Beruflich Dokumente
Kultur Dokumente
Insurance premiums Banking industry Betting on Cricket team Weather forecasting Medical decisions Getting a job Lottery prize Gambling
16-08-2013
Gamblers have been taking chances based on their judgements. Seventeen century French mathematicians tried to give it a mathematical basis. They were Antoine Gombauld (1607-84), Blaise Pascal (1623-62) and Pierre de Fermat (1601-65). In 19th century Pierrie Simon, Marquis de Laplace unified early ideas and compiled the first general theory of probability.
Probabilty: S C Agarkar, BRIMS 16-08-2013 3
The warning was issued by the Surgeon General that Cigarette smoking is hazardous to your health. How might probability theory have played a part in this warning? A well known manufacturer of children clothing decides to expand its product line by adding preteen clothing. In what way you think the decision involves probability theory
16-08-2013
Event: It is one or more of the possible outcomes of doing something (head or tail during coin tossing). Experiment: It is an activity that produces an event. Sample space: It is the set of all possible outcomes of an experiment S= (head, tail). Mutually exclusive events: If one and only one event can take place (head or tail). Collectively exhaustive list: All possible events can result in the experiment (HH, HT, TT, etc.).
Probabilty: S C Agarkar, BRIMS 16-08-2013 5
Give a collectively exhaustive list of all the possible outcomes of tossing two dice. Give the sample space of outcomes for the following experiment in terms of their sex make up: the birth of (a) twins, (b) triplets. Give the probability of each of the following totals in the rolling of two dice: 1, 2, 5, 6,7,10,11 Ans: 0, 1/36, 5/36, 6/36,4/36,3/36,2/36
16-08-2013
16-08-2013
Classical probability is also called a priory probability because we can give answer in advance (a priori) without conducting an experiment. For example, coin tossing or dice rolling. P(E)= Number of event outcomes/Total number of possible outcomes Probability of getting head in coin tossing is P(H)= =0.5. Probability of getting 5 in dice rolling is P(5)= 1/6 This is an ideal case and everyday cases would be more complicated.
16-08-2013
This method uses the relative frequencies of past occurrences as probabilities. Look at how often an event has occurred in the past an predict the occurrence of the event in the future. Data on the number and nature of accidents on the highway enables us to guess possible accidents and attempt to prevent them. Data on the sale of previously launched gadget enables one to predict the sale of newly launched gadget.
16-08-2013
The subjective approach of assigning probabilities was introduced in 1926 by Frank Ramsey in his book The Foundation of Mathematics and Other Logical Essays. Subjective probability can be defined as the probability assigned to an event by an individual based on his/her beliefs and experiences. Examples are: Choosing a right person for a job, entering into a new business, launching a new product, giving a judgement on nuclear plant, etc.
Probabilty: S C Agarkar, BRIMS 16-08-2013 10
Determine the probabilities of the following events in drawing a card from a standard deck of 52: (a) A queen, (b) A Club (c) An ace in red suit, (d) A red card, (e) A face card, (f) what type of probability estimates are these? Classify the following probability estimates as to their types (classical, relative frequency or subjective) (a) You will make B in this course is 0.75. (b) A family has two children (c) My candidate will win (d) Student from this course will go abroad. (e) I will get selected for a football team.
16-08-2013
12
Marginal or unconditional probability is so called when there is a possibility of only one event occurring. It is given by the formula P(A)= 1/Total number of cases. It is read as the probability of event A happening. Examples are a person securing Gold Medal in Olympics, a person winning the state lottery, a person becoming a governor of a Reserve Bank, etc.
Probabilty: S C Agarkar, BRIMS 16-08-2013 13
The probability of two or more independent events occurring together or in succession P(AB) = P(A) * P(B) The probability of heads on two successive tosses is the probability of heads on first toss times the probability of heads on second toss. It will be .5*.5= .25
16-08-2013
14
Addition Rule for events that are mutually excusive. It is used when we are interested in the probability that one thing or the other will occur assuming that each of them is mutually exclusive. Addition rule for events that are not mutually exclusive. It is used when we are interested in the probability that one thing or the other will occur assuming that each of them is not mutually exclusive.
16-08-2013
15
If A and B events are mutually exclusive then we calculate the probability that one thing or another will occur by addition formula: P (A or B) = P(A) + P(B). It is read as probability of either A or B occurring is given by the addition of A occurring and B occurring. Suppose five candidates have been short listed for a summer job. Chance of A getting a job is 1/5 and the chance of B getting the job is also 1/5. Probability of A or B getting the job is 1/5+1/5=2/5 that is 0.4
As safety officer of an airline Debbie Best has been asked to give a talk to the press concerning engine safety. As part of her talk she has decided to include the probability of two-engine jet having failure on flight. After consulting her record she find the following information about last years operating record 29 reported failures of the right engine 33 reported failures of left engine there was no crash attributed There were 345,000 flights during the year What probability should she report?
When two events are not mutually exclusive then the addition rule needs to be modified. In this case we have to avoid double counting. Hence the formula is modified as P(A or B) = P(A) + P(B) P(AB) If we wish to determine the probability of drawing either an ace or a heart from a deck of cards then P (Ace or Heart)= P(Ace) + P(Heart) P (A&H) = 4/52 + 13/52 1/52 = 16/25 or 4/13
16-08-2013
18
When two events happen, the outcome of the first event may or may not have an effect on the outcome of the second event. Events are statistically independent when occurrence of one event has no effect on the probability of occurrence of any other event Events are statistically dependent when occurrence of one vent has direct effect on the probability of occurrence of another event.
Probabilty: S C Agarkar, BRIMS 16-08-2013 19
Let us examine the events that are statistically independent. In this case the occurrence of one event has no effect on the probability of the occurrence on any other event. There are three types of probabilities under statistical independence:
Marginal Probability Joint Probability Conditional Probability.
16-08-2013
20
A marginal or unconditional probability is the simple probability of occurrence of an event. In a fair coin toss P(H)= 0.5 and P(T)= 0.5. This is true for every toss. Even if the coin is unfair or biased the outcome of any particular toss is completely unrelated to the outcome of tosses made earlier.
16-08-2013
21
The probability of two or more independent events occurring together or in succession is the product of their marginal probabilities. Multiplication rule for joint probabilities under statistical independence is expressed as P(AB) = P(A) * P(B) P(AB): Probability of events A and B occurring together or in succession P(A): Marginal probability of event A occurring P(B): Marginal probability of event A occurring
Probability of getting two heads on two successive tosses is 0.5 * 0.5 = 0.25. Probability of getting three heads on three successive tosses is 0.5*0.5*0.5= 0.125 Probability of tails, tails and heads in that order on three successive tosses is 0.5*0.5*0.5= 0.125. Probability of at least two heads on three tosses is 0.125+0.125= 0.5
16-08-2013
23
Conditional probability is the probability that a second event (B) will occur if the first event (A) has already happened. For statistical independent event the conditional probability of event B given that A has occurred is simply the probability of event B: P(A\B) = P(B). The probability that second toss would result into head even if the result of the first toss was head is 0.5 not affected by previous result.
16-08-2013
24
Type of probability
Symbol
Formula
Marginal
P(A)
P(A)
Joint
P(AB)
P(A)P(B)
Conditional
P(B\A)
P(B)
16-08-2013
25
What is the probability that in selecting two cards one at a time from the deck with replacement the second card is
(a) A spade, given that the first card was a heart (b) Black given that the first card was red (c) A queen, given that the first card was a queen
16-08-2013
26
Statistical dependence exists when the probability of some event is dependent upon or affected by the occurrence of some other event. Conditional and joint probabilities under statistical dependence are more involved than marginal probabilities.
16-08-2013
27
The general formula for conditional probability under statistical dependence is P(B\A) = P(BA)P(A) if the occurrence of B is dependent on the occurrence of A. It is P(A\B) = P(AB)P(B) if the occurrence of A is dependent on the occurrence of B. If there are ten balls (3 coloured and dotted, 1 coloured and stripped, 2 gray and dotted and 4 gray and striped) in a box. To calculate the probability of dotted given coloured we will have P(D\C) = P(DC)P(C) = 0.30.4
Probabilty: S C Agarkar, BRIMS 16-08-2013 28
The formula for conditional probability under conditions of statistical dependence is P(B\A)=P(BA)P(A) By cross multiplication we get the following formula for joint probabilities P(BA) = P(B\A) P(A) Continuing with example of coloured gray, dotted and striped balls we will have P(CD)= P(C\D) P(D)= 0.60.5 = 0.3
16-08-2013
29
Marginal probabilities under statistical dependence are computed by summing up the probabilities of all the joint events in which the simple event occurs. P(C)= P(CD) + P(CS) P(G)= P(GD + P(GS) P(C)= 0.3 + 0.1= 0.4 P(G)= 0.2 + 0.4= 0.6 P(D)= 0.3 + 0.2= 0.5 P(S)= 0.1 + 0.4 = 0.5
Probabilty: S C Agarkar, BRIMS 16-08-2013 30
Type of Probability
Marginal
Symbol
P(A)
Joint
Conditional
16-08-2013
31
Given that P(A)=1/6, P(B)=1/3, P(C)= 4/9, P(A&C)= 1/12 and P(B\C)=1/4, find the probabilities P(A\C), P(C\A), P(B&C), P(C\B). Myers clothiers knows that 1 out of 10 families in its trading area qualifies for their charge accounts and that 1 out of 15 families in this area has applied for an account, From past records, 90 percent of credit applications are accepted. What is the probability that an area family will apply for a Myers charge card and be accepted.
16-08-2013
32
A dice is rolled twice and the sum of the numbers appearing on them is observed to be 7. What is the conditional probability that the number 2 has appeared at least once? The required probability is P(A\B)=P(AB)/P(B) A= getting number 2 at least once P(A)= 11/36: (2,1); (2,2); (2,3), etc. B= getting 7 as sum of the numbers on two dice P(B)= 6/36: (2,5); (5,2); (1,6); (6,1); (3,4); (4,3) P(AB)= 2/36: (2,5); (5,2) P(A/B)= P(AB) P(B) = 2/36 6/36 =1/3
We estimate certain probability based on the data and experiences. It needs to be modified as more data is made available or collected. The new probabilities thus estimated are called revised or posterior probabilities. Posterior probabilities play a major role in decision making in business world.
16-08-2013
34
The concept of posterior probabilities is attributed to Reverend Thomas Bayes (17021761). He wanted to prove the existence of God with the help of mathematics. He developed a lot of mathematics related to probability but did not publish the work. His work was brought to light after his death. Bayes theorem is one of them.
16-08-2013
35
The basic formula for conditional probability under dependence is P(B/A)= P(BA)P(A). It is called Bayes theorem. Bayes theorem offers a powerful statistical method of evaluating new information and revising prior estimates. If correctly used it makes it unnecessary to gather masses of data over long periods of time in order to make decisions based on probabilities.
Probabilty: S C Agarkar, BRIMS 16-08-2013 36
Assume that we have equal number of two deformed dice in a bowl. On half of them ace (one dot) comes up 40% of the time. Therefore, P(ace) for type 1 is .4. On the other half ace comes 70% of the time. Hence P(ace) for type 2 is .7. One dice is drawn and rolled once shows up ace (one dot). Which one it is? What is the probability that it is type 1 dice? Since the number of type 1 and type 2 dice are equal we might think that the probability of getting type 1 dice id 0.5.
16-08-2013
37
Elementary event
Type 1 Type 2
P(ace/ele event)
0.4 0.7
0.4*0.5=0.20 0.7*0.5=0.35
The joint probability of ace and type 1 dice is .4*.5=0.2, the joint probability of ace and type 2 dice is .7*.5=05.
16-08-2013
38
P(B\A)= P(BA)/P(A) P(type 1\ace)= P(type 1, ace)/P(ace) P (type 1\ace)= .20/.55= .364 Thus the probability that we have drawn type 1 dice is 0.364. P(type2\ace) = P(type 2, ace)/P(ace) = .35/.55 = .636 The probability that we have drawn type 2 dice is .636. Our new posterior estimate is that there is a higher probability that the dice in our hand is type 2 than type 1.
16-08-2013
39
Assume that the same dice is rolled second time and again comes up one dot. The joint probability of two one dots on two successive rolls for type 1 is .4*.4= .16. It is .7*.7= .49 for the second dice. Joint probabilities of two aces on two successive rolls in type 1 is .16*.5= .080 Joint probabilities of two aces on two successive rolls in type 2 is .49*.5= .245
16-08-2013
40
P(type1\2 aces)= P(type 1, 2 aces)/P(aces) =.80/.325= .246 P(type2\2 aces)= P(type 2, 2 aces)/ P(2 aces) .245/.325= .754 Probability that it is type 1 is .246 and the probabilities that it is type 2 is .754 We have thus changed the original probability from .5 to .246 for type 1 and .754 for type 2 based on the information.
16-08-2013
41
A manufacturing firm produces pipes in two plants I and II with daily production of 1,500 and 2,000 pipes respectively. The fraction of defective pipes produced by two plants I and II are 0.006 and 0.008 respectively. If a pipe is selected at random from days production is found to be defective, what is the chance that it has come from plant I, plant II? P(E1) probability that a pipe is made in plant 1 is 1500/1500+2000 = 3/7 P(E2) probability that a pipe is made in plant II is 2000/1500+2000=4/7 P(A) is the probability that a defective pipe is drawn P(E1A)= 3/7*0.006 and P(E2A)=4/7*0.008 P(E1\A)= P(E1A) P(E1A)+P(E2A) = 3/7*0.0063/7*0.006+4/7*0.008 =9/25 Similarly P(E2\A) = 16/25
16-08-2013
42
There was a fire accident in a building. The investigation undertaken later by an expert showed that (a) Probability of short circuit is 0.8 (b) Probability of LPG cylinder explosion is 0.2 (c) Chance of fire accident is 30% for short circuit and it is 95% for LPG explosion. What do you think is the most likely cause of fire?
16-08-2013
43
Let A be the event that there was fire accident Let E1 be the event that there could have been short circuit, Let E2 be the vent that there could have been an LPG explosion. Given P(E1) = 0.8 and P(E2)=0.2 Also P(A/E1)= 0.3 and P(A/E2)= 0.95 P(E1) * (P(A/E1) = 0.8 * 0.3 = 0.24----- I P(E2) * P (A/E2)= 0.2 * 0.95 = 0.19 ----- II Since I > II, it is more likely that the fire took place because of short circuit.
The probability that a person stopping at gas station will ask to have his tyres checked is 0.12, the probability that he will ask to have his oil checked is 0.29 and the probability that he will ask to have them both checked is 0.07 (a) what is the probability that a person stopping at gas station will have either his oil or tyre checked? (b) that a person who has checked his tyres will also check his oil? (c) that a person who has checked his oil will aso get the tyres checked?
Probabilty: S C Agarkar, BRIMS 16-08-2013 45
P(A)=0.12, P(B)= 0.29 P(AB)= 0.07 P(AorB)= P(A)+P(B)-P (AB) P(A/B)= P(AB)/P(A) P(B/A)= P(AB)/P(B)
16-08-2013
46
Start
Are events mutually exclusive ?
No
Yes
Addition rule: P(A Or B) = P(A) + P(B)
No
The marginal probability of event A occurring is the sum of the probabilities of all joint events in which A occurs
Yes
The marginal probability of event A occurring is P(A)
The joint probability of two events occurring together or in succession is P(BA) = P(B\A) * P(A)
The joint probability of two events occurring together or in succession is P(AB) =P(A)*P(B)
The conditional probability of one event occurring given that another has already occurred is P(B\A) =P(B)
The conditional probability of one event occurring given that another has already occurred is P(B\A) = P(BA)/P(A)