Advanced Business Statistics

for Decision Making

Facilitator- Dr. Shilpa Bhaskar Mujumdar
 Lecture Agenda
• Introduction
• Course outcomes
• Syllabus
• Books
• Pre learning
• Probability
 Course Outcomes (CO)
1. Students should be able to apply the appropriate Probabilistic tools required for Data Analytics
to real time Problems
2. Students should be able to understood how the sample space can be reduced by introducing
the random variables and ease of obtaining the probabilistic models
3. To Student should be able to identify appropriateness of standard probability distributions and
apply it to real time problems
4. Students should be able to apply the appropriate sampling techniques for data collection and
testing of hypothesis, correlation, regression for prediction.
5. Students should be able to apply the appropriate point estimators and interval estimators for
estimation of unknown parameters of the distributions
 Books Recommended

SrNo Title of Book Authors Publication

1 Statistical Techniques in Lind, Marchal, Wathen Tata McGraw-Hill

Business and Economics Companies
2 Statistics for Business and Anderson, Sweeny, South-Western CENGAGE
Economics Williams Learning
3 Business Statistics :For Ken Black Wiley
Contemporary Decision
Making
4 Complete Business Amir Aczel, Jayavel Mc Graw Hill
Statistics Sounderpandian
5 Head First Statistics: A Dawn Griffiths O′Reilly
Brain-Friendly Guide
6 Statistics for Business: Robert A. Stine and Dean Pearson
Decision Making and Foster
Analysis
7 Statistics : F. Y. B. Sc. Dr. P. G. Dixit, Dr. V. R. Nirali Prakashan
Statistics- Paper II Prayag and Mr. D. L.
Limaye
4
 MBA(IT) Specialisations

• Data analytics

• Banking and Financial Markets

• Software Project Management

5
Advanced Business Statistics
for Decision Making
https://www.youtube.com/watch?v=af5embKsb2g
 Pre-learning
• Principles of addition and multiplication
• Permutation
• Combination
• Basic concepts of set theory
 Probability
• Three definitions of probability
• Empirical
• Classical
• Axioms
• How to Calculate Probability?
 Relative frequency
Marks of Frequency (f) Less than Relative Cumulative
The discrete frequency distribution students (No. of students) C.F. frequency Relative
frequency
for marks of students is given in table. 0 1 1
1/30=
Calculate relative frequency and 1 2 1+2=3 3/30=
2 2 5 5/30=
less than cumulative relative 3 4 9
4 4 13
frequency. 5 6 19
6 3 22
𝐶𝑙𝑎𝑠𝑠 𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦 7 2 24
Relative frequency= 8 4 28
𝑇𝑜𝑡𝑎𝑙 𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦
9 1 29
10 1 30

Total N= 𝑓=30
 Relative frequency contd..
Marks of Frequency (f) Less than C.F. Relative Less than
students (No. of students) frequency Cumulative
Relative frequency
0 1 1
(1/30)=0.03 (1/30)=0.03
1 2 1+2=3
(2/30)=0.07 (3/30)=0.10
2 2 5
0.07 (5/30)=0.17
3 4 9
0.13 0.30
4 4 13
0.13 0.43
5 6 19
0.20 0.63
6 3 22
0.10 0.73
7 2 24
0.07 0.80
8 4 28
0.13 0.93
9 1 29
0.03 0.97
10 1 30
0.03 1.00
Total N= 𝑓=30 1
Normalization of Frequencies
Relative frequency

Marks No. of Students

C.I. Div A Div B

0-20 5 5

20-40 10 10

40-60 20 20

60-80 11 13

80-100 4 12

Total
50 60
Normalization of Frequencies
Relative frequency

Marks No. of Students Relative frequency

C.I. Div A Div B Div A Div B

0-20 5 5
0.1 0.08
20-40 10 10
0.2 0.17
40-60 20 20
0.4 0.33
60-80 11 13
0.22 0.22
80-100 4 12
0.08 0.2
Total
50 60 1 1
 Relative Frequency Definition
• Relative frequency- It shows the proportion in which observation
appear in data individually or in class intervals. The total relative
frequency is always 1. it facilitates comparison of 2 or more frequency
distributions with different number of observations.

𝐶𝑙𝑎𝑠𝑠 𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦
• Relative frequency=
𝑇𝑜𝑡𝑎𝑙 𝑓𝑟𝑒𝑞𝑢𝑒𝑛𝑐𝑦
 Classical definition of Probability
• Consider a random experiment with sample space S. The experiment
results in n(S) mutually exclusive and equally likely outcomes. Let A be
the event on the sample space S with n(A) outcomes. Then
𝑛(𝐴) 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 𝑖𝑛 𝑒𝑣𝑒𝑛𝑡 𝐴
• P(A)= =
𝑛(𝑆) 𝑇𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 𝑖𝑛 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑝𝑎𝑐𝑒 𝑆
𝑛(𝐴)
• If A is an impossible event then A=Φ={ }, n(A)=0 and P(A)= =0
𝑛(𝑆)
𝑛(𝐴) 𝑛(𝑆)
• If A is a sure event then A=S then n(A)=n(S) and P(A)= = =1
𝑛(𝑆) 𝑛(𝑆)
• Hence 0 ≤P(A) ≤ 1
 Classical definition of Probability
• Consider a random experiment with sample space S. The experiment
results in n(S) mutually exclusive and equally likely outcomes. Let A be
the event on the sample space S with n(A) outcomes. Then
𝑛(𝐴) 𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 𝑖𝑛 𝑒𝑣𝑒𝑛𝑡 𝐴
• P(A)= =
𝑛(𝑆) 𝑇𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 𝑖𝑛 𝑠𝑎𝑚𝑝𝑙𝑒 𝑠𝑝𝑎𝑐𝑒 𝑆

• Imp 0 ≤P(A) ≤ 1
 Random Experiment
• Deterministic Experiment

• Any operation that results in only one outcome

• Example-An object thrown in sky falls down

• Random Experiment

• Any operation that results in two or more outcomes

• Example-Toss a coin, Appear for exam, Roll a die
 Sample Space and Events
• Sample space
• The set of all possible outcomes of a random experiment.
• It is denoted by S or Ω
• Random experiment toss a coin,
• S={H,T}
• Random experiment toss two coins,
• S={HH,HT,TH,TT}

• Sample space can be discrete or continuous

• Discrete sample space- with finite or countable number of outcomes
• Continuous sample space-with uncountable infinite number of outcomes
 Sample Space and Events
• Discrete Sample space
• S={H,T} (finite) or S={H, TH,TTH,TTTH,………….} (countably infinite)
• Continuous Sample space
• Measuring height of a person S=(130, 190)cms
• Events
• A subset of a sample space
• Event denoted by capital letters A,B,C etc.
• Let S={HH,HT,TH,TT} then event A=two heads occur, then A={HH}
 Mutually exclusive and Equally likely
outcomes
• Mutually exclusive outcomes
• The occurrence of one outcome prevents occurrence of remaining outcomes.
• Example –when a coin is tossed occurrence of Head and Tail

• Equally likely outcomes

• If all outcomes have equal chance of occurrence
• Example –when a fair coin is tossed occurrence of Head and Tail is equally likely
 Numerical on Classical Definition of Probability

• Consider the random experiment of rolling a fair die and calculate probability of getting an odd
number. NEXT

• S={1,2,3,4,5,6}
• n(S)=6
• Let event A=getting an odd number
• A={1,3,5}
• n(A)=3
𝑛(𝐴) 3
• P(A)= = =0.5
𝑛(𝑆) 6
• Find the number of ways in which the letters of the word "GARDEN" can be arranged.
• Find the number of ways in which the 3 cards can be drawn from a well shuffled pack of cards
• Four cards are drawn at random from a well shuffled [pack of 52 cards. Find the probability that
(a) All four cards are of red colour (b) 2 cards are red and 2 cards are black
L3-Numericals on Classical Definition of Probability

• Addition principle of counting

• If one operation can be performed in m ways and another opreration can be
performed in n ways then, The total number of ways in which either
operation 1 or operation 2 can be performed is m+n
• Multiplication principle of counting
• If one operation can be performed in m ways and another opreration can be
performed in n ways then, The total number of ways in which operation 1
and operation 2 can be performed is m*n=mn
 Numericals on Classical Definition of Probability
contd.
• The letters of the word “seminar” are arranged at random. Find the probability that the vowels
occupy even places.
• Permutation
• The total number of arrangements of n distinct objects taken r at a time without repetition is
given by

• Four cards are drawn at random from a well shuffled pack of 52 cards. Find the probability that (a)
All four cards are of red colour (b) 2 cards are red and 2 cards are black

• Combination
• It is a selection of objects. The number of ways in which r objects can be selected without
repetition out of n distinct objects is given by Type equation here.
• A basket contains 5 mangoes and 4 oranges. If any 3 fruits are to be drawn from the basket find
the probability that at least one mango is selected.
 Types of Events
• Simple or elementary event
• Impossible event
• Sure or certain event
• Mutually exclusive or disjoint events
• Complement of an event
• Exhaustive events
• Mutually exclusive and Exhaustive events
 Types of Events contd.
• Simple or elementary event
• Consists single outcome of sample space S
• Example: Toss two coins S={HH,HT,TH,TT}
• Let event A=two heads occur
• A={HH}
• Sure or certain event
• Contains all outcome of sample space S
• Example: Toss two coins S={HH,HT,TH,TT}
• Let event B=at most two heads occur
• B={TT,HT,TH,HH}=S
 Types of Events contd..
• Impossible event
• Consists of no outcome of sample space S
• Example: Toss two coins S={HH,HT,TH,TT}
• Let event A=Neither head nor tail occurs
• A={ }=Φ
• Mutually exclusive or disjoint events
• Let A and B are two events on sample space S
• If AՈB=Φ={ }
• Example Toss two coins S={HH,HT,TH,TT}
• Let event A== two head occurs={HH}
• Event B=Only one head occurs={HT,TH}
• Complement of an event
• Let A be the event on sample space S
• Set of all outcomes in S but not in A, denoted by A’
• Example: Toss two coins S={HH,HT,TH,TT}
• Let event A= two head occurs={HH}
• A’={HT,TH,TT}
 Types of Events contd…
• Exhaustive events
• Let A, B and C are three events on sample space S
• If AUBUC=S,
• then A,B,C are exhaustive events
• Example: Roll a die S={1,2,3,4,5,6}
• Event A= a number less than 4 occurs ={1,2,3}
• Event B=a multiple of 3 occurs={3,6}
• Evenvt C=a number greater than 3 occurs={4,5,6}
• AUBUC={1,2,3,4,5,6}=S
 Set theory and occurrence of Events
• Notations for occurrence of events
• Represent occurrence of following events using set theory notations
• Occurrence of at least one of the given events
• Occurrence of all the given events or simultaneous occurrence of
events
• Occurrence of none of the given events
 Set theory and occurrence of Events
• Notations for occurrence of events
• Let A, B are two events on sample space S corresponding to a random experiment
then represent following events using union(U) and intersection(Ո)
• OR=>U
• AND=> Ո
• Occurrence of at least one of the given events i.e. either A occurs or
B occurs
• AUB- ven diagram
• Both A and B occurs
• A Ո B-ven diagram
 Limitations of Classical Definition of
Probability
• Random experiments
• Equally likely outcomes
• Toss a coin (fair?)
• S={H,T}
• n(s)=2
• Toss a coin until head occurs
• S={H, TH,TTH,TTTH,………….}
• n(s)=?
• Measuring height of a person
• S=(130, 190)cms
• n(s)=?

• Equally likely outcomes & Infinite sample space

 Axioms of Probability
• Russian mathematician A. N. Kolmogorov (1933)
• Axiom: A statement accepted heuristically and not proved
• Let S be a sample space corresponding to a random experiment. Let A be any
event of S. Then probability of event A denoted by P(A), is defined as a real
valued function on S, which satisfies following axioms:
• Axiom1 : P(A)≥0
• Axiom2 : P(S)=1
• Axiom3 : If 𝐴1 , 𝐴2 ……𝐴𝑛 are any mutually exclusive events of S, then
• P(𝐴1 𝑈𝐴2 U….. 𝑈𝐴𝑛 )=P(𝐴1 )+P(𝐴2 )+….+P(𝐴𝑛 )
• i.e. P( 𝑛𝑖=1 𝐴𝑖 = 𝑛𝑖=1 𝑃(𝐴𝑖 )
 Theorems on Probability

Th1: Let A be any event of S then P(A’)=1-P(A)

Th2: P(Φ)=0
Th3: Let A be any event of S then 0 ≤P(A) ≤ 1
Th4: Addition theorem of Probability
Let A and B are any two events of S, then
P(AUB)=P(A)+P(B)-P(AՈB)
P(AUB)=P(A)+P(B) [if A and B are disjoint P(AՈB)=0]