214.22 3,083.31
Mar '21 5080.59 2253.2 2,827.39
Dec '20 4955.16 2138.28 2,816.88
Sep '20 4765.31 2001.3 2,764.01
Jun '20 4454.99 1967.05 2,487.94
Mar '20 4551.23 2167.02 2,384.21
Dec '19 5912.7 2117.78 3,794.92
Sep '19 6103.05 2036.26 4,066.79
Jun '19 6277.72 1916.28 4,361.44
Mar '19 4266.06 1723.68 2,542.38
Dec '18 4985.66 1639.98 3,345.68
Sep '18 4636.98 1528.12 3,108.86
Jun '18 4506.84 1512.9 2,993.94
Mar '18 4076.36 1446.71 2,629.65
Dec '17 3820.5 1416.88 2,403.62
Sep '17 3727.11 1375.06 2,352.05
Jun '17 3640.01 1352.79 2,287.22

Step 1:
H0: u1=u2, so here Total Income from operations is equals to Total cost, u1-
u2=0
Ha: u1 != u2, so here Total Income from operations is not equals to Total cost

pg. 7
 n1 20
n2 20

x1bar 4,887.78
x2bar 1907.629

s1 785.2440557
s2 381.3309679

Level of significance a – 0.10

a/2 – 0.50

Step 2:

Now, n < 30 so we will apply t distribution

For that we need to find the degree of freedom (df)

df =

df = 18,61,14= 19

Step 3:

Now we have to find t(degree of freedom, a/2)= t(19,0.5)= 1.729

Df=19

Rejection Rejection
0.05 0.05

- 1.729 0 1.729

pg. 8
 Step 4:

Now find the t value=

t = (4,887.78 - 1907.629) – (0)/sqr(30,830.80+7,270.60)

t = 2,980.151/195.19

t= 15.26

Hence t is greater than Rejection value. Hence, we have to reject the Null Hypothesis
value.

pg. 9
a) Chose a suitable statistical tool for it.

Microsoft Excel

pg. 10
 MS Excel does offer a wide variety of tools for data visualization and simple
statistics. It’s simple to generate summary metrics and customizable graphics
and figures, making it a usable tool for many who want to see the basics of their
data. As many individuals and companies both own and know how to use Excel,
it also makes it an accessible option for those looking to get started with
statistics.

pg. 11
b) Frame null and alternate hypothesis:

Sr. Null hypothesis Alternate hypothesis

No.
1. The null hypothesis is a general An alternative hypothesis is a
statement that states that there statement that describes that
is no relationship between two there is a relationship between
phenomenon’s under two selected variables in a study
consideration or that there is no
association between two groups
2. The symbol for the null The symbol of the alternative
hypothesis is H0, and it is read hypothesis is either H1 or
as H-null, H-zero, or H-naught Ha while using less than, greater
than or not equal signs
3. The principle of the null The principle behind the
hypothesis is collecting the data alternative hypothesis is similar
and determining the chances of to that of the null hypothesis
the collected data in the study of
a random sample, proving that
the null hypothesis is true
4. It is followed by ‘equals to’ sign. It is followed by not equals to,
‘less than’ or ‘greater than’ sign

pg. 12
 c) Test using the data if you have to reject the null hypothesis using the
critical value approach.
Critical Value Approach to Two-Tailed Hypothesis Testing:
• The critical values will occur in both the lower and upper tails of the standard normal
curve.
• Use the standard normal probability distribution table to find za/2 (the t-value with an
area of a/2 in the upper tail of the distribution).
• The rejection rule is: Reject H0 if t < -ta/2 or t > ta/2

Critical Value Approaches:

Step 1. Determine the hypotheses:
H0: U = 59602.94
Ha: U != 59602.94
Step 2. Specify the level of significance
a = 0.10%
a/2= 0.5%
Step 3. Test Statistic for Hypothesis tests about a Population Mean: standard
deviation unknown

Calculations is:

pg. 13
 xbar 2,980.15
s 571.160617
n 20
U0 59602.94

t = 2980.15 - 59602.94/ (571.160617/Sqr 20)

= -56,622.79/ (571.160617/Sqr 20)
= -56,622.79/ 127.50
t = -444.1

Step 4: Determine the critical values and rejection rule:

t(α/2,  n  - 1)
a/2 0.5
n 20
n-1 19

t(0.5,  19) = -1.729 0r 1.729

So, the Conclusion is that t value should be less than -ta/2 or greater than ta/2 and
t
we are rejecting the Null value Hypothesis because t value is greater than (0.5,  19).

Hence, we are rejecting the it.

pg. 14
Q2. Is “other income” greater than the “total income from operations”. Test at
95% confidence interval?
Other Income Total income from
operations
Mar '22 1902 5739.72
Dec '21 1876.78 5494.94
Sep '21 1837.2 5463.06
Jun '21 1781.07 5297.53
Mar '21 1780.12 5080.59
Dec '20 1705.46 4955.16
Sep '20 1553.84 4765.31
Jun '20 1519.19 4454.99
Mar '20 1772 4551.23
Dec '19 1789.4 5912.70
Sep '19 1726.66 6103.05
Jun '19 1663.25 6277.72
Mar '19 1558.99 4266.06
Dec '18 1468.85 4985.66
Sep '18 1317.28 4636.98
Jun '18 1301.6 4506.84
Mar '18 1208.51 4076.36
Dec '17 1186.76 3820.50
Sep '17 1187.57 3727.11
Jun '17 1167.26 3640.01
TOTAL 31303.79 97755.52

x1 = 1565.15
x2 = 4887.77
The Other Income is not greater than the “Total income from the operations”.

pg. 15
What are Confidence Intervals in Statistics?

The confidence interval (CI) is a range of values that’s likely to include a population value
with a certain degree of confidence. It is often expressed as a % whereby a population mean
lies between an upper and lower interval.

What does a 95% confidence interval mean?

The 95% confidence interval is a range of values that you can be 95% confident contains the
true mean of the population. Due to natural sampling variability, the sample mean (center of
the CI) will vary from sample to sample.
The confidence is in the method, not in a particular CI. If we repeated the sampling method
many times, approximately 95% of the intervals constructed would capture the true
population mean.
Therefore, as the sample size increases, the range of interval values will narrow, meaning
that you know that mean with much more accuracy compared with a smaller sample.
We can visualize this using a normal distribution (see the below graph).

pg. 16
For example, the probability of the population mean value being between -1.96 and +1.96
standard deviations (z-scores) from the sample mean is 95%.
Accordingly, there is a 5% chance that the population mean lies outside of the upper and
lower confidence interval (as illustrated by the 2.5% of outliers on either side of the 1.96 z-
scores).

How do I calculate a confidence interval?

To calculate the confidence interval, start by computing the mean and standard error of the
sample.
Remember, you must calculate an upper and low score for the confidence interval using
the z-score for the chosen confidence level (see table below).

Confidence Level Z-Score

0.90 1.645

0.95 1.96

pg. 17
 Confidence Level Z-Score

0.99 2.58

Confidence Interval Formula

Where:

 X is the mean

 Z is the chosen Z-value (1.96 for 95%)
 s is the standard error
 n is the sample size

For the lower interval score divide the standard error by the square root on n, and then
multiply the sum of this calculation by the z-score (1.96 for 95%). Finally, subtract the value
of this calculation from the sample mean.

For the above problem 95% confidence interval will be calculated as follows:

 X (mean) = 86
 Z = 1.960 (from the table above for 95%)
 s (standard error) = 6.2
 n (sample size) = 46
 Therefore at 5% level of significance, the population mean is expected to lie within
the interval of: X + 1.96 standard error of mean.

Lower Value: 86 - 1.960 × 6.2 √46 = 86 - 1.79 = 84.21

Upper Value: 86 + 1.960 × 6.2 √46 = 86 + 1.79 = 87.79
So, the population mean is likely to be between 84.21 and 87.79

pg. 18
Finding R Squared / The Coefficient of Determination

2.Calculation :

Below is the calculation of correlation coefficient and coefficient of

determination using Employee Cost and Total Income from Operation

pg. 19
 1. Test if income from operations is independent of Employee cost at a
90% confidence interval.

Computing the Confidence Interval for a Difference Between Two Means

If either sample size is less than 30, then the t-table is used.

 If n1 < 30 or n2 < 30, use the t-table:\

Use the t-table with degrees of freedom = n1+n2-2

Confidence interval = (x1–x2) +/- t*√((sp2/n1) + (sp2/n2))

where:

 x1, x2: sample 1 mean, sample 2 mean

 t: the t-critical value based on the confidence level and (n 1+n2-2) degrees of
freedom
 sp2: pooled variance, calculated as ((n1-1)s12 + (n2-1)s22) / (n1+n2-2)
 t: the t-critical value
 n1, n2: sample 1 size, sample 2 size

For both large and small samples Sp is the pooled estimate of the common
standard deviation (assuming that the variances in the populations are similar)
computed as the weighted average of the standard deviations in the samples.

pg. 20
Please find the attached excel solution for reference

pg. 21
Q4. Find the trend of the total income from operation with respect to time.
The formula for trend analysis (change in amount) can be derived by subtracting the base
year amount from the current year amount. Mathematically, it is represented as,
Change in Amount = Current Year Amount – Base Year Amount
The formula for trend analysis (percentage change) can be derived by dividing the difference
between the current year amount and the base year amount by the base year amount.
Mathematically, it is represented as,
Percentage Change = [(Current Year Amount – Base Year Amount) / Base Year
Amount]

Month Change in Percentage Total income from

Year Amount change operations

Mar '22 2099.71 58% 5739.72

Dec '21 1854.93 51% 5494.94
Sep '21 1823.05 50% 5463.06
Jun '21 1657.52 46% 5297.53
Mar '21 1440.58 40% 5080.59
Dec '20 1315.15 36% 4955.16
Sep '20 1125.3 31% 4765.31
Jun '20 814.98 22% 4454.99
Mar '20 911.22 25% 4551.23
Dec '19 2272.69 62% 5912.7
Sep '19 2463.04 68% 6103.05
Jun '19 2637.71 72% 6277.72
Mar '19 626.05 17% 4266.06
Dec '18 1345.65 37% 4985.66
Sep '18 996.97 27% 4636.98
Jun '18 866.83 24% 4506.84
Mar '18 436.35 12% 4076.36
Dec '17 180.49 5% 3820.5
Sep '17 87.1 2% 3727.11
Jun '17 0 0% 3640.01

In the above table, it can be seen that:

 Although the company has grown in the last two years, it has witnessed significant
growth in June 2019
 The profitability has also moved in tandem with the revenue, which is always a good
sign as it indicates better operational control.
Below is the graphical representation of the trend in each line item.

pg. 22
 Change in Amount

Trend of Total income from Operations with time

3000 80%
2500 70%

Percentage change
60%
2000 50%
1500 40%
1000 30%
20%
500 10%
0 0%

Axis Title

Change in Amounts
(Trend of Total income from operation with time)
Percentage change

State all your assumptions if any for all the questions:

pg. 23
a) As per the Analysis, we have applied multiple test to get the less deviation from the mean
value, but somehow it got rejected.
b) Among these assumptions, the data must be randomly sampled from the population of
interest and the data variables must follow a normal distribution.
c) We calculated the values of mean, average, standard deviation, sample size etc
d) We used 2 sample z-test to evaluate the difference between the 2 groups and used the
formula for cumulative area for 90% confidence interval where level of significance is 5%

Problem 2

pg. 24
Q1. If open and High values are same

data.csv

H0: u1=u2 : open = high, so u1 - u2 = 0

Ha: u1 !=u2 : open is not equals to high, so u1 – u2 !=0

n1 226
n2 226

x1bar 2637.15 x2bar 2668.153

s1 201.748
s2 206.138

Level of significance a = 0.10, then a/2= 0.50

n>30, then Z test Normal distribution

0.90

0.05

0.05 Rejected Area

Rejected Area 0

-1.645(critical values) 1.645(critical values)

Z test: two-sample z-test to evaluate the difference between two groups

pg. 25
Z= (2637.15 - 2668.153) – (0)/sqr(201.748^2/226)+( 206.137^2/226)

Z= -30.9996/sqr(180.098+ 188.019)

Z = -30.9996/19.186

Z= -1.615

So, Here fails to reject Null Hypothesis. Z value does not lie in Rejected Area.

pg. 26
Q2. IF close and low values are the same?

H0: u1 close = u2 low (close is equal to low)

For u1 = u2 = 0

Ha: u1 close = u2 low (close is not equal to low)

For u1 – u2 !=0

For Confidence interval = 90%

And a = 0.05

As given,

N1 = 226, X1bar = 2632.348, S1 = 202.2403

N2 = 226, X2bar = 2601.838, S2 = 196.9758

N > 30, Z test normal distribution.

Cumulative Area = Az = 0.95

Zc =1.645

0.90

0.50

0.50 Rejected Area

Rejected Area 0

-1.645(critical values) 1.645(critical values)

We can use the two-sample z-test to evaluate the difference between two groups:

pg. 27
 or more formally:

Z= (2632.348- 2601.838) – (0)/sqr(202.2403^2/226)+(196.9758^2/226)

Z= 30.502/sqr(352.657)

Z= 1.6242

So Now, Z value not lie in critical area reason, Hence we are not rejecting Null value Hypothesis.

pg. 28
Q3. Open and close values are the same

 x1, x2: sample 1 mean, sample 2 mean

x1 = 2637.15
x2 = 2632.34

 n1, n2: sample 1 size, sample 2 size

n1 = 226
n2 = 226

Sample Variance for Open and Close

  = sample variance
  = sum of…
 Χ = each value
  = sample mean
 n = number of values in the sample

Number of Values in the Sample (n)= n1= 226 and n2= 226
n1-1= 225, n2-1 = 225
X1 = 2637.15, X2 = 2632.34

Sum of Open (X1-Xbar1)2 = 9158012.04

Sum of Close (X2 – Xbar2)2 = 9202760

Sample Var1 (open), By using above formula in Excel we got Var1 = (X1-Xbar1)2/(n1-
1) = 40702.27

pg. 29
Sample Var2 (Close), By using above formula in Excel we got Var2 =(X2 – Xbar2)2/(n2-
1) = 40901.15

Standard Deviation

By using above formula we have calculated Standard Deviation for Open and Close
Sd1 for Open σ 1 = 20351.13
Sd2 for Close σ 2 = 20450.57

Now we will be going to calculate z-test for Comparing Two Means

Hypothesis test

Formula: 

where   and   are the means of the two samples, Δ is the hypothesized difference
between the population means (0 if testing for equal means), σ 1 and σ 2 are the
standard deviations of the two populations, and n 1and n 2are the sizes of the two
samples which we have already calculated above.

Null hypothesis: H 0: μ 1 = μ 2

or H 0: μ 1 – μ 2= 0

alternative hypothesis: H  a : μ 1 ≠ μ 2

or: H  a : μ 1 – μ 2≠ 0 

pg. 30
We can use the two-sample z-test to evaluate the difference between two groups:

or more formally:

The results of the study found the following:

For the Open group, the mean score was X1 = 2637.15, S.D σ 1 = 20351.13, n = 226
For the Close group, the mean score was X2 = 2632.34, S.D σ 2=20450.57, n= 226

By using above formula we got Z = 2.61

The Z Cumulative probability to a z‐score of 2.61 is 0.9955.

Please find the attached excel solution file for reference purpose

pg. 31
Q4. Low and high values are the same

IF Low and high values are the same:

H0: u1 low = u2 high (Low is equal to high)

For u1 = u2 = 0

Ha: u1 low = u2 high (Low is not equal to high)

For u1 – u2 !=0

For Confidence interval = 90%

And a = 0.05

As given,

N1 = 226, X1bar = 2601.83, S1 = 196.97

N2 = 226, X2bar =2668.15, S2 = 206.13

N > 30, Z test normal distribution.

pg. 32
Cumulative Area = Az = 0.95

Zc =1.645

0.90

0.05

0.05 Rejected Area

Rejected Area 0

-1.645(critical values) 1.645(critical values)

We can use the two-sample z-test to evaluate the difference between two groups:

or more formally:

Z= (2601.83- 2668.15) – (0)/sqr(196.97^2/226)+( 206.13^2/226)

Z= -66.32/sqr(177.66+ 188.00)

Z = -66.32/19.104

Z= -3.472

So here Z value is greater than critical value, hence we are rejecting Null value hypothesis

pg. 33
Q5. Write a descriptive report using the information gained by the analysis in
not more than 500 words
Provide your recommendations to an investor based on your analysis in
problems 1 and 2.

 According to the problem, we have analysed two scenarios based on

company’s data as well as Indices data.

 We have applied multiple analysis assumptions to get the less deviation in the
result.

 You can never be too familiar with your data, and time spent examining it is
nearly always time well spent. Descriptive statistics and graphic displays can
also be the final product of a statistical analysis.

For Providing Recommendations to an investor:

 The same data set may be considered as either a population or a sample,

depending on the reason for its collection and analysis. For instance, the final
exam grades of the students in a class are a population if the purpose of the
analysis is to describe the distribution of scores in that class, but they are a
sample if the purpose of the analysis is to make some inference from those
scores to the scores of other students (perhaps students in different classes
or different schools).

 Analyzing a population means your data set is the complete population of

interest, so you are performing your calculations on all members of the group
of interest to you and can make direct statements about the characteristics of
that group. In contrast, analyzing a sample means you are working with a
subset drawn from a larger population, and any statements made about the
larger group from which your sample was drawn are probabilistic rather than
absolute.

 There is no absolute agreement among statisticians about how to

define outliers, but nearly everyone agrees that it is important that they be
identified and that appropriate analytical techniques be used for data sets that
contain outliers. An outlier is a data point or observation whose value is quite
different from the others in the data set being analyzed. This is sometimes
described as a data point that seems to come from a different population or is
outside the typical pattern of the other data points.
pg. 34
References:

1.https://www.open.edu/openlearncreate/pluginfile.php/183122/mod_resource/
content/1/Report%20writingGRSQ61.pdf

2. https://www.moneycontrol.com/

3. www1.nseindia.com/products/content/equities/indices/historical_index_data.html

4. http://www.stat.ucla.edu/~cochran/stat10/winter/lectures/lect21.html

5. https://www.cliffsnotes.com/study-guides/statistics/univariate-inferential-tests/two-
sample-z-test-for-comparing-two-means

pg. 35