Chapter 05 Probability Dr. Halil İbrahim CEBECİ Statistics Lecture Notes Assigning Probability to Events Key components of the statistical inference process is probability because it provides the link between sample and population. Random Experiment: An action or process that leads to one of several possible outcomes E.g. Flip a coin (Heads and Tails), Record student evaluations of a course (poor, fair, good, very good, excellent) Statistics Lecture Notes – Chapter 05 Assigning Probability to Events Sample Space: A sample space of a random experiment is a list of all possible outcomes of the experiment. The outcomes must be exhaustive and Mutually exclusive All the possible outcomes must be included (exhaustive) No two outcomes can occur at the same time (Mutually exclusive) 𝑆𝑎𝑚𝑝𝑙𝑒 𝑠𝑝𝑎𝑐𝑒 = 𝑆 = 𝑂1 , 𝑂2 , … , 𝑂𝑘 Statistics Lecture Notes – Chapter 05 Assigning Probability to Events Requirements of probebilities: Given a 𝑆𝑎𝑚𝑝𝑙𝑒 𝑠𝑝𝑎𝑐𝑒 = 𝑆 = 𝑂1 , 𝑂2 , … , 𝑂𝑘 , the probabilities assigned to the outcomes must satisfy two requirements: 1. The Probability of any outcome must lie between 0 and 1. That is , 0 ≤ 𝑃 𝑂𝑖 ≤ 1 for each 𝑖 2.The sum of the probabilities of all the outcomes in a sample space must be 1. That is, 𝑘 𝑃 𝑂𝑖 = 1 𝑖=1 Statistics Lecture Notes – Chapter 05 Approaches to Assigning Probabilities Event: An event is a collection or set of one or more simple events is a sample space. E.g. Achieve grade of A (𝐴 = 80, 81, 82, … , 99,100 ) Probability of events: Sum of the probabilities of the simple events that constitute the event. Ex5.1 – Probabilities of the courses grade are 𝑃 𝐴 = 0.2, 𝑃 𝐵 = 0.3, 𝑃 𝐶 = 0.25, 𝑃 𝐷 = 0.15, 𝑃 𝐹 = 0,1 Probability of the event, pass the course, is 𝑃 𝑃𝑎𝑠𝑠 𝑡ℎ𝑒 𝑐𝑜𝑢𝑟𝑠 = 𝑃 𝐴 + 𝑃 𝐵 + 𝑃 𝐶 + 𝑃 𝐷 = 0.90 Statistics Lecture Notes – Chapter 05 Interpreting Probability One way to interpret probability is this: If a random experiment is repeated an infinite number of times, the relative frequency for any given outcome is the probability of this outcome. For example, the probability of heads in flip of a balanced coin is .5, determined using the classical approach. The probability is interpreted as being the long-term relative frequency of heads if the coin is flipped an infinite number of times. Statistics Lecture Notes – Chapter 05 Joint Probability (Intersection) Joint probability is the probability that two events will occur simultaneously. (Intersection of Events A and B is the event that occurs when both A and B occur.) Ex5.2 – Suppose that a potential investor examined the relationship between how well the mutual fund performs and where the fun manager earned his or her MBA. Analyze the probabilities given below and interpret the results. Mutual Fund Outperforms Market Mutual Fund does not Outperforms Market Top 20 MBA Programs 0.11 0.29 Not Top 20 MBA Programs 0.06 0.54 Statistics Lecture Notes – Chapter 05 Joint Probability (Intersection) A5.2 – Evens notaion presented below. 𝐴1 = 𝐹𝑢𝑛𝑑 𝑚𝑎𝑛𝑎𝑔𝑒𝑟 𝑔𝑟𝑎𝑑𝑢𝑎𝑡𝑒𝑑 𝑓𝑟𝑜𝑚 𝑡𝑜𝑝 20 𝑀𝐵𝐴 𝑝𝑟𝑜𝑔𝑟𝑎𝑚 𝐴2 = 𝐹𝑢𝑛𝑑 𝑚𝑎𝑛𝑎𝑔𝑒𝑟 𝑑𝑖𝑑 𝑛𝑜𝑡 𝑔𝑟𝑎𝑑𝑢𝑎𝑡 𝑓𝑟𝑜𝑚 𝑡𝑜𝑝 20 𝑀𝐵𝐴 𝑝𝑟𝑜𝑔𝑟𝑎𝑚 𝐵1 = 𝐹𝑢𝑛𝑑 𝑜𝑢𝑡𝑝𝑒𝑟𝑓𝑜𝑟𝑚 𝑡ℎ𝑒 𝑚𝑎𝑟𝑘𝑒𝑡 𝐵2 = 𝐹𝑢𝑛𝑑 𝑑𝑜𝑒𝑠 𝑛𝑜𝑡 𝑜𝑢𝑡𝑝𝑒𝑟𝑓𝑜𝑟𝑚 𝑡ℎ𝑒 𝑚𝑎𝑟𝑘𝑒𝑡 Joint probabilities are; 𝑃 𝑃 𝑃 𝑃 𝐴1 𝑎𝑛𝑑 𝐵1 𝐴2 𝑎𝑛𝑑 𝐵1 𝐴1 𝑎𝑛𝑑 𝐵2 𝐴2 𝑎𝑛𝑑 𝐵2 Statistics Lecture Notes – Chapter 05 = 0.11 = 0.06 = 0.29 = 0.54 Marginal Probability Marginal probability is the probability of the occurrence of the single event Mutual Fund Outperforms Market Mutual Fund does not Outperforms Market Totals Top 20 MBA Programs 𝑃 𝐴1 𝑎𝑛𝑑 𝐵1 = 0.11 𝑃 𝐴1 𝑎𝑛𝑑 𝐵2 = 0.29 𝑃 𝐴1 = 0.40 Not Top 20 MBA Programs 𝑃 𝐴2 𝑎𝑛𝑑 𝐵1 = 0.06 𝑃 𝐴2 𝑎𝑛𝑑 𝐵2 = 0.54 𝑃 𝐴2 = 0.60 𝑃 𝐵1 = 0.06 𝑃 𝐵2 = 0.06 Totals Marginal Probablilites Statistics Lecture Notes – Chapter 05 Conditional Probability Conditional probability is used to determine how two events are related; that is, we can determine the probability of one event given the occurrence of another related event. Conditional probabilities are written as 𝑷(𝑨 | 𝑩) and read as “the probability of event A given event B” and is calculated as: 𝑃(𝐴 𝑎𝑛𝑑 𝐵) 𝑃 𝐴𝐵 = 𝑃(𝐵) Statistics Lecture Notes – Chapter 05 Conditional Probability Ex5.3 - The Dean of the School of Business at Owens University collected the following information about undergraduate students in her college: Male Female Totals Accounting 170 110 280 Finance 120 100 220 Marketing 160 70 230 Management 150 120 270 Totals 600 400 1000 Given that the student is a female, what is the probability that she is an accounting major? Statistics Lecture Notes – Chapter 05 Conditional Probability A5.3 – Random experiment given below 𝐴: 𝑆𝑡𝑢𝑑𝑒𝑛𝑡 ′ 𝑠 𝑟𝑒𝑔𝑖𝑠𝑡𝑒𝑟𝑒𝑑 𝑎𝑡 𝐴𝑐𝑐𝑜𝑢𝑛𝑡𝑖𝑛𝑔 𝑀𝑎𝑗𝑜𝑟 𝐹: 𝑆𝑡𝑢𝑑𝑒𝑛𝑡𝑠 𝑔𝑒𝑛𝑑𝑒𝑟 𝑃(𝐴 𝑣𝑒 𝐹) 110 1000 𝑃 𝐴𝐹 = = = 0.275 400 𝑃(𝐹) 1000 Statistics Lecture Notes – Chapter 05 Independence One of the objectives of calculating conditional probability is to determine whether two events are related. In particular, we would like to know whether they are independent, that is, if the probability of one event is not affected by the occurrence of the other event. Two events A and B are said to be independent 𝑃(𝐴|𝐵) = 𝑃(𝐴) 𝑃(𝐵|𝐴) = 𝑃(𝐵) Statistics Lecture Notes – Chapter 05 Independence Ex5.4 – Refer to table of Ex5.2, calculate probability of funds outperforms the market when the manager graduation probability is given. 𝑃 𝐴1 𝐵1 𝑃(𝐴1 𝑎𝑛𝑑 𝐵1 ) 0.11 = = = 0.647 𝑃(𝐵1 ) 0.17 The marginal probability that a manager graduated from a top-20 MBA program is 𝑃 𝐴1 = 0.40 Since the two probabilities are not equal, we conclude that the two events are dependent. Statistics Lecture Notes – Chapter 05 Union Another event that is the combination of other events is the union Union of Events 𝐴 and 𝐵 is the event that occurs when either 𝐴 or 𝐵 or both occur. Ex5.5 – Refer to table of Ex5.2, Determine the probability that a ramdomly selected fund outperforms the market or the manager graduated from a top-20 MBA programs. 𝑃 𝐴1 𝑜𝑟 𝐵1 = 𝑃 𝐴1 𝑎𝑛𝑑 𝐵1 + 𝑃 𝐴1 𝑎𝑛𝑑 𝐵2 + 𝑃 𝐴2 𝑎𝑛𝑑 𝐵1 𝑃 𝐴1 𝑜𝑟 𝐵1 = 0.11 + 0.06 + 0.29 = 0.46 Shortcut: 𝑃 𝐴1 𝑜𝑟 𝐵1 = 1 − 𝑃 𝐴2 𝑜𝑟 𝐵2 = 1 − 0.54 = 0.46 Statistics Lecture Notes – Chapter 05 Probability Rules and Trees Complemet Rule: The complement of an event A is the event that occurs when A does not occur. The complement rule gives us the probability of an event NOT occurring. That is: 𝑃(𝐴) = 1 – 𝑃(𝐴) For example, in the simple roll of a die, the probability of the number “1” being rolled is 1/6. The probability that some number other than “1” will be rolled is 1 – 1/6 = 5/6. Statistics Lecture Notes – Chapter 05 Probability Rules and Trees Multiplication Rule: The multiplication rule is used to calculate the joint probability of two events. It is based on the formula for conditional probability defined earlier: 𝑃(𝐴 𝑎𝑛𝑑 𝐵) 𝑃 𝐴𝐵 = 𝑃(𝐵) If we multiply both sides of the equation by 𝑃(𝐵) we have: 𝑃(𝐴 𝑎𝑛𝑑 𝐵) = 𝑃(𝐴 | 𝐵) ∗ 𝑃(𝐵) Likewise, 𝑃(𝐴 𝑎𝑛𝑑 𝐵) = 𝑃(𝐵 | 𝐴) ∗ 𝑃(𝐴) If A and B are independent events, then 𝑃 𝐴 𝑎𝑛𝑑 𝐵 = 𝑃 𝐴 ∗ 𝑃(𝐵) Statistics Lecture Notes – Chapter 05 Probability Rules and Trees Addition Rule: The Probability that event A, or event B, or both occur is 𝑃(𝐴 𝑜𝑟 𝐵) = 𝑃(𝐴) + 𝑃(𝐵) – 𝑃(𝐴 𝑎𝑛𝑑 𝐵) Why do we subtract the joint probability P(A and B) from the sum of the probabilities of A and B? 𝑃(𝐴 𝑜𝑟 𝐵) = 𝑃(𝐴) + 𝑃(𝐵) – 𝑃(𝐴 𝑎𝑛𝑑 𝐵) When two events are mutually exclusive Statistics Lecture Notes – Chapter 05 Probability Rules and Trees Probability Trees: An effective and simpler method of applying rules is the probability tree, wherein the events in an experiment are represented by lines. Ex5.6 – Student who graduate from law school must still pass a bar exam. First time test takers passes the exam with the ratio of 72%. Candidates who fail the first exam may take it again. Second time test takers passes with ratio of 88%. Find the probability that a randomly selected student Joint Probability becomes a lawyer. First Exam Pass 0.72 Second Exam Pass (0.72) 0.72 Pass 0.88 Fail and Pass (0.28*0.88) 0.2464 Fail 0.28 Fail 0.12 Statistics Lecture Notes – Chapter 05 Fail (0.28*0.12) 0.0336 Bayes’ Theorem Bayes’ Theorem is a method for revising a probability given additional information. P( A1 ) P( B / A1 ) P( A1 | B) P( A1 ) P( B / A1 ) P( A2 ) P( B / A2 ) Statistics Lecture Notes – Chapter 05 Bayes’ Theorem Ex5.7 - Duff Cola Company recently received several complaints that their bottles are under-filled. A complaint was received today but the production manager is unable to identify which of the two Springfield plants (A or B) filled this bottle. What is the probability that the under-filled bottle came from plant A? % of total production % of underfilled bottle A 55 3 B 45 4 Statistics Lecture Notes – Chapter 05 Bayes’ Theorem A5.7 - Duff Cola Company recently received several P ( A) P (U / A) P( A / U ) P ( A) P (U / A) P ( B ) P (U / B ) .55(.03) .4783 .55(.03) .45(.04) The likelihood the bottle was filled in Plant A is .4783. Statistics Lecture Notes – Chapter 05 Exercises Q5.1 - A manufacturing plant conducted a survey to determine its employees’ reactions toward a proposed change in working hours. A breakdown of the responses is shown in the following table: Reaction Work Area Agree Disagree Production 17 23 Office 8 2 Suppose an employee is chosen at random, with the relevant events being defined as follows: A: The employee works in production. B: The employee agrees with the proposed change. Express each of the following events in words, and find the probabilities a) 𝐴 b) (𝐴 𝑜𝑟 𝐵) Statistics Lecture Notes – Chapter 05 c) (𝐴 𝑎𝑛𝑑 𝐵) d) (𝐴 𝑜𝑟 𝐵 ) Exercises Q5.2 - A manufacturing plant conducted a survey to determine its employees’ reactions toward a proposed change in working hours. A breakdown of the responses is shown in the following table: Men Women Less than 2 years 28 26 2 years or more 82 64 One employee is selected at random, and two events are defined as follows: A: The employee is male. B: The employee has worked for the company for two years or more. find the following probabilities a) 𝐵 b) (𝐴 𝑜𝑟 𝐵) c) (𝐴 𝑎𝑛𝑑 𝐵) Statistics Lecture Notes – Chapter 05 d) (𝐴 𝑜𝑟 𝐵 ) Exercises Q5.3 - An accounting firm has advertised the availability of its report describing recent changes to the federal income tax act. The first 200 callers requesting a copy of the report are classified in the following table according to the medium by which the caller became aware of the report and the caller’s primary interest. Primary Interest Radio Newspaper Word of Mouth Personel Tax 34 20 26 Coorporate Tax 36 70 14 One caller is selected at random, and two events are: A: The caller is primarily interested in corporate tax. B: The caller became aware of the report through the newspaper. Express each of the following probabilities in words, and find its numerical value: a) 𝑃 𝐴 𝐵 b) 𝑃 𝐵 𝐴 c) 𝑃 𝐴 𝐵 d) 𝑃 𝐴 𝐵 Statistics Lecture Notes – Chapter 05 Exercises Q5.4 - A firm’s employees were surveyed to determine their feelings toward a new dental plan and a new life insurance plan. The results showed that 81% favored the insurance plan, while only 35% favored the dental plan. Of those who favored the insurance plan, 30% also favored the dental plan. a. What percentage of the employees favored both plans? b. What percentage of the employees favored at least one of the plans? Statistics Lecture Notes – Chapter 05 Exercises Q5.4 - Consider two events, A and B, for which 𝑃(𝐴) = 0.2, 𝑃(𝐵) = 0.6, and 𝑃(𝐴 𝑜𝑟 𝐵) = 0.68 a. Find 𝑃(𝐴 𝑎𝑛𝑑 𝐵) b. Are A and B independent events? c. Are A and B mutually exclusive events? Q5.5 - An electrical contractor has observed that 90% of his accounts are paid within 30 days. Of those that are not paid within 30 days, 40% remain unpaid after 60 days. If one account is selected at random, what is the probability that it is paid within 60 days? Q5.6 - A mechanic has removed six spark plugs from an engine and finds two to be defective. If two spark plugs are selected at random from among these six, what is the probability that exactly one of them is defective? Statistics Lecture Notes – Chapter 05