Sei sulla pagina 1di 28

Part – 1 Descriptive Analytics:-

Students are to visit any business concern (Small or medium scale organisation) and are to do
the following.

A). Identify the products/ services sold and categorise them based on units sold and
revenue earned:-

The products are selected based on my field work on BHAVANI SERVICE POINT, which renders
bike services. The service centre has acquired large number of customers who got services
regularly from this service point.
The information gathered are on the products, which service centre replace the damaged
products at the time of repair.
Here I have noticed some of the small spare parts of bikes are sold at high prices and all the
item they charge high prices are like indicators, clutch cable etc.
Variables Contents Selling Units sold Labour Rent
Price
Variable 1 chain link 193 12 18000 13000
Variable 2 gasket 10 30
Variable 3 assembly element filter 77 22
Variable 4 indicator 455 24
Variable 5 spark plug 45 30
Variable 6 headlight 165 35
153

These are the main products by which the service point makes more profit and they are focusing more
the small spare parts rather than going with other standard products

The products available at service point are not the branded products, as it is in the rural area most of
the visitors are rural customers. Where they may not be well known about the prices that are fixed
for the products.

Where the profits are highly generated with the low service cost.
B. Categorise them based on profit margins (gross profit margins). Assumptions and relative
comparison methods to be used to arrive at these numbers:-

chain link gasket assembly indicators spark plug headlight


element
filter

Per Unit 83 38 70 155 45 75


Per Day 996 1140 1540 3720 1350 2625
Per Month 29880 34200 46200 11600 40500 78750

profit Per Unit

75 83

45 38

70
155

chain link gasket essembly element filter indicators spark plug headlight
PROFIT PER UNIT
155
160
140
120
100 83
70 75
80
60 45
38
40
20
0
chain link gasket essembly indicators spark plug headlight
element filter

profit Per Day

996
2625 1140

1540
1350

3720

chain link 83 gasket 38 essembly element filter 70 indicators 155 spark plug 45 headlight 75

PROFIT PER DAY


4000 3720
3500
3000 2625
2500
2000
1540
1350
1500 1140
996
1000
500
0
chain link gasket essembly indicators spark plug headlight
element filter
profit Per Month

29880

78750
34200

46200
40500

11600

chain link 83 996 gasket 38 1140 essembly element filter 70 1540


indicators 155 3720 spark plug 45 1350 headlight 75 2625

PROFIT PER MONTH


78750
80000
70000
60000
50000 46200
40500
40000 34200
29880
30000
20000 11600
10000
0
chain link gasket essembly indicators spark plug headlight
element filter

C). identify the customer segments purchasing the goods/ services:-

The service point was established in 1998 by the partner of two members and business got
developed day by day. They acquired many customers within a shorter period of time by its
quality of service. Here the customer segmentation is based upon the different bikes that the
customers have, and what are the different parts have been replaced to different bikes of
different model.

And which bikes are more accurately getting spare parts to replace at the time of repair, these
shows profit earnings ratios between different bike models.
chain link gasket indicator spark plug headlight

round link chain rubber gaskets LED indicators E3 spark plug reflector

flat link chain cork gaskets D type turn signal NGK spark plug projector headlamp

twisted curb custom made blinkers AC delco spark HID lights


chain gaskets plug
square link chain non asbestos turn signals copper resistor filament bulb
gaskets spark plug

Customer Segmentation
12 11
10 10 10 10
10 9
8 8 8
8 6
6 5 5 5 5
4 4 4 4
4 3 3 3 3
2 2 2 2 2 2 2
2 1

0
1 2 3 4 5 6

splendor pashion pro pulsar honda activa dio

chain link chain link


4
4
3.5 3
3 4
3
2.5 2 2
2
1.5 1
2
1 2
0.5 1
0

splendor pashion pro pulsar


honda activa dio
gasket gasket
11
12 10
4
10
2 10
8
6 3
4
3
4 2
2 11
0

splendor 4 pashion pro 2


pulsar 1 honda activa 2 dio 3

essembler element filter essembler element filter


5 5 5
5
4.5 4
5 5
4
3.5 3
3
2.5
4
2 5
1.5 3
1
0.5
0
splendor 4 10
pashion pro 2 11 pulsar 1 3
honda activa 2 2 dio 3 4

indicator indicator
8 8
8
2
7
8
6
5 4 8
4
3 2 2 4
2
2
1
0
splendor 4 10 5
pashion pro 2 11 5 pulsar 1 3 3
honda activa 2 2 4 dio 3 4 5
spark plug spark plug
10 10
10
3
8 2 10
6 5 5

4 3
2 10
2
0
splendor 4 10 5 8
pashion pro 2 11 5 4 pulsar 1 3 3 2
honda activa 2 2 4 8 dio 3 4 5 2

headlight headlight
10
10 9
6
9 8 10
8
7 6 9
6 2 8
5
4
3 2
2 splendor 4 10 5 8 10
1 pashion pro 2 11 5 4 10
0
pulsar 1 3 3 2 5
honda activa 2 2 4 8 2
dio 3 4 5 2 3

D). identify a problem area as provided by the business owner / self-identification:-

 Warranty management
 Delivery time management
 Parking facilities
 Lack of power supply
 Maintaining cleanliness
 Job rotation
 Water management
E). develop an appropriate hypothesis/ hypotheses to identify the real problem:-

 Warranty management: they deal with most of the unbranded products so it’s difficult
to manage warranty services in the service point.
 Delivery time management: most of the time they makes delay in delivering the bikes
which are given for service. So they can inform the customer after completing bike
service, by a message or by making a call.
 Parking facilities: one of the major problem is providing parking for the bikes,
requirement of place in large area.
 Equipment maintenance: here to maintain the equipment’s in the service point is an
important thing and also includes more expenses for its maintenance.
 F). Develop suitable methodology to solve the problem

F). Develop suitable methodology to solve the problem

 They can setup rain water harvesting within their premises which helps them in overcoming
the water problem.
 Making an agreement with the employees not to quit a job all of a sudden, before they quit
some of the procedures should be followed and which may influence the employees to
continue their work.
 To maintain cleanliness they can share the responsibility to every employees how takes the
bikes for services
 For continues power supply here they should install power generator, it could be useful for
continuous work.
Part B
2.1 Identify the variables and develop a questionnaire using appropriate scales
Variables Considered:
 Time
 Money
 Preference
 Interest
Questionnaire Formed Using Scale of
 Like spending time in shopping
o Strongly Agree
o Agree
o Neutral
o Disagree
o Strongly Disagree
 Likes traditional or conventional shopping
o Strongly Agree
o Agree
o Neutral
o Disagree
o Strongly Disagree
 Selection of product is very bored
o Strongly Agree
o Agree
o Neutral
o Disagree
o Strongly Disagree
 Like to spend more money
o Strongly Agree
o Agree
o Neutral
o Disagree
o Strongly Disagree

Sunil 0 3 5 5 3
Veda shree 1 3 4 2 2
Jean Walker 0 5 5 4 3
Adithya krishna 0 5 5 4 5
Namratha 1 5 5 2 1
Vinutha 1 2 4 4 2
Manoj 0 4 4 4 3
Preethi 1 3 4 2 3
Abhi 1 4 4 3 3
Danush 0 5 4 3 4
Kajol 1 2 5 4 2
Samanta 1 4 4 5 3
Kiran 0 5 5 4 3
Pawan 0 5 5 3 3
Ramaj 0 5 4 3 4
Trivikrama R 0 3 5 2 2
Ashmitha 1 2 4 5 5
Vignesh.D 0 3 4 3 3
Bhavish S 0 5 5 5 5
Umesh 0 4 5 4 2
Maheshreddy 0 5 4 4 4
Navya 1 2 4 4 2
Sushma 1 5 5 5 5
Supriya 1 5 4 5 4
Harsha 0 5 5 5 5
Swathi 1 5 5 5 4
Kalpa 1 5 5 5 4
Bijith 0 5 5 5 5
Radha 1 5 5 5 5
Vidhya 1 5 4 4 4
tejashwini 1 3 5 5 3
Dilip kumar 0 5 5 5 5
Rahul 0 5 5 5 5
Dilip 0 5 5 5 5
Praveen 0 4 4 5 5
Milan p s 0 4 5 4 5
Saketh 0 4 5 3 4
Anupama 1 4 4 4 4
Naren 0 5 4 3 2
Nishmitha 1 3 4 2 3
Harshita 1 3 4 2 3

2.2 Develop a two group discriminant model

All the figures below are obtained by running a discriminant analysis on the survey made on
supermarket shopping by Male and Female

Group Statistics
Valid N (listwise)
Gender Mean Std. Deviation Unweighted Weighted
0 Timestamp 13790122636.66 00:00:00.000 4 4.000

I prefer traditional or 3.75 00:00:01.258 4 4.000


conventional shopping
selection of products is boring 3.50 00:00:01.732 4 4.000

Time spent on Shopping 2.00 00:00:01.414 4 4.000


Shopping satisfaction 3.00 00:00:00.816 4 4.000
V11 2.25 00:00:01.893 4 4.000
1 Timestamp 13790122608.97 00:00:00.000 3 3.000

I prefer traditional or 4.67 00:00:00.577 3 3.000


conventional shopping
selection of products is boring 3.00 00:00:01.000 3 3.000

Time spent on Shopping 2.67 00:00:01.155 3 3.000


Shopping satisfaction 2.00 00:00:01.732 3 3.000
V11 2.33 00:00:02.082 3 3.000
Total Timestamp 13790122624.79 00:00:00.000 7 7.000

I prefer traditional or 4.14 00:00:01.069 7 7.000


conventional shopping
selection of products is boring 3.29 00:00:01.380 7 7.000

Time spent on Shopping 2.29 00:00:01.254 7 7.000


Shopping satisfaction 2.57 00:00:01.272 7 7.000
V11 2.29 00:00:01.799 7 7.000
Table 2.2 (A) group statistics
Tests of Equality of Group Means
Wilks' Lambda F df1 df2 Sig.
Timestamp .a
I prefer traditional or conventional .790 1.330 1 5 .301
shopping

selection of products is boring .962 .195 1 5 .677

Time spent on Shopping .919 .440 1 5 .537

Shopping satisfaction .824 1.071 1 5 .348

V11 .999 .003 1 5 .958

Table2.2 (b): Tests of Equality of Group Means

Pooled Within-Groups Matrices


I prefer
traditional or selection of
conventional products is Time spent on Shopping
shopping boring Shopping satisfaction
Correlation I prefer traditional or 1.000 .017 -.006 .207
conventional shopping
selection of products is .017 1.000 .266 .050
boring
Time spent on Shopping -.006 .266 1.000 .392
Shopping satisfaction .207 .050 .392 1.000

Table2.2 (c): Pooled Within-Groups Matrices

Box's Test of Equality of Covariance Matrices

Log Determinants
Gender Rank Log Determinant
0 4 1.495

1 4 1.259

Pooled within-groups 4 1.576

The ranks and natural logarithms of determinants


printed are those of the group covariance
matrices.

Test Results
Box's M 9.666

F Approx. .886

df1 10

df2 10425.579

Sig. .546

Tests null hypothesis of equal


population covariance matrices.

Table2.2 (d): Box’s Test of Equality of Covariance matrices

Summary of Canonical Discriminant Functions

Eigenvalues

Function Eigenvalue % of Variance Cumulative % Canonical Correlation


1 .268a 100.0 100.0 .460

a. First 1 canonical discriminant functions were used in the analysis.

Wilks' Lambda

Test of Function(s) Wilks' Lambda Chi-square df Sig.


1 .789 12.581 4 .014
Table2.2 (e): Summary of canonical discriminant functions

Standardized Canonical Discriminant Function


Coefficients

Function

1
I prefer traditional or conventional shopping .164

selection of products is boring .079

Time spent on Shopping .886

Shopping satisfaction -.929

Structure Matrix
Function
1
Shopping satisfaction -.543
Time spent on Shopping .541
selection of products is boring .271

I prefer traditional or conventional shopping -.032

Pooled within-groups correlations between discriminating


variables and standardized canonical discriminant
functions
Variables ordered by absolute size of correlation within
function.

Table2.2 (f): Standard canonical discriminant function coefficient and structure matrix

Functions at Group Centroids

Function
Gender 1
0 -.418

1 .618
Unstandardized canonical discriminant functions
evaluated at group means

Table2.2 (g): Separate-groups


graphs of Gender

Classification Statistics

Classification Processing Summary


Processed 57

Excluded Missing or out-of-range group codes 0

At least one missing discriminating 0


variable

Used in Output 57

Prior Probabilities for Groups


Cases Used in Analysis

Gender Prior Unweighted Weighted


0 .500 34 34.000

1 .500 23 23.000

Total 1.000 57 57.000

Classification Resultsa
Predicted Group Membership

Gender 0 1 Total Table2.2


Original Count 0 26 8 34 (f):
1 13 10 23

% 0 76.5 23.5 100.0

1 56.5 43.5 100.0

a. 63.2% of original grouped cases correctly classified.


Classification statistics
2.3 As Business Analysts, state your assumptions and suggestions based on the model
developed

Tests of Equality of Group Means


Wilks' Lambda F df1 df2 Sig.
Timestamp .a
I prefer traditional or .790 1.330 1 5 .301
conventional shopping

selection of products is boring .962 .195 1 5 .677

Time spent on Shopping .919 .440 1 5 .537

Shopping satisfaction .824 1.071 1 5 .348

V11 .999 .003 1 5 .958

Table2.3 (a): Tests of Equality of Group Means

Test of equality of groups means measure each independent variables potential before
the model is created. Each test displays the results of a one-way ANOVA for the
independent variable using the grouping variables as the factor.

Wilks’ Lamba is measure of a variables potential. Smaller values indicate the variable is
better at discriminating between groups.

Summary of Canonical Discriminant Functions

Eigenvalues
Canonical
Function Eigenvalue % of Variance Cumulative % Correlation
1 4.460a 100.0 100.0 .904
a. First 1 canonical discriminant functions were used in the analysis.
Wilks' Lambda
Test of Function(s) Wilks' Lambda Chi-square df Sig.
1 .183 4.244 5 .515

Analysis on summary of canonical Discriminant Function:

 The canonical correlation is the measure of association between the discriminant


function and the dependent variable
 The square of canonical correlation coefficient is the percentage of variance explained
in the dependent variable.
 Smaller values of Wilks' lambda indicate greater discriminatory ability of the function.
The associated chi-square statistic tests the hypothesis that the means of the
functions listed are equal across groups. The small significance value indicates that the
discriminant function does better than chance at separating the groups.

Box's Test of Equality of Covariance Matrices

Log Determinants
Gender Rank Log Determinant
0 4 1.495
1 4 1.259
Pooled within-groups 4 1.576
The ranks and natural logarithms of determinants printed are those of the group covariance matrices.

Test Results
Box's M 9.666
F Approx. .886
df1 10
df2 10425.579
Sig. .546
Tests null hypothesis of equal population covariance matrices.
Table2.2 (d): Box’s Test of Equality of Covariance matrices

The "Rank" column indicates the number of independent variables in this case. Since
discriminant analysis assumes homogeneity of covariance matrices between groups, we
would like to see the determinants be relatively equal.

Box's M test tests the assumption of homogeneity of covariance matrices. This test is very
sensitive to meeting the assumption of multivariate normality.

Discriminant function analysis is robust even when the homogeneity of variances


assumption is not met, provided the data do not contain important outliers.

From the data it can be concluded the groups do differ in their covariance matrices,
violating an assumption of DA.
Part C

3.1 Obtain adjusted closing price for last 60 months and present descriptive statistics for
both.

I have selected FITBIT Corporation (FIT) and ROGERS Corporation (ROG) for Prescriptive
Analytics

60 months adjusted closing price for both the companies is showed below table:

Date Adj Close ROG Adj Close FIT


01-06-2015 66.139999 38.23
01-07-2015 55.970001 47.599998
01-08-2015 55.66 34.490002
01-09-2015 53.18 37.689999
01-10-2015 46.52 40.540001
01-11-2015 55.43 28.719999
01-12-2015 51.57 29.59
01-01-2016 47.470001 16.6
01-02-2016 53.419998 12.23
01-03-2016 59.869999 15.15
01-04-2016 57.360001 18.25
01-05-2016 66.470001 14.18
01-06-2016 61.099998 12.22
01-07-2016 68.440002 13.66
01-08-2016 55.91 15.48
01-09-2016 61.080002 14.84
01-10-2016 54.43 13.26
01-11-2016 74.32 8.36
01-12-2016 76.809998 7.32
01-01-2017 79.949997 6.01
01-02-2017 82.510002 6.21
01-03-2017 85.870003 5.92
01-04-2017 102.940002 5.72
01-05-2017 106.209999 5.23
01-06-2017 108.620003 5.31
01-07-2017 117.970001 5.16
01-08-2017 118.550003 6.03
01-09-2017 133.279999 6.96
01-10-2017 152.080002 6.14
01-11-2017 161.100006 6.86
01-12-2017 161.919998 5.71
01-01-2018 164.779999 5.15
01-02-2018 137.320007 4.78
01-03-2018 119.540001 5.1
01-04-2018 106.699997 5.55
01-05-2018 113.959999 5.43
01-06-2018 111.459999 6.53
01-07-2018 116.57 5.93
01-08-2018 138.070007 6.02
01-09-2018 147.320007 5.35
01-10-2018 123.059998 4.73
01-11-2018 128.660004 5.51
01-12-2018 99.059998 4.97
01-01-2019 126.910004 6.17
01-02-2019 155.25 5.92
01-03-2019 158.880005 5.92
01-04-2019 167.520004 5.28
01-05-2019 137.990005 4.63
01-06-2019 172.580002 4.4
01-07-2019 158.660004 4.2
01-08-2019 132.419998 3.09
01-09-2019 136.710007 3.81
01-10-2019 152.729996 3.86

Adj close price of both companies

200
150
100
50
0
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39 41 43 45 47 49 51 53

Adj Close ROG Adj Close FIT

Figure 3.1(a): Line chart of Adjust close price of both companies

3.2 Calculate the monthly return of each share, yielding 59 observations. Plot the
histograms and report observations. Perform a brief comparative analysis across the two
firms.
Date Adj Close ROG Returns Adj Close FIT Returns
01-06-2015 66.139999 38.23
01-07-2015 55.970001 -0.166957842 47.599998 0.219212172
01-08-2015 55.66 -0.005554095 34.490002 -0.322163234
01-09-2015 53.18 -0.04557937 37.689999 0.088725296
01-10-2015 46.52 -0.133800058 40.540001 0.072894385
01-11-2015 55.43 0.175238636 28.719999 -0.344695456
01-12-2015 51.57 -0.072180855 29.59 0.029842757
01-01-2016 47.470001 -0.082842154 16.6 -0.578033771
01-02-2016 53.419998 0.118087217 12.23 -0.305510746
01-03-2016 59.869999 0.113990358 15.15 0.214108582
01-04-2016 57.360001 -0.042828315 18.25 0.186164548
01-05-2016 66.470001 0.147403519 14.18 -0.252332559
01-06-2016 61.099998 -0.0842389 12.22 -0.148758567
01-07-2016 68.440002 0.113445645 13.66 0.1113979
01-08-2016 55.91 -0.202214223 15.48 0.125077014
01-09-2016 61.080002 0.088441258 14.84 -0.04222263
01-10-2016 54.43 -0.115269041 13.26 -0.112574253
01-11-2016 74.32 0.311464622 8.36 -0.461293558
01-12-2016 76.809998 0.032954719 7.32 -0.132848099
01-01-2017 79.949997 0.040066588 6.01 -0.197185579
01-02-2017 82.510002 0.031518121 6.21 0.032736147
01-03-2017 85.870003 0.039915037 5.92 -0.047824447
01-04-2017 102.940002 0.181311754 5.72 -0.034367644
01-05-2017 106.209999 0.031271943 5.23 -0.089557527
01-06-2017 108.620003 0.022437323 5.31 0.015180557
01-07-2017 117.970001 0.082574783 5.16 -0.028655256
01-08-2017 118.550003 0.004904474 6.03 0.155810431
01-09-2017 133.279999 0.117117333 6.96 0.143432464
01-10-2017 152.080002 0.13195454 6.14 -0.125354732
01-11-2017 161.100006 0.057618616 6.86 0.1108827
01-12-2017 161.919998 0.005077046 5.71 -0.183488418
01-01-2018 164.779999 0.017508871 5.15 -0.103222309
01-02-2018 137.320007 -0.182297225 4.78 -0.074556168
01-03-2018 119.540001 -0.138662968 5.1 0.064799993
01-04-2018 106.699997 -0.113629922 5.55 0.084557388
01-05-2018 113.959999 0.065826371 5.43 -0.021858794
01-06-2018 111.459999 -0.022181728 6.53 0.184467809
01-07-2018 116.57 0.044826178 5.93 -0.09638273
01-08-2018 138.070007 0.169268903 6.02 0.015063046
01-09-2018 147.320007 0.064846285 5.35 -0.117990698
01-10-2018 123.059998 -0.179935114 4.73 -0.123171358
01-11-2018 128.660004 0.044501272 5.51 0.152639421
01-12-2018 99.059998 -0.26144759 4.97 -0.103144783
01-01-2019 126.910004 0.247752498 6.17 0.216278998
01-02-2019 155.25 0.201558515 5.92 -0.041362389
01-03-2019 158.880005 0.023112511 5.92 0
01-04-2019 167.520004 0.052953539 5.28 -0.114410351
01-05-2019 137.990005 -0.193921516 4.63 -0.13136923
01-06-2019 172.580002 0.223679654 4.4 -0.050952327
01-07-2019 158.660004 -0.084097336 4.2 -0.046520016
01-08-2019 132.419998 -0.180784899 3.09 -0.306913434
01-09-2019 136.710007 0.031883271 3.81 0.209458098
01-10-2019 152.729996 0.110809685 3.86 0.013037994
Table 3.2(a): Monthly Returns of FITBIT Corporation and ROGERS Corporation

Bin Frequency
-0.26145 1
-0.1796 5
-0.09776 5
-0.01591 7
0.065931 18
0.147775 9
0.22962 5
More 2

Frequency
20

15

10

5 Frequency
0

Figure 3.2(a): Histogram of ROGERS Corporation Returns using Bin frequency

Bin Frequency
-0.57803 1
-0.46414 0
-0.35025 1
-0.23636 5
-0.12246 7
-0.00857 16
0.10532 10
More 12

Frequency
18
16
14
12
10
8
6
Frequency
4
2
0

Figure 3.2(a): Histogram of FITBIT Corporation Returns using Bin frequency

Figure 3.2(c): Combined histogram of FITBIT Corporation and ROGERS corporation python
3.3 Create 50 random portfolios (can be easily done in MS Excel or Python) and calculate
the mean, SD as well as Mean/SD for such portfolios.

Figure 3.3(a): Scatter plot by Sharpe Ratio

ret stdev sharpe weight ROG weight FIT


25 0.018411 0.340832 0.054017 0.599462 0.400538
4 0.012122 0.340873 0.035562 0.589510 0.410490
14 0.034563 0.341478 0.101216 0.625025 0.374975
7 -0.007878 0.342098 -0.023029 0.557857 0.442143
26 0.043732 0.342325 0.127750 0.639536 0.360464
40 -0.012684 0.342638 -0.037020 0.550251 0.449749
42 0.048471 0.342898 0.141357 0.647036 0.352964
2 -0.017872 0.343327 -0.052056 0.542041 0.457959
38 0.059246 0.344543 0.171955 0.664088 0.335912
29 -0.025826 0.344596 -0.074946 0.529453 0.470547
6 0.060562 0.344776 0.175657 0.666171 0.333829
41 0.061707 0.344984 0.178869 0.667983 0.332017
18 -0.041710 0.347890 -0.119893 0.504316 0.495684
11 -0.042770 0.348145 -0.122851 0.502637 0.497363
32 0.086550 0.350782 0.246734 0.707299 0.292701
9 0.094728 0.353212 0.268190 0.720242 0.279758
36 0.102728 0.355832 0.288699 0.732903 0.267097
34 -0.075051 0.357968 -0.209660 0.451549 0.548451
43 -0.075232 0.358034 -0.210126 0.451263 0.548737
19 0.109864 0.358365 0.306570 0.744196 0.255804
8 0.111386 0.358930 0.310328 0.746605 0.253395
1 0.112921 0.359507 0.314100 0.749034 0.250966
15 -0.084488 0.361562 -0.233676 0.436614 0.563386
33 0.124953 0.364318 0.342978 0.768076 0.231924
20 0.127106 0.365232 0.348015 0.771484 0.228516
37 -0.101496 0.368816 -0.275194 0.409698 0.590302
47 -0.106178 0.370982 -0.286207 0.402289 0.597711
0 -0.107747 0.371724 -0.289858 0.399804 0.600196
48 -0.118277 0.376904 -0.313811 0.383141 0.616859
24 -0.119154 0.377351 -0.315765 0.381752 0.618248
5 -0.119816 0.377690 -0.317233 0.380705 0.619295
39 -0.123450 0.379574 -0.325232 0.374954 0.625046
13 -0.128233 0.382116 -0.335586 0.367384 0.632616
49 0.171437 0.387349 0.442590 0.841641 0.158359
3 0.173550 0.388551 0.446660 0.844986 0.155014
45 -0.170537 0.407376 -0.418622 0.300434 0.699566
21 0.206656 0.408943 0.505341 0.897379 0.102621
16 -0.175997 0.410973 -0.428243 0.291793 0.708207
46 0.215362 0.414762 0.519242 0.911157 0.088843
30 0.215726 0.415009 0.519809 0.911733 0.088267
27 -0.208170 0.433546 -0.480157 0.240876 0.759124
23 -0.208774 0.433991 -0.481056 0.239920 0.760080
10 -0.226805 0.447600 -0.506713 0.211384 0.788616
31 -0.242113 0.459625 -0.526762 0.187157 0.812843
22 -0.243112 0.460424 -0.528017 0.185577 0.814423
28 -0.251117 0.466886 -0.537856 0.172907 0.827093
12 -0.263199 0.476834 -0.551972 0.153787 0.846213
17 -0.293851 0.503036 -0.584155 0.105276 0.894724
35 -0.321328 0.527565 -0.609077 0.061792 0.938208
44 -0.346961 0.551216 -0.629447 0.021224 0.978776

Table 3.3(a): Obtained random portfolio of both the companies using Python

count mean std min 25% 50% 75% max


FIT Return 51.0 -0.030031 0.162770 -0.439000 -0.116852 -0.041344 0.090508 0.245095

ROG Return 51.0 0.022625 0.131686 -0.230064 -0.080081 0.032020 0.106301 0.365423

Table 3.3(b): calculation Mean, Standard deviation and quartiles of companies returns using

3.4 Break the SD into suitable class intervals and identify portfolios with largest mean for
each of the class intervals and plot with SD (mid-point of class interval) and maximum
value of mean in that SD class interval. These are prescribed portfolios (optimal
portfolios).

Class Interval Portfolio Class

0.31 to 0.41 Low risk Portfolio

0.42 to 0.48 Median risk Portfolio

0.49 to 0.57 High risk Portfolio

Table 3.4(a): standard deviation classified by three classes in Python

Low risk Portfolio

ret stdev sharpe weight FIT weight ROG


8 0.021860 0.340879 0.064128 0.395079 0.604921
7 0.023293 0.340913 0.068326 0.392811 0.607189
3 0.026962 0.341039 0.079059 0.387005 0.612995
13 0.004662 0.341136 0.013665 0.422297 0.577703
39 0.034194 0.341451 0.100144 0.375559 0.624441
25 0.042368 0.342177 0.123818 0.362624 0.637376
15 -0.012196 0.342579 -0.035602 0.448977 0.551023
11 -0.015388 0.342983 -0.044864 0.454027 0.545973
48 -0.018471 0.343414 -0.053787 0.458907 0.541093
24 -0.019690 0.343595 -0.057307 0.460837 0.539163
16 0.056532 0.344084 0.164298 0.340206 0.659794
14 -0.023281 0.344162 -0.067645 0.466519 0.533481
4 0.057415 0.344230 0.166791 0.338810 0.661190
45 -0.023754 0.344241 -0.069003 0.467267 0.532733
ret stdev sharpe weight FIT weight ROG
18 0.059516 0.344590 0.172715 0.335485 0.664515
26 -0.034075 0.346182 -0.098432 0.483602 0.516398
30 -0.039173 0.347297 -0.112795 0.491670 0.508330
40 -0.042669 0.348120 -0.122569 0.497202 0.502798
42 -0.053497 0.350973 -0.152424 0.514338 0.485662
28 -0.075098 0.357985 -0.209779 0.548524 0.451476
20 -0.088790 0.363304 -0.244396 0.570194 0.429806
49 -0.091596 0.364474 -0.251310 0.574634 0.425366
19 -0.097045 0.366823 -0.264554 0.583258 0.416742
12 -0.100707 0.368458 -0.273319 0.589053 0.410947
32 -0.106481 0.371125 -0.286915 0.598192 0.401808
43 -0.107559 0.371635 -0.289421 0.599898 0.400102
31 -0.107916 0.371804 -0.290249 0.600462 0.399538
35 0.142743 0.372329 0.383377 0.203770 0.796230
22 -0.116756 0.376134 -0.310410 0.614452 0.385548
23 -0.124302 0.380022 -0.327092 0.626395 0.373605
6 -0.133892 0.385209 -0.347583 0.641572 0.358428
36 -0.166255 0.404606 -0.410905 0.692789 0.307211
44 0.200437 0.404898 0.495030 0.112463 0.887537
29 -0.172600 0.408727 -0.422287 0.702832 0.297168
41 -0.177699 0.412109 -0.431193 0.710901 0.289099
38 0.219264 0.417428 0.525275 0.082667 0.917333
Table 3.4(b): Calculation of Low risk portfolio using python

Median risk Portfolio

1 -0.200950 0.428286 -0.469196 0.747698 0.252302

27 0.242175 0.433751 0.558328 0.046408 0.953592

2 -0.212048 0.436415 -0.485886 0.765262 0.234738

9 0.246083 0.436644 0.563578 0.040224 0.959776

47 -0.216864 0.440019 -0.492851 0.772884 0.227116

1 0.257032 0.444910 0.577717 0.022895 0.977105

34 0.261309 0.448201 0.583019 0.016126 0.983874


0 -0.229781 0.449905 -0.510733 0.793327 0.206673

37 0.265868 0.451744 0.588536 0.008912 0.991088

5 0.266770 0.452450 0.589612 0.007485 0.992515

17 -0.267292 0.480255 -0.556563 0.852691 0.147309


Table 3.4(c): Calculation of Median risk portfolio using python

High risk Portfolio

10 -0.286795 0.496889 -0.577181 0.883556 0.116444

33 -0.338231 0.543084 -0.622796 0.964958 0.035042

46 -0.359009 0.562561 -0.638169 0.997842 0.002158

Table 3.4(d): Calculation of High risk portfolio using python

3.5 Discuss the limitations of this approach.

 Complex Method: It is complex to compute standard deviation and difficult to


understand as compared to other measures of dispersion.
 High Effect: Standard deviation is highly affected by the extreme values in the series.
 Not suitable for open and class frequency distribution: Standard deviation cannot be
obtained for open end class frequency distribution.
 Portfolio Comparison: Each portfolio is unique, and that uniqueness is both an
advantage and a disadvantage. A portfolio is not a standardized test and should not
be treated as such.

Potrebbero piacerti anche