NMIMS

DECISION SCIENCE
APPLICABLE FOR JUNE 2022

1. Three airlines serve a Srinagar. Airline ‘Amira’ has 50% of all the scheduled flights,
airline ‘Biyas’ has 30%, and airline ‘chinar’ has the remaining 20%. Their on-time
rates are 80%, 65%, and 40%, respectively.
Part 1) Draw the Probability tree diagram. (Note: You may use any software for this,
like MS paint, MS office, etc.)
Part 2) a plane has just left on time. What is the probability that it was airline ‘Amira’?

Answer:

It is given in the question that three airlines serve Srinagar. Airline Amira has 50% of all the
scheduled flights, airline Biyas has 30%, and airline Chinar has the remaining 20%

i.e. A,B,C are mutually exclusive and exhaustive events as there is no other flight than these
three.

Flight Prob Time rates prob Combined prob

A 0.50 0.80 0.5*0.8 = 0.40

B 0.30 0.65 0.3*0.65 = 0.195

C 0.20 0.40 0.2*0.4 = 0.08

Total = 0.675

Or

Given
P(A)=0.5, P(B)=0.3, P(C)=0.2,
P(Yes|A)=0.8, P(Yes|B)=0.65, P(Yes|C)=0.4
The Law of Total Probability

P(Yes)=P(A)P(Yes|A)+P(B)P(Yes|B)+P(C)P(Yes|C)
=0.5(0.8)+0.3(0.65)+0.2(0.4)
=0.4+0.195+0.08
=0.675

The probability that it will reach to its destination on time is 0.675.

A plane has just left on time. What is the probability that it was airline A

= P(A/time) = Pr of time and A/Prob of time

= 0.4/0.675

= 0.5926

Probability tree diagram

2. Rashmi Dhar, manufacturer, and seller of ‘Kashmiri- kahwa’ through E-commerce’s

websites. She wanted to know the effect of her spending in advertisement of ‘Kahwa’ on
the sales,along with the other factors; ‘number of sales representatives’, ‘customer-
satisfaction ratings’. For this research she has gathered the sales data in the following
table, along with other necessary information.
Part 1) Define dependent and independent variables
Part 2) Write regression model equation only
Part 3) Run regression analysis in EXCEL (copy all those tables from EXCEL and
paste them in your document).
Part 4) Write the Interpretation of Regression statistics-table, ANOVA- table.
Write an interpretation (by referring P-value/ t-stat) on significant effect of independent
variables on sales.

Region/ Sales of Spending inadvertise number of sales customer-satisfaction

istricts Kahwa (in INR) representatives ratings (1=highly
(inINR) (person) dissatisfied to 5 =
highly satisfied
Kupwara 55328 5512 1 1
Badgam 56251 8337 1 1
Lehladak 57126 8788 4 1
h
Kargil 58739 8828 5 1
Punch 66984 9050 5 2
Rajouri 70676 10150 7 2
Kathua 73206 11236 8 2
Baramula 80571 12538 8 3
Bandipore 93168 13161 8 3
Srinagar 99432 13448 9 4

Answer:

1)
Variables Dependent/Independent
Sales Dependent variable
 Spending Independentvariable
Sales Person Independentvariable
Consumer Satisfaction Independentvariable

2. Regression Model equation

Sales=Intercept+ (a*Adv. Spending)+(b*no of Sales Person)+(c*Consumer Satisfaction)
Where; a,b,c are respective co-efficient of variables

3. Regression analysis in EXCEL

Regression Statistics  
Multiple R 0.98109
R Square 0.96253
Adjusted R Square 0.9438
Standard Error 3721.76
Observations 10

Anova
  df SS MS F Significance F
Regression 3 2135139002 711713000.8 51.3818 0.00011
83108800.5
Residual 6 5 13851466.76    
Total 9 2218247803      

Coefficient Standard P- Lower Upper Lower Upper

  t Stat
ients Error value 95% 95% 95.0% 95.0%
8538.400
Intercept 32355.3 0 3.789382 0.0090 11462.5 53248 11462.5 53248
Spending 1.6868 1.500232 1.124382 0.3038 -1.9841 5.357 -1.9841 5.357
Sales 1061.613
Person -155.53 4 -0.146502 0.8883 -2753.2 2442.14 -2753.2 2442.14
Consumer 11309.3 2589.262 4.367781 0.0047 4973.64 17645 4973.64 17645
Satisfaction 9

4. Regression Statistics:

 Higher R and R Square Value suggest positive correlation

 Even Adjusted R Square Value is near 1 show highly positive impact of variables on
Sales.
 Standard Error is also very low.
 Combined all the factors; Higher Adjusted R Square, Low Standard Error means
better predictability of sales based on variables.

ANOVA Table:

 Alpha (Significance of F) is less than 0.05 shows significant relationship between

sales and variables.
 Comparatively lower SSE and MSE show lower variation and higher predictability.
 Higher p values for Advertisement Spending a Sales Person suggest no significant
impact as compared to Consumer Satisfaction on Sales. I.e. Only Consumer
Satisfaction can be used for predicting sales while other 2 variables can be ignored.

3.a. According to one survey in India, 75% of Instagram users love REELS. Suppose
that 25Instagram users (randomly selected) have been approached in the university
located in vileparle. They have been asked about their status of like/ dislike the
Instagram- REELS.

a) What is the probability that exactly 15 of them would agree with the claim (or said
they love Insta-REELS)?
b) What is the probability that exactly 20 of them would agree with the claim (or said
they love Insta-REELS)?
3.b. ‘Bhartdarshan’ is an Internet-based travel agency wherein customers can see
videos of the cities they plan to visit. The number of hits daily is a normally distributed
random variable with a mean of 10,000 and a standard deviation of 2,400.
a. What is the probability of getting more than 12,000 hits?
b. What is the probability of getting fewer than 9,000 hits?

Answer:

A)

As given in the question,

N = 25

P = 0.75

Q= 0.25

x = 15, 20

Probability that Exactly 15 of them would agree with the claim

Px = NCx * P^x * Q^(N-x)

P(15) = 25C15 * (0.75)^15 * (0.25)^10

= 3268760 * 0.01336 * 0.00000095

= 0.0416

Probability that Exactly 20 of them would agree with the claim

Px = NCx * P^x * Q^(N-x)

P(20) = 25C20 * (0.75)^20 * (0.25)^5

= 53130 * 0.00317 * 0.000977

= 0.1645

B)

Probability of getting more than 12,000 hits

Z = (x-µ)/σ

z = 12000 - 10000
2400

z = 2000/2400
z = 0.83

Therefore, as per z table P = 0.7977

But since we want ‘greater than’, we need to subtract the probability from 1

P = 1 – 0.7977 = 0.2023

Probability of getting fewer than 9,000 hits

Z = (x-µ)/σ

z = 9000 - 10000
2400

z = -1000/2400

z = -0.42

Therefore, as per z table P = 0.3384