Statistics_Chapter 3_Lecture 7 4/11/2023 CONTENTS LECTURE 7 Chapter 3 - Introduction to Probability (Events, Sample spaces, probability; Unions and intersections; Conditional Probability) Chapter 4 - Probability Distributions (Types of Variables, The Normal Distribution, The Binomial Distribution) Chapter 5 – Inferences Based on a Single Sample: Estimation with Confidence Intervals (Large-sample confidence interval for population mean, Small-sample confidence interval for population mean, Large-sample confidence interval for population proportion, Sample size) Chapter 6 – Inferences Based on a Single Sample: Hypothesis Testing (Large-sample test of hypothesis about a population mean, p-values, Small-sample test of hypothesis about a population mean, Large-sample test of hypothesis about a population proportion) Chapter 7 – Inferences Based on Two Samples: Confidence Intervals and Tests of Hypotheses (Target parameter, Comparing two population means, Comparing two population proportions, Sample size) Chapter 8 - Analysis of Variance (ANOVA) 1 1 Chapter 3 - Introduction to Probability 2 prof. dr. Laura Asandului 1 Statistics_Chapter 3_Lecture 7 4/11/2023 3. Introduction to Probability By the end of this chapter, you will be able to . . . 1 Understand the meaning of an experiment, an outcome, an event, and a sample space. 2 Describe the classical method of assigning probability. 3 Explain the Law of Large Numbers and the relative frequency method of assigning probability. Sometimes, the amount of uncertainty in our daily lives is so great that there appears to be no order to the world whatsoever. However, if you look closely, there are patterns in randomness. In this chapter, we learn to become better decision-makers by becoming acquainted with the tools of probability in order to quantify many of the uncertainties of everyday life. 3 3. Introduction to Probability We try to cope with uncertainty by estimating the chances that a particular event will occur. We are daily called on to make intelligent decisions about probabilities. Consider the following scenarios and think about how the italicized words all refer to uncertainty: • What is the chance that there will be a speed trap on this stretch of A7 on a particular day? • What is the likelihood that this lottery ticket will make me rich? • What is the probability that this throw of the dice will come up a six? 4 prof. dr. Laura Asandului 2 Statistics_Chapter 3_Lecture 7 4/11/2023 Chapter 3 - Introduction to Probability 1. Most managerial decisions are made in the face of some uncertainty regarding the possible consequences of these decisions. The decision-maker is unsure of the outcome. Determining the chances of the various possible outcomes occurring in advance should help in making the correct decision. 2. Probability is a measure of uncertainty. 3. Probability theory deals with predicting how likely it is that something will happen. 5 3.1 Experiment, Sample Space, Event 1. Experiment In probability, an experiment is any activity for which the outcome is uncertain. An outcome is the result of a single performance of an experiment. Consider the stock market, for example. Suppose you own 100 shares of Consolidated Widgets and are interested in the share price at the end of trading tomorrow. Will the share price increase or decrease? The actual result is uncertain. 2. Sample point is the outcome of an experiment 3. Sample space (S) is the collection of all possible outcomes of a random experiment 4. Event (E) – any subset of outcomes from the sample space © 2011 Pearson Education, Inc 6 prof. dr. Laura Asandului 3 Statistics_Chapter 3_Lecture 7 4/11/2023 3.1 Experiment, Sample Space, Event Examples Experiment Sample Space • Toss a Coin {Head, Tail} • Toss 2 Coins {HH, HT, TH, TT} • Play a Football Game {Win, Lose, Tie} • Quality control check {Defective, Good} • Observe Gender {Male, Female} Note: H – Head; T - Tail © 2011 Pearson Education, Inc 7 3.1 Experiment, Sample Space, Event Sample Space Properties 1. Experiment: Observe Gender Mutually Exclusive 2 outcomes can not occur at the same time — Male & Female in same person 2. Collectively Exhaustive One outcome in sample space must occur. — Male or Female © 2011 Pearson Education, Inc © 1984-1994 T/Maker Co. 8 prof. dr. Laura Asandului 4 Statistics_Chapter 3_Lecture 7 4/11/2023 3.1 Experiment, Sample Space, Event Examples Experiment: Toss 2 Coins Sample Space: HH, HT, TH, TT Event Outcomes in Event 1 Head & 1 Tail Head on 1st Coin At Least 1 Head Heads on Both HT, TH HH, HT HH, HT, TH HH Experiment: Roll a die Sample space: {1, 2, 3, 4, 5, 6} Event E: roll an even number = {2, 4, 6} Event L: roll a 4 or larger = {4, 5, 6} Note: H – Head; T - Tail 9 3.1 Experiment, Sample Space, Event Example Let the Sample Space be the collection of all possible outcomes of rolling one die: S = [1, 2, 3, 4, 5, 6] Let A be the event “Number rolled is even” Let B be the event “Number rolled is at least 4” Then A = [2, 4, 6] and B = [4, 5, 6] Copyright © 2013 Pearson Education 10 prof. dr. Laura Asandului 5 Statistics_Chapter 3_Lecture 7 4/11/2023 3.2 Probability The probability of an outcome represents the chance or likelihood that the outcome will occur. 1. Numerical measure of the likelihood that an event will occur is denoted 1 Certain P(Event) or P(A) 2. pi represents the probability of sample point i. All sample point probabilities must lie between 0 and 1, inclusive (0 ≤ pi ≤ 1). 3. .5 Sum of sample points is 1. The probabilities of all sample points within a sample space must sum to 1 ( pi = 1). 0 Impossible 11 3.2 Probability There are three approaches to assessing the probability of an uncertain event: 1. Classical method of assigning probability 2. Relative frequency method 3. Subjective method 12 prof. dr. Laura Asandului 6 Statistics_Chapter 3_Lecture 7 4/11/2023 3.2 Probability 3.2.1Classical Probability Assumes all outcomes in the sample space are equally likely to occur. Equally likely outcomes are outcomes that have the same probability of occurring. For example, if you toss a fair coin, the probability of observing either of the outcomes’ heads or tails is the same. The classical method of assigning probabilities is used when an experiment has equally likely outcomes. Classical probability of event A: P(A) = N number of outcomes in event A = N total number of outcomes in the sample space 13 3.2 Probability 3.2.1Classical Probability Example: The object of a game is to roll a 6 on a single roll of a single fair die. If you do so, you win $5. It costs $1 to play the game. What is the probability of winning? Solution The sample space for a single die toss consists of six outcomes, {1, 2, 3, 4, 5, 6}. When the six outcomes are equally likely, we say that the die is fair. If the outcomes are not equally likely, then the die is loaded or defective. If we assume the die is fair, then, since the sum of the probabilities of the n = 6 outcomes must equal 1, the probability of any particular outcome must equal 1/6, using the classical method. The probability of winning: P(W ) = 1/6 P A = number of outcomes in event A 1 = total number of outcomes in the sample space 6 14 prof. dr. Laura Asandului 7 Statistics_Chapter 3_Lecture 7 4/11/2023 3.2 Probability 3.2.1Classical Probability Example: Find the probability of obtaining one head and one tail when a fair coin is tossed twice. Solution We assume that the N(S ) = 4 outcomes in the sample space {HH, HT, TH, TT} are equally likely. Recall that the sum of the probabilities of all the outcomes in the sample space must equal 1. Thus, each of the four outcomes must have a probability of 1/4. Let E be the event that one head and one tail is obtained. Then E = {HT, TH}, so N(E ) = 2. Thus, P A = N number of outcomes in event A 2 1 = = = N total number of outcomes in the sample space 4 2 15 3.2 Probability 3.2.1Classical Probability Counting the Possible Outcomes • Use the Combinations formula to determine the number of combinations of n items taken k at a time; • The number of combinations of k objects chosen from n is the number of possible selections that can be made Cnk • where n! k! (n k)! • n! = n(n-1)(n-2)…(1) • 0! = 1 by definition 16 prof. dr. Laura Asandului 8 Statistics_Chapter 3_Lecture 7 4/11/2023 Example (continued) Suppose that two letters are to be selected from A, B, C, D. How many combinations are possible (i.e., order is not important)? • Solution The number of combinations is C 24 4! 6 2! (4 2)! The combinations are AB (same as BA) BC (same as CB) AC (same as CA) BD (same as DB) AD (same as DA) CD (same as DC) Copyright © 2013 Pearson Education 17 3.2 Probability Law of Large Numbers As the number of times that an experiment is repeated increases, the relative frequency (proportion) of a particular outcome tends to approach the probability of the outcome. • For quantitative data, as the number of times that an experiment is repeated increases, the mean of the outcomes tends to approach the population mean. • For categorical (qualitative) data, as the number of times that an experiment is repeated increases, the proportion of times a particular outcome occurs tends to approach the population proportion. 18 prof. dr. Laura Asandului 9 Statistics_Chapter 3_Lecture 7 4/11/2023 3.2 Probability 3.2.2 Relative frequency probability If we can’t use the classical method for assigning probabilities, then the Law of Large Numbers gives us a hint about how we can estimate the probability of an event. Relative frequency can be used to estimate the probability of the event. The probability of event A is approximately equal to the relative frequency of event A. P(A) = n frequency of event A = n total number of events 3.2.3 Subjective probability refers to the assignment of a probability value to an outcome based on personal judgment. There are cases where the outcomes are not equally likely (so the classical method does not apply) and there has been no previous research (so the relative frequency approach does not apply). The subjective method should be used when the event is not repeatable. 19 3.2 Probability 3.2.2 Relative frequency probability Example: A recent study found that 35% of all online teen girls are bloggers, compared to 20% of online teen boys. Suppose that the 35% came from a random sample of 100 teen girls who use the Internet, 35 of whom are bloggers. If we choose one teen girl at random, find the probability that she is a blogger. Solution: Define the event. Event B: The online girl is a blogger. We use the relative frequency method to find the probability of event B: P(B) = = event = total number of events = 35% 20 prof. dr. Laura Asandului 10 Statistics_Chapter 3_Lecture 7 4/11/2023 3.3 Unions & Intersections Compound events: Composition of two or more other events. Can be formed in two different ways. 1. Union • Outcomes in either events A or B or both • ‘OR’ statement • Denoted by symbol (i.e., A B) 2. Intersection • Outcomes in both events A and B • ‘AND’ statement • Denoted by symbol (i.e., A B) © 2011 Pearson Education, Inc 21 3.3 Unions & Intersections • Union of Events – If A and B are two events in a sample space S, then the union, A U B, is the set of all outcomes in S that belong to either A or B. • Venn diagram S A B The entire shaded area represents AUB Copyright © 2013 Pearson Education 22 prof. dr. Laura Asandului 11 Statistics_Chapter 3_Lecture 7 4/11/2023 3.3 Unions & Intersections Examples • S = {1,2,3,4,5,6} • E = {1,3,5} • F = {1,2,3} E U F = {1,2,3,5} • A = {H} • B = {T} A U B = {H, T} 23 3.3 Unions & Intersections • Intersection of Events – If A and B are two events in a sample space S, then the intersection, A ∩ B, is the set of all outcomes in S that belong to both A and B. • Venn diagram S A AB B Copyright © 2013 Pearson Education 24 prof. dr. Laura Asandului 12 Statistics_Chapter 3_Lecture 7 4/11/2023 3.3 Unions & Intersections • Two events are said to be mutually exclusive if the events have no outcomes in common, events that do not occur simultaneously. Two events are mutually exclusive if, when one event occurs, the other cannot occur. • Two events are mutually exclusive if, when one event occurs, the other cannot occur. • Mutually Exclusive Events are also said to be Disjoint Events (i.e., the set A ∩ B is empty) Sample Space S Event A Event B 25 3.3 Unions & Intersections Example S = [1, 2, 3, 4, 5, 6] A = [2, 4, 6] B = [4, 5, 6] • Mutually exclusive: • A and B are not mutually exclusive • The outcomes 4 and 6 are common to both • Collectively exhaustive: • A and B are not collectively exhaustive • A U B does not contain 1 or 3 Copyright © 2013 Pearson Education 26 prof. dr. Laura Asandului 13 Statistics_Chapter 3_Lecture 7 4/11/2023 3.3 Unions & Intersections Example: 1. P(A) = 6/10 2. P(D) = 5/10 3. P(C B) = 1/10 4. P(A D) = 9/10 5. P(B D) = 3/10 Event A Event C D 4 2 Total 6 B 1 3 4 Total 5 5 10 © 2011 Pearson Education, Inc 27 Event Probability Using Two–Way Table (2x2 Table) Event Event B1 B2 Total A1 P(A 1 B1) P(A 1 B 2) P(A 1) A2 P(A 2 B1) P(A 2 B 2) P(A 2) Total Joint Probability P(B 1) P(B 2) 1 Marginal (Simple) Probability © 2011 Pearson Education, Inc 28 prof. dr. Laura Asandului 14 Statistics_Chapter 3_Lecture 7 4/11/2023 3.4 Complementary Events Complement of Event A • The event that A does not occur • All events not in A • Denote complement of A by AC or 𝑨 The sum of the probabilities of complementary events equals 1: A P(A) + P(AC) = 1 AC S © 2011 Pearson Education, Inc 29 3.4 Complementary Events Example S = [1, 2, 3, 4, 5, 6] A = [2, 4, 6] B = [4, 5, 6] Complements: A = [1, 3, 5] B = [1, 2, 3] Intersections: A ∩ B = [4, 6] Unions: A ∩ B = [5] A ∪ B = [2, 4, 5, 6] A ∪ A = [1, 2, 3, 4, 5, 6] = S Copyright © 2013 Pearson Education 30 prof. dr. Laura Asandului 15 Statistics_Chapter 3_Lecture 7 4/11/2023 3.5 The Additive Rule 1. Used to get compound probabilities for union of events 2. P(A OR B) = P(A B) = P(A) + P(B) – P(A B) 3. If events A and B are mutually exclusive, P(A B) = 0. The additive rule (addition law) for mutually exclusive events is: P(A OR B) = P(A B) = P(A) + P(B) P(A or B or C) = P(A) + P(B) + P(C) © 2011 Pearson Education, Inc 31 3.5 The Additive Rule Example: Using the additive rule, the probabilities are: 1. P(A D) = P(A) + P(D) – P(A D) = = 6 5 2 9 + – = 10 10 10 10 2. P(B C) = P(B) + P(C) – P(B C) = Event A Event C D 4 2 Total 6 B 1 3 4 Total 5 5 10 4 5 1 8 + – = 10 10 10 10 © 2011 Pearson Education, Inc 32 prof. dr. Laura Asandului 16 Statistics_Chapter 3_Lecture 7 4/11/2023 3.6 Conditional Probability • Partial knowledge about the outcome of an experiment • Probability that the share price of IBM increased today? • Dow Jones Industrial Average rose 20 points • Conditional probability that the price of IBM share increased, given that the DJIA rose 20 points? For two related events A and B, the probability of B given A is called a conditional probability and denoted P(B u A). Conditional probabilities can often be interpreted as percentages of some subset of a population. For example, the conditional probability that a customer responded, given that the customer has a credit card on file, may be interpreted as the percentage of customers with credit cards who responded. 33 3.6 Conditional Probability The probability of an event given that another event has occurred is called a conditional probability. The conditional probability of A given B is denoted by P(A|B). A conditional probability is computed as follows : P(A | B) = P(A and B) = P(A B) P(B) P(B) 34 prof. dr. Laura Asandului 17 Statistics_Chapter 3_Lecture 7 4/11/2023 3.6 Conditional Probability Example: Using the table then the formula, what’s the probability? P C B ) P C B ) 110 1 4 P B ) 4 10 Event A Event C D 4 2 Total 6 B 1 3 4 Total 5 5 10 © 2011 Pearson Education, Inc 35 3.6 Conditional Probability Event M = Marrley Oil Profitable Event C = Cullins Mining Profitable P(C | M ) = Cullins Mining Profitable given Marrley Oil Profitable We know: P(M C) = 0.36, P(M) = 0.70 Thus: 𝑃(𝐶|𝑀) = 𝑃(𝐶 ∩ 𝑀) 0.36 = = 0.5143 𝑃(𝑀) 0.70 36 prof. dr. Laura Asandului 18 Statistics_Chapter 3_Lecture 7 4/11/2023 3.7 Multiplication Rule 1. Used to get compound probabilities for the intersection of events 2. The rule is written as: P(A and B) = P(A B) = P(A) P(B|A) = P(B) P(A|B) 3. For Independent Events: P(A and B) = P(A B) = P(A) P(B) © 2011 Pearson Education, Inc 37 3.7 Multiplication Rule Example: Using the multiplicative rule, the probabilities are: P C B ) P C ) P B C ) P B D ) P B ) P D B ) 5 1 1 10 5 10 4 3 6 10 5 25 P A B ) P A ) P B A ) 0 Event A Event C D 4 2 Total 6 B 1 3 4 Total 5 5 10 © 2011 Pearson Education, Inc 38 prof. dr. Laura Asandului 19 Statistics_Chapter 3_Lecture 7 4/11/2023 Independent Events Since having a credit card increased the probability of a customer responding from 0.1667 to 0.2818, we can therefore say that the probability of responding depends in part on whether the customer has a credit card. In other words, events R and C are dependent events. On the other hand, if the probability of responding had been unaffected by whether the customer had a credit card, then we would have said that R and C were independent events. That is, R and C would have been independent events had P(R | C ) equaled P(R ). In general, if the occurrence of an event does not affect the probability of a second event, then the two events are independent. 39 Independent Events If the probability of event A is not changed by the existence of event B, we would say that events A and B are independent. Two events A and B are independent if: P(A|B) = P(A) P(A B) = P(A) P(B) or P(B|A) = P(B) Tests for independence 40 prof. dr. Laura Asandului 20 Statistics_Chapter 3_Lecture 7 4/11/2023 Example Keep Kool Inc. manufactures window air conditioners in both a deluxe model and a standard model. An auditor collected 200 invoices for a month, some of which were sent to wholesalers and the remainder to retailers. Of the 140 retail invoices, 28 are for the standard model. Of the wholesale invoices, 24 are for the standard model. Find the following probabilities: a. The invoice selected is for the deluxe model. b. The invoice selected is a wholesale invoice for the deluxe model. c. The invoice selected is either a wholesale invoice or an invoice for the standard model. 41 Solution Display the data in a cross-classification table: MODEL Wholesale (W) Retail (R) Total Deluxe (D) 36 112 148 Standard (S) 24 28 52 Total 60 140 200 The sample space consists of 200 invoices. The events of interest are as follows: W: Wholesale invoice is selected R: Retail invoice is selected D: Invoice for the deluxe model is selected S: Invoice for the standard model is selected 42 prof. dr. Laura Asandului 21 Statistics_Chapter 3_Lecture 7 4/11/2023 Solution a. The invoice selected is for the deluxe model. • Each invoice has the same chance of being selected, therefore the probability that any particular invoice will be selected is 1/200. • There are 148 invoices for the deluxe model • 𝑃 𝐷 = event D contains 148 simple events. = 0.74 • The events of interest are as follows: W: Wholesale invoice is selected R: Retail invoice is selected D: Invoice for the deluxe model is selected S: Invoice for the standard model is selected MODEL Wholesale (W) Retail (R) Total Deluxe (D) 36 112 148 Standard (S) 24 28 52 Total 60 140 200 43 Solution b.. The invoice selected is a wholesale invoice for the deluxe model • There are 36 wholesale invoices for the deluxe model • 𝑃 𝐷∩𝑊 = the event 𝐷 ∩ 𝑊 contains 36 simple events. = 0.18 • The events of interest are as follows: W: Wholesale invoice is selected R: Retail invoice is selected D: Invoice for the deluxe model is selected S: Invoice for the standard model is selected MODEL Wholesale (W) Retail (R) Total Deluxe (D) 36 112 148 Standard (S) 24 28 52 Total 60 140 200 44 prof. dr. Laura Asandului 22 Statistics_Chapter 3_Lecture 7 4/11/2023 Solution c. The invoice selected is either a wholesale invoice or an invoice for the standard model • The number of invoices that are either wholesale invoices or invoices for the standard model is 36 + 24 + 28 = 88 • The event 𝑊 ∪ 𝑆 contains 88 simple events. = 0.44 • 𝑃 𝑊∪𝑆 = • The events of interest are as follows: W: Wholesale invoice is selected R: Retail invoice is selected D: Invoice for the deluxe model is selected S: Invoice for the standard model is selected MODEL Wholesale (W) Retail (R) Total Deluxe (D) 36 112 148 Standard (S) 24 28 52 Total 60 140 200 45 Example • Suppose that the invoice selected by the auditor is a wholesale invoice (W). • We may determine the probability that this invoice is for the deluxe model (D), making use of the knowledge that it is a wholesale invoice. In other words, we are seeking the MODEL Wholesale (W) Retail (R) Total Deluxe (D) 36 112 148 Standard (S) 24 28 52 Total 60 140 200 conditional probability that D will occur, given that W occurred (P(D|W)). • Wholesale invoice was selected restricts our inquiry to the first column; the size of the sample space is now 60 simple events. • P(D|W) = • P(D|W) = = . . = = 0.60 ( ∩ ) ( ) = 0.60 Joint probabilities MODEL Wholesale (W) Retail (R) Total Deluxe (D) 0.18 0.56 0.74 Standard (S) 0.12 0.14 0.26 Total 0.30 0.70 1.00 Marginal probabilities Marginal probabilities 46 prof. dr. Laura Asandului 23 Statistics_Chapter 3_Lecture 7 4/11/2023 Dependent events Example P(D) = 0.74 P(D|W) = 0.60 P(D) ≠ P(D|W) 47 Example Event M = Marrley Oil Profitable Event C = Cullins Mining Profitable M C = Marrley Oil Profitable or Cullins Mining Profitable We know: P(M) = 0.70, P(C) = 0.48, P(M C) = 0.36 Thus: P(M C) = P(M) + P(C) P(M C) = 0.70 + 0.48 0.36 = 0.82 48 prof. dr. Laura Asandului 24 Statistics_Chapter 3_Lecture 7 4/11/2023 Example Event M = Marrley Oil Profitable Event C = Cullins Mining Profitable M C = Marrley Oil Profitable and Cullins Mining Profitable We know: P(M) = 0.70, P(C|M) = 0.5143 Thus: P(M C) = P(M)P(M|C) = (0.70)(0.5143) = 0.36 49 Multiplication Rule for Independent Events Event M = Marrley Oil Profitable Event C = Cullins Mining Profitable Are events M and C independent? DoesP(M C) = P(M)P(C) ? We know: P(M C) = 0.36, P(M) = 0.70, P(C) = 0.48 But: P(M)P(C) = (0.70)(0.48) = 0.34, not 0.36 Hence: M and C are not independent. 50 prof. dr. Laura Asandului 25 Statistics_Chapter 3_Lecture 7 4/11/2023 Type of Compound Event Union (A or B) Mutually Exclusive P(A or B) = P(A B) = P(A) + P(B) Intersection Complementary (A and B) (not A) Not Mutually Exclusive Independent P(A or B) = P(A and B) = P(A B) = P(A) + P(A B) = P(A) P(B) P(B) – P(A B) Dependent P(A and B) = P(A B)= P(A) P(B|A) = P(B) P(A|B) P(A) + P(AC) = 1 Conditional (A given B) Independent P(A | B) = P(A) Dependent P(A | B) = P(A and B) P(B) = P(A B) P(B) 51 Example A CONTINGENCY TABLE is a table used to classify sample observations according to two or more identifiable characteristics E.g. A survey of 150 adults classified each as to gender and the number of movies attended last month. Each respondent is classified according to two criteria—the number of movies attended and gender. 52 prof. dr. Laura Asandului 26 Statistics_Chapter 3_Lecture 7 4/11/2023 What is the probability of randomly selecting a male person P(B1)? 1. 2. 3. 4. 5. 70/150 80/150 60/150 20/150 70/80 Answer Now 53 What is the probability of randomly selecting a person who would have seen 2 movies (A3) and was male (B1)? 1. 2. 3. 4. 5. 20/150 10/20 10/150 20/10 10/70 Answer Now 54 prof. dr. Laura Asandului 27 Statistics_Chapter 3_Lecture 7 4/11/2023 Example 1) What is the probability of randomly selecting a person who would have seen 2 movies (A3) and was male (B1)? 20 10 10 P A3 B1 ) P A3 )PB1 | A 3 ) 0.06(6) 150 20 150 55 Example 1) What is the probability of randomly selecting a person who would not have seen any movie (A1) and was female (B2)? 60 40 40 P A1 B2 ) P A1 )P B2 | A 1 ) 0.26(6) 150 60 150 2) What is the probability of randomly selecting a person who would not have seen any movie (A1) or was female (B2)? 60 80 40 P A1 B2 ) P A1 ) PB2 ) P A1 B2 ) 0.66(6) 150 150 150 56 prof. dr. Laura Asandului 28 Statistics_Chapter 3_Lecture 7 4/11/2023 57 prof. dr. Laura Asandului 29