TABLE OF CONTENTS TOPIC Lesson I: PROBABILITY A. Concept of Probability 1. Classical or Priori Approach 2. Frequency or Posteriori Approach 3. Subjective Approach B. Combinational Analysis 1. Fundamental Principle of Counting 2. Permutation 3. Combination C. Axioms of Probability 1, Conditional Probability 2. Theorems on Conditional Probability 3. Independent Events 4. Baye’s Theorem Exercises Lesson If: DISCRETE PROBABILITY DISTRIBUTION A. Probability Distribution B. Types of Probability Distribution 1. Binomial Distribution 2. Hypergeometric Distribution 3. Poisson Distribution Exercises Lesson I: NORMAL DISTRIBUTION Definition Skewed Distribution Properties of Normal Curve ‘Areas Under Normal Curve . Applications xercises peepee p Lesson IV: SAMPLING THEORY A. Frequency Distribution B. Sampling Distributions 1, Sampling Distribution of Means 2. Sampling Distribution of Proportion 3. Sampling Distribution of Variances Exercises PAGE 10 ir 12 16 17 18 18 19 19 21 23 24 27 29 33Lesson V: TESTS OF HYPOTHESIS A. Statistical hypothesis - Null hypothesis B. Type I and Type II Errors C. Level of Significance D, One-tailed and Two-tailed Tests E. Steps in hypothesis — testing F. Special tests of significance for large samples - means; proportions; differences of mean; and differences in proportions G. Special tests of significance for small samples - means and difference of means Exercises Lesson VI: SIMPLE ANALYSIS OF VARIANCE (ANOVA) A. Definition B. Steps for One-way Analysis of Variance C. Example Problems Exercises Lesson VII: ANALYSIS OF ENUMERATION DATA ( CHI-SQUARE) A. Definition B. Classification of Enumeration Data 1. One-way Classification 2. Two-way Classification C. Uses of Chi-square D. Steps E. Example Problems Exercises Lesson VIII: SIMPLE REGRESSION AND CORRELATION ANALYSIS ‘A. Simple Regression Analysis B, Simple Correlation Analysis C. Example Problems Exercises REFERENCES an w a 42 43 45 0 a 57 ssWHAT THIS TEACHING GUIDE IS ABOUT ._., This teaching guide is written to assist the professor in teaching Probability and Statistics. This may be used as a guide for the whole semester but the professor has the option to widen the topic coverage depending upon the students’ capability. Students may use this as a study material but it is not recommended that this manuscript replace the role of a textbook. Probability and Statistics is one of the minor subject in BSME and BSEE. It covers probability theory; discrete and continuous distribution function; sampling theory; estimation; test of hypothesis; regression and correlation analysis; and analysis of variance. The topics contained in this teaching guide are the following: + Probability + Discrete Probability Distribution + Normal Distribution + Sampling Theory + Tests of Hypothesis + Simple Analysis of Variance (ANOVA) + Analysis of Enumeration Data ( CHI-SQUARE) + Simple Regression and Correlation AnalysisLESSOVL PROBABILITY Objective: ALthe end of the lesson, the student should be able to: explain the three conceptual approaches for defining probability. define different terms used in probability such us event, sample space and population. recognize the fundamental principle of counting, permutation & combination. 4. recall the 6 axioms of probability. 5. solve problems related to probability. 6. compute problems related to the different types of discrete probability distribution.PROBABILITY A The Ce \cept of Probability As u measure of the chance or probability with which we ean expect the event to occur nvenient to assign a number between 0 and 1. or 0 and 100%. 3 Conceptual Approaches for defining probability 1. Classical or a prio proach — If an event can occur in h different ways out of a {otal number of n possible ways all of which are equally likely or mutually exclusive, then the probability of the event is h/n. Example: In tossing a coin, the probability of obtaining a head is one out of two. By equally likely: The probability of getting a head is oy rable outi 1 P(1) = —RUMPEF of Favorable outcome total number of expected outcomes 2 it is con Note: equally likely means that he outcome permits the determination of probability values even before any sample events are observe. By mutually exclusive means that an occurrence of one event precludes the occurrence of the other event. s P(A)==- where: P(A) — probability of any event A S~ number of successful outcomes 2, Frequency or a posteriori approach. If afier n repetition of an experiment, where n is very large, an event is observe to occur in h of these, then the probability of the event is h/n This is also called empirical probability of the event. total number of favorable outcomes total number of cases P(success) = Example: If we toss a coin 1000 times and find that it comes up heads 532 times we estimate 532 the probability of a head to be jo00" 0.532. 3. Subjective Approach. If we determine the probability of an event by recalling previous experiences, available data on hand or degree of belief that a certain event. will or will not occur. This personal view of probability is based on analysis of Bayesian decision. Sample Space (S) refers to the set of all possible outcomes of a statistical process or experiment, An event is a subset A of the sample space S it is a set of possible outcomes. Example: Assume that the experiment involving tussing of two coins and recording the possible outcomes (S) by using a box diagram. E neice H_{T = event 1 where coin | is tossed PHA AT E2= event 2 where coin 2 is tossed & [trate $= (HH), (HT), (TH, (TT) Dy using the concept of Cartesian Product Let Ey ={UT} Fa = {UIT} S=E)x Ea = {(H), (HT), (TH), (TT)}‘imple: Assume that an experiment involves a survey of faculty of certain university with ‘epards their educational qualification, ‘The following questions are answered: 1. Age 5 [Under 30 over 10, 2. Sex (iy) 7 Mate C7) Femate 3. Educational Attainment (B3) [C]_ Battetor's Master's Doctor's Degree (i) Degree Degree nd Eto form the sample space (S). Use the Cartesian Product to the three sets Analysis: Define sets Ly, Ey and Ey as ={U,O} where: U = under 30 and O = over 30 ={M,F} where: M= male and c ={B.C, D)} where: B= bachelor’s degree, C = master’s degree, D= doctorate depree XTX Ey g Ia Ky UMB. UMC UMD UrB. ure uED OMB omc omD ° Orb ore orp TREE DIAGRAM rom the example, there are 12 possible outcomes. B, Combinational Analysis 1, Fundamental Principle of Counting If'an experiment consists of k separate steps and the first ‘step can oceur in 7, different ways, the second in madifferent ways, ... and the Ath in the m, different ways, then the number of different possible outcome of the experiment is... my... m Example: A car number plate contains 3 distinct letters followed by three none igi How many different car number plates can be printed? tice wane Analysis: The first letter can be printed in 26 different ways, the second letter i different ways, the third letter in 24 different ways, the first, second, and thind digit in 9 different ways (since duplication is possible). Hence 26 25.24.9.9.9= 11,372,400 different plates can be printed.2. Permutations inpose that we are given m distinet objects and wish to arrange r of these objects in a ince there are m ways of choosing the first object, and after this is done m1 ways of and finally m — r+! ways of choosing the rih objects, it follows iple of counting that the number of dilferent arrangement ot by the findamental pri permutations, Permutation — an orderly arrangement of n objects trom a set of # objects. a Permutation without ‘repetition The number of permutation of n objects taken r at a time is denoted by any of the following symbols: P(nr); nPr; Ph aredefinedas P(r) In particular case, where r= n, the number of permutations of ordering of n distinct object is P(n.n) = nt Example: whi ‘Count the three-letter computer code words that can be made from A, B, C, D and E litions are prohibited, Given: n= 5. r=3 Solution: P(5,3) = 6, Permutation with repetition ‘The number of distinct permutations of nm things of which ni of one kind, mz of @ second kind ....mofak" is Peon’) m where: n’ = ny, 2 My. Mare alike yng tng tary! Example: Form all possible 11 letter words using the word Philippin Given: n=11,m=3 p's »m=3i's ‘Solution: P(n.n') 1,108,800 letters Application of permutation Suppose we are concerned with choosing a ball from an urn, a card from the deck of cards or a sample from # population. When we choose one ball after another from the urn, say times, we call the choice an ordered sample of size r. Let us consider two cases: i) Sampling with replacement ‘The ball is replaced in the urn before the next ball is chosen, ways to choose each ball, then there are nee ne nae different ordered samples with replacement of size r. ‘These are the independent events where the occurrence of one event does not affect the occurrence of another event. ii) Sampling without replacement ‘The ball is not replaced in the um so that no repetition in the ordered sample is permitted. The ordered sample of size r without replacement is n(n-1)(n-2)..(1-T+1)! nt F000) Gen eH ince there are different different ordered sample of size without replacement from a population of objects. “There are dependent events since no repetition is permitted, thus the occurrence of the second event is determined by the occurrence of the first event. Example: In how many ways can we choose three balls in an um containing 10 balls? a) with replacement .) without replacement Solution: 4.) 10.10.10 = 10? of 1,000 different ordered samples of size 3 with replacement 4b) 10.9.8 = 720 different ordered samples of size 3 without replacement ‘The symbol #, read “nCe" i "or C(n.r) where r and n are positive integers and n> r is defined as CE) = Cone = MALDOrH2)0m-r1 noni anti i (oe) = aa een mle nCr read as “the combinations of'n things taken rata time (my =! e rir)! Suppose r =n, Bye Lt, % ni(n=n)! al In the ease of combination, we are not concemed with the order in which the objects are Brouped, se = 8 876 Example: (§) = —%_ 2(e-ay 2a 78 Example: i the number of ways in which 5 cards cun be chosen or seleeted from a total of 12 ji cards is 12.11.109..71 y= (12 y= BaLiose7 nes ( ) 5.4.3.2.471 792 C. Axioms of Probability Let $~ sample space B= the class of events P—real value A - probability function P(A) = the probability of event A A. - Forevery event A, 0< P(A) 1A; Ay ~ IFA and B are mutually exclusive events, then P(AU 18) = P(A) + PB). Au = IAL Ar. isa sequence of mutually exclusive events, then POAWU Az U Ag U 1 UAn ) = P(AI) © P(A2) P(Ag) F... PAg) Hy PAI) Aq. - ICA and B are not mutually exclusive, then P(AU B) = P(A) + PB) = PVA und B) As = IA and B are independent events, then P(A and B) = P(A 1B) = P(A) P(B) Ap = ICA and B are dependent events, then 0 Example: A ball is drawn at random from a box containing 6 red balls, 4 white balls and 5 blue balls. Determine the probability that is (a) red, (b) white, (c) blue, (d) not red (e) red or white. Solution: Let R, W and B denote the events of drawing a red ball, white ball and blue bal, respectively. OO ie 8.) POR) * ioral ways of choosing aball 64445 ces, b) POW)" Saas 35 Ss ©) PO) = Gyaes 15 d) PQnot red) = 1 ~ P(R) =red or white ball _6+4 0) re eI .. Ways of choosing red or whi . - 1 Mc or sa = Pena total ways of choosing a ball Gras Another solution: ) MRUW) = 1 p(B) = 1 b) Since events R and W are mutually exclusive it follows from (Ay) PQRUW) = PQR) + POW) = et Ad ‘cample: Determine the probability that a randomly chosen family have an annual household income (a) between P6,110 and P11,000 (b) less than or equal to P16,000 (c) at one of the extremes of | being less than P6,000 or at least P21,000. Given; Annual Household Income for $00 families Category Income Range (P) Number of Families ' less than 6,000 60 a 6,001 ~ 11,000 100 3 11,001 -~ 16,000 160 4 16,001 ~21,000 140 5 21,001 and above 40 ‘Total 500 Solution: The events are mutually exclusive. Take the probabilities with respect to categories. 100 Pe)" So0 = 92 60, 100 160 (b) PU oF 2 oF 3) = P(L) + PQ) + PG) =o + coe + Se = 0.12 + 0.20 +032 = 0.64 P = P(1)+P(5) = 52 + 40 = = (©) PC or 5)= PCI) 4 PS)= o> + = 0.12 + 0.08 = 0,20 Examp OF 100 individuals who applied for computer programming positions with a large n, 40 had prior work experience (W) and 30 had professional certificate (C). However, 20 of the applicants had both work experience and certificate, 4) Construct a Venn Diagram to portray these events. b) Find the probability that a randomly applicant has either work experience or a certificate (or both). the probability that the chosen applicant had either work experience or a jeate but not both. corti Solution: a) Venn Diagram b) P(WUC) = P(W) + P(C) = PWaC) “= + = e x = nos Note: the events are not mutually exclusive, ©) P(WUC, but not both) = P(WUC) - P(WnC) = 0.50-- 0.20 = 0.30'. Conditionat Probabitiyy Let A und B be two e rents such that P(A)>1, Denote by P(IVA) the probability of B ul ILA his occurred. to have ocet coor Pace replacing the ‘original faeeee nmclocenty een comer mee Deftition: MWA) “a Where: PAN B) called joint probability A and B. oF MA.01) © P(A) PBA) e are be Probability that both A and B vccur tye ea ; occured, * PCOVA) is called the conditional proba en A, ie. the probability that B will ‘ecur given that A has occurred, ind the probability that a single toss of a dic results in a number less than 4 if itis ._Biven that the toss resulted in an odd number. Solution: Let A be the event (odd number) B be the event (less than 4) raja! o2 PB)= PC) +ayePay=t+ 24 t= t P etal Man B)=2=2 , = Pani) Ya _2 roa)= y ; 2. Theorems on Conditional Probability A. For any three events Ai,A2,A3 PCAIMA2 MA 1) = P(A1) P(AdAI) P(AYAINA) ‘The probability that Ay and A 2and A 3 all occur is equal to the probability that A, occurs times the probability that Az occurs given that A; has occurred times the probability that Ay occurs given that both A; and A 2 had occurred, The resull is easily generalized to n events, B, Ian event A must result in one of the mutually exclusive events Ai, A3,A3,.-- + An then P(A) = P(A1) P(A/A,) + P(A2) PCA/A2) +... #P(Aa) P(A/An), 3. Independent Events If P(B/A) = P(B), i.e. the probability of B occurring is not affected by the ‘occurrence or non-occurrence of A, then we say that A and B are independent events. P(A NB) = P(A) P(B) IfAy,A2,A3 are to be independent then they must be pair wise independent, PALM AK= P(A) P(X) j#K where k= 1, 2,3 also POAL Aa As) = (AL) PCA) PCAs) Example: A fair die is tossed twice, Find the probability of getting a 4, 5 or 6 on the first toss ‘and w 1, 2,3 or 4 on the second (oss,Atlant Let Ay be the event “4, § oF 6" om the First to Ar be the event “1, 2, 3 oF 4" on the second toss, Solve P(AY A Ag)» MAY (since 4, 5, or 6 are 3 oul of 6 equally likely possibilities) MAYA) = P(g) (the result of the second loss is independent of the first) P(Ad) = 2 = = (since 1, 2,3 oF 4 are a out of 6 equally likely possibiliti MAL AAD) © PAY) PAYA = EXE 4 Bayes' Theorem Let Sis the union of the mutually exclusive events Aj where j= 1, 2,3, S©AUALUAIU..U Ay A ‘Ae AL SAMPLE SPACK ‘The shaded portion B is the intersection ob B and the sample space thus p B=(AJUAZUASU..UA) OB Using the distributive law B=(A\NB)U (ANB)... (Ag B) where: (Aj 0B) are mutually exclusive P(B) = PAIN B) + P(A2 NB) +... + P(g 8) Applying the mi tion theorem P(B) = P(A1) P(B/Ay) + P(Az ) PC B/Aa) +... + P(Ag) P(B/A,) ‘The conditional probability of A; given B is P(AjnB) peapey= Se P(B) + Bayes’ eh = _ PLA POa/A) a P(A))P(B/A\) Or hia P(Aj)P(B/Aj) PCAs) P(B/Ax) + P(Az ) P( B/Az ) +--+ P(An) P(B/An) Example: (na certain assembly plant, three machines, By, Ba, and By, make 30%, 45%, and 25% respectively, of the products, It is known from the past experience that 2%, 3%, tnd 2% of the products made by each machine, respectively are defective. Suppose that a finished product is randomly selected, what is the probability that is defective? Solution; Consider the following events: the product is defective 1B: the product is made by machine By Bz: the product is made by machine By By: the product is made by machine Bsates Ls tule of elimination; = P(Bi) P(A/B,) + P(B2 ) P(A/B ) + P(By) P(A/Ba) P(By) P(AVB)) = (0.3)(0.02) = 0.006 lee eM) 0.024 ry * 003 P(B2) P(AIB,) P(B3) P(A/B)) TREE DIAGRAM co the previous example, ia praduet were chosen randomly and ive, what is the probability that it is made by machine By? Example: With referer found to be dete Solution: Using Bayes’ Theorem: P(Bs)P(A/N3) P¢ByYA) = ————_P6)P Ais) __ OM) Sa PCATBaD PCBs YPCA/Ba) FPO) POAT) 0.005 PuByA) =———228S__ =. (BVA) = Couey aorss rons | "4 Example: Box 1 contains 3 red and 2 blue marbles while Box II contains 2 red and 8 blue marbles. A fair coin is tossed. If the coin tums up heads a marble is chosen from Box 1; if it (ums up tails a marble is chosen from Box Il. Find the probability that a red marble is chosen. Solution: Consider the following events: red marble is chosen Box is chosen Box Il is chosen POR) = PCL) PORE) + PCL) PORMID Hxample: With reference to the previous example, suppose that the one who tosses the o ‘does not reveal whether if hus turned up heads or tails (so that the box from which a marble was chosen is not revealed) but docs reveal that a red marble was chosen. What is the probability that Box I was chosen (ic. the coin turned up head)? Solution: Dts NeaG)Gn) * Exercises: 1) How many different committees of 3 men and 4 women ean be formed from 8 men and 6 women? 2) Um [has 2 white and 3 black balls; un Il, 4 white and 1 black; urn Il, 3 white and 4 black, An urn has selected at random and a ball drawn at random is found to be white. Find the probability that urn I was selected. 3) The probability that a man wil hit target is 2/3. Ihe shoots atthe target until he hits it forthe first time, find the probability that it will take 5 shoots.LESSON I, DISCRETE PROBABILITY DISTRIBUTION Objectives: AL the end of the lesson, the student should be able to: |. define random variable, discrete random variable and continuous random variable, | construct a probability distribution in tabular form. define and formulate the mean, variance & standard deviation of a probability distribution, le, |. define the expected value of a random vari . explain the types if discrete probability distribution. 10M. DISCRETE PROBABILITY DISTRIBUTION A random variable is w function that associates u real number with which each ‘clement in the sample space, I is usually denoted by a capital etter such as X or Y. Example: Suppose that a coin is tossed twice so that the sample space is Se (WH +HT+TH+TT). . Let X represents the number of heads which can come up. With cach sample point we ‘can assuelate a number for X as shown: Sample Point ~~ [WT] AT [7 re] x ay ‘A rundom variable is called DISCRETE RANDOM VARIABLE if its set of possible outcomes is countable. Example: number of defective bulbs number of children in a family number of heads that turned up in tossing a coin When a random variable can take one value on a continuous scale, it is called a CONTINUOUS RANDOM VARIABLE, In most practical problems these variable represent measured data, Example: heights, weights, temperature, distance, A. Probability Distribution Definition: Let X be a random variable on a sample space S with a X(8) = (Xi, X24 Xs, «++ Xn J. We can turn X(S) into a probability space by defining the probability of Xj to be P(X=X;) or (Xi). This function is called a Probability Function or Distribution of X. ‘he tabular form is Xr |X Xa FRX) | 1%) AX) which satisfies the conditions f (Xi) 2 0 and Zf (Xj) = 1. Example: A pair of fair dice is tossed, The equiprobable space $ had 36 pairs of numbers between | and 6. $= (11), (1.2)s (13) +» 6.6) ‘Then X is a random variable with an image set. X(S ‘The probability distribution fof X is computed as NU) = PERN = PCL) 2S 2) PER) = PCE, 112, 241 2) Z 113) = P(X=3) = PC(3, 1}, (3, 2}.43, 3}, 42s 3), 3) = MA) = P(X=4) = PCE4, 1,4, 2), 44, 39,64, 49,03, 49,42, 4,01 4) = Z M5) = P(X=5) = PES, 1},45, 24565, 3,45, 49,5, 5,44, 5), (3, 53,12, 5}, 3 = 2 6) = Re P({6, 1},{6, 2}4(6, 3},(6, 4},(6, 5),(6, 6),{5, 6} (4, 6},(3, 6},{2, 6},{1, 6}), 6 (1,2,3,4,5, 6}. ‘The tabular form: [XT 172) 3) 4) 3 76 F(X) | 16 | 3/36 15736 17736 [9736 111736 | ‘The expected value of a random variable is the summation of each value of the variable multiplied by its probability, Ithe variable X has values X; , Xp, .. Xq and probabilities P(X:), P(Xa), . .. » PO%) respectively, the expected value of the variable X is given by nu‘ BCX) © Xp + PK) # XQ PK Het Xa PK) ‘he mean (u) of the probability distribution is F(X) HEX) ‘The variance (8?) = B(X- p)? « P(X)» EX? POX) 12 J. ‘The standard deviation (8) is the square rvot of the variance. Hrumple: Referting \o the previous example tabulate the expected value or mean and Variance, wea 447 Pe EX? EX) epee ME Ae? Feary) <= Be — Gye = 1.97 3=VI97=14 x PO) XP) | XT PO) _] 1 136 136 rT | 136 2 336 O36 4 1236 3 5136 15/36 9 | 45/36 4 7136 28/36 16 [ 112/36 ee ee ie ‘225/36 6 1186 | 6656 36 396386 total 16136 791136 Example: By investigating in a particular stock, a person can make a profit in one year of with probability 0.3 or take a loss of $1000 with probability 0,7, what is this person's expected gain? Solution: Expected gain = (4000)(0.3) - (1000X0.7) = $500 Example: Let the random variable X represents the number of defective parts for a machine when 3 parts are sampled from a production line and tested, The following is the probability distribution of X. (ex 0 T 273 (Cig [ost [038 To.10 [0.01 Calculate the variance 8°? Solution: Compute for. = (0)(0.51) +(1)(0.38) + (2)(0.10) + (3)(0.01) = 0.61 EX? P(X) = (0)(0.51) +(1)(0.38) + (4)(0.10) + (9)(0.01) = 0.87 8 = DX? P(X) - 4? = 0.87 - (0.61) = 0.49 1. ‘Types of Discrete Probability Distribution 4, Bluomtal Distribution ‘There are certain conditions which exist in a binomial distribution, namely, 1, Iisa series of trials with only two possible outcomes for each trial, Ex.: head or tail for a coin, success or failure, and right or wrong, 2, ‘The trialy are Independent of one unother, ‘This means that the chance of getting any of the possible outcome does not vary from trial to trial (means that the selection is done with replacement), Usually the probability of getting a head or tal is 4. 3, Given a fixed number of trials, we desire to find a certain mixture, ‘Binomlul distribulion may be denoted by b(x;n,p).Mxsmp) =( )p'q?"* The probability distribution of the blwomlal random varlable x, the ‘number of successes in independent trials, ven by. PO) == (pC ~ py where p= probability wf success 4 (1-p) probability of ile _Mhe probability of exactly x successes is Example; thal a certain kind of component will survive a given shock test is a nd the probability that exactly 2 of the next 4 components tested survive. ‘Sulution: Assurning that the tests are independent ann! p= % for each of the 4 test. “ (214,34) “(APE aA. Vor the probability distribution: wv a +t Zo 00039 oe Example: The probability that a patient recovers from a rare blood disease is 0.4. 1f 15 people ‘are known to have contracted this disease, what is the probability that a) at least 10 survive b) from 3 10 8 survive ©) exactly 5 survive Solution: etx be the number of people that survive a) P(x210)= 1 ~ P(x<10) = 1 - £2. b(x; 15,04) ium table At) ~ 1 (0.9662) = 0.0338 b) PO12) © 1 PQKS12) = 1 EE q (45 20,0.70) 1) - 02277 = 0.9723 by mean (1) np * 20(0,70) » 14 €). variance (8%) = np(1-p) = 20 (0.7K 1 ~ 0.7) * 4.2 d) standard devintion (8) * VA2 = 2.05 2. Mypergeometrie Distributlon ‘ hypergeometric experiment is one that possesses the following (wo properties: 1) A random sample of size nis velected without replacement from N item 2) Kof'N items maybe classified as successes and N ~k are classified as failures, Hypergeometric Distribution = the probability distribution of the hypergeometric random variable x, the number of successes in a random sumple of size n selected from N items of which k ue labelled suceess and N ~k labelled fallure, is , dis Hox: Nem, ) , OMe n From the definition, the total number of samples of size n choven from N items is (M1). ‘These samples are assumed (0 be equally likely. There are ('f) ways of selecting x successes from the k that are available and for each of these ways we can choose the n ~ x failures in (X=K) ways. ‘Thus the (otal number of favourable samples among the (}) possible samples is given by QQ). Example: A commitice of size 5 is to be selected at random from 3 chemists and $ physicians. Find the probability distribution for the number of chemists on the committce. Solution; Jet the random variable x be the number of chemists on the committee, ay(s Pox0) = HO; 8,5,-- G24 $ a Poel) = h(t; 8, 5,3) =- DO x @) ay Pixe2) = h(2; = G8) _ 30 M2) = HO 8, 8.3) ° AG =F OO _ 1 P(x=3) = h(; 8, 5, 3) "@ % In tabular form: x 0 1 2 3 h(x; 8, 5,3)_| 1/56 _| 15/56 | 30/56 | 10/56 Example: A box contains 6 blue marbles and 4 red marbles. An experiment is performed in which a marble is chosen at random and its color observed, but the marble is not replaced. Find the probability that after 5 trlaly of the experiment 3 blue marbles have been chosen, Given: k= 6, N= 10, n=5, x=3 Let x the number of blue marbles,Gyo) (fyh P(x=3) « ages) = BO OA762 G") ) _The mean und varlance of the hypergeometric distribution Wx; Non, k) are: on Bg wean (y=, variance (4) = From the previous problem, find the mean, variance and standard deviation. Solu: svean(u)= 22 w 3 ance (8%) o( 1922 y. 5 -& (1-4) wbx variance (8°) =( ys 7A aes 0.69 10-1 standard deviation (3) = ¥0.667 = 0.8164 Example: Lots of 40 components each are called acceptable if they contain no more than 3 defectives, The procedure for sampling the lot is to select 5 components at random and (o teject the lot fa defective is found. What is the probability and exactly 1 defective will be found in the sample if there are 3 defective in the lot? Also, find the mean and variance. Solution, 144 x be the number of defective component Given; x= 1, N°40,k=3, 055 By (37° P(x=1) © hl; 40, 5, 9 = 03011 # 35 3 wm 8B 20 M25). 5.3. By 0 B= a) SG (l- Ga) = 03113 Example: Out of nine families living in Maria Cristina Street, six of them own their homes and three of them rent. If four families are interviewed at random (without replacement), what is the probability that 3 are homeowners? Solution: Let x be the number of homeowners Given: x=3, N=9, k=6, n=4 GG) __G)G) (x23) = (3; 9, 4, 6) = = Co) @ 4 Poisson Distribution Simon Poisson (1781 ~ 1840) developed Poisson distribution which is very useful to dccision-inuking with respect to quality control situation, waiting line problems (queue) and other upplieation to business. Unlike binomial and hypergeometric distribution, this focused ‘on the nian number of occurrences per unit time, distance or area. Properties of Poisson Proce 1, The number of outcomes occurring in one time interval as speci ion i i specified region is independent of the number that oceurs in any other disjoint time interval or the region of space, 2, The probability that a single outcome will occur during a very short time interval {nu small region is proportional the length of the time interval or the size ofthe region and does not depend on the number of outcomes occurring outside this time interval or region. 3. The probability that more than one outcome will occur in such a sort ime intecval or fall in such a small region is negligible.‘The number X of outcomes occurring in a Poisson experiment is called Poisson random variable and its probability distribution is called Poisson distribution, ‘The probability distribution of the Poisson random variable X. representing the number + of outcomes occurring in a given time interval or specified region denoted by t is given by Maye Ox At) = uot =0,1,2,... where: 2. is the averaze number of autcomes per unit time or region © = 2.71828, ‘The mean-number of outcomes is computed from = At, where tis the specific time or shall denote by the symbol P(x3 At). ‘Table A.2 contains Poisson Probability sum p(ry At) = Ey-0 P(X: At) for a few selected values of At ranging from 0.1 to 18. Example: ‘The average number of radioactive particles passing through a counter during 1 millisecond in a laboratory experiment is 4. What is the probability that 6 particles enter the counter in a given millisecond? Solution: et x be the number of particles that entered the counter Given; x=6 dt -4 46 (6; 4)= == 0.1042 Using table A.2: (6; 4) = D8.o p(x; 4) - E810 p(x; 4) = 0.8893 — 0.7851 = 0.1042 Example: ‘The average number of oil tankers arriving ech day at a certain port city is known (o be 10, The facilities at the port can handle at most 15 tankers per day. What is the probability that on a given day tankers will have to be sent away? Solution: let x be the number of tankers arriving euch day. P(x 15) = 1 ~ P(es15)= 1 - E850 OX; 10) 0.9513 = 0.0487 ‘The mean (4) and variance (3°) of the Poisson distribution p(x; At) both have the values At. weO=e Example: A plate glass windows produced by a chemical process contains 0.015 bubbles per square meter. Monica wanted to buy a 10-by-2-meter plate glass window, ‘a, Find the probability that it will have no bubbles it, b. Find the probability that it will have 5 bubbles in it. Solution: Area of the glass = 10 x 2.= 20 m? ‘The expected value of bubbles = (20 m? \(0,015 bubbles/ m?) = 0.3 bubbles a b. Exercises: 1) Out of 2000 families: 4 children each how many would you expect to have (a) at least | boy, (b) 2 boys, (c) 1 or 2 girls, (d) no girls? 2) If 20% of the bolis produced by a machine ure defective, determine the probability that out of 4 bolts chosen at random (a) 1, (b) 0, (c) less than 2, bolts will be defective. 3) If the probability of a defective bolt is 0.1, find (a) the mean and (b) the standard deviation for the number of defective bolts in a total of 400 bolts. 16LESSOVI. NORMAL DISTRIBUTION Objectives: Al the end of the lesson, the student should be able to: 1. define Normal distribution and Normal random variable. 5. relate the proper s of a Normal curve. 6. compute the central point in the normal distributi 7. compute and locate areas under normal curve. 8, solve problems related to normal distribution, 17ML NORMAL DISTRIBUTION 4 Definition ‘The most important continuous probability distribution in the entire field of statistics is the normal distribution. Its graph, called normal curve isthe bell-shaped curve shown in the igure. 3 — # A continuous random variable X having the bell-shaped distribution (in the figure) is called the normal random variable, The mathematical equation for the probability distribution of the normal variable depends upon the wo parameters « and 8, its mean and standard deviation, Hence, the density function of the normal random variable X with mean (4) and variance (8°), is 0s 18) = ai eo where: m= 3.1416 and ¢=2.71828. MET or moi mar= ze; on (-() 4 2. Skewed Distribution While the distributions of many variables tend to approximate a normal distribution, there ure some variables whose distributions are non-normal. These types are called skewed distributions. ‘Two types of skewed distributions: 1, Skewed to the right 2. Skewed to the left A distribution that is skewed fo the right bas a tail that is longer on the right end. ‘While one that is skewed to the left has a longer left tail. ‘Normal curves with 1 < 2 and 8; = 3.= cs ” Nonnal curves with y= 42 and 8; < 82. mye Normal curves with yr < pz and 8 <8. J. Properties of a Normal Curve: 1.) Itis symmetrical about 4. 2.) The mode, which is the point on the horizontal axis where the curve is a maximum, ‘occurs at x = Ht. 3.) The tails or ends are asymptotic relative to the horizontal line. 4,) The total area under the normal curve is equal to | or 100%. 5.) The normal curve area maybe sub-divided into at least three standard scores each to the left and to the right of the vertical axis. 6.) Along the horizontal line, the distance from one integral standard score to the next integral standard score is measured by the standard deviation, 4, Areas Unier the Normal Curve ‘The first step in finding areas under the normal curve is to convert the normal curve of uny given variable into a standardized normal curve by using the formula where: z* standard score x» a given value of a particular variable 8 standard deviation ‘The distribution of a normal random variable with mean zero and variable | is called a standard normal distribution,‘The original and transformed distributions arc illustrated below: oT 0 v — 62.27% —> + 95.45% ———+ —@@_— 9.739% ——____+ Hxample 1.) Given a standard normal distribution, find the area under the curve that lies (a) the right of = 1.84 and (b) between z -1.97 and z,= 0.86, Solution: Using table A.3 | (a) A = 1 area to the lef of z i 1.84 = 1 0.9671 = 0.0329 i (b) A - urea to the left of 2945 — area to the Ieli of 197 = 0.8051 ~ 0.0244 = 0.7807 “197 086 Example 2.) Given a standard normal distribution, find the value of k such that (a) P(z> k) = 0.3015 and (b) P(k < z<-0,18) = 0.4197. Solution: (a) area to the lef of k= 1 - 0.3015 .6985 Using table A.3 it follows that k = 0.52. (b) area to the left of k = area to the left of 9,4 - 0.4197 k = 0.4286 -0.4197 = 0.0089 04197 Using table A.3 it follows that k = -2.37 k 0.18 Example 3.) assumes a value between 45 and 62. Solution: a normal distribution with 4 = 50 and 8 = 10, find the probability that x w= 50* PCAS 362) = P(%> 1.24) = 1 — P(e < 1.24) = 1 - 0.8925 = 0.1075 Hxample 5.) Given a normal distribution with 4 = 40 and 5 = 6, find the value of x that has 45% of the area to the left and (b) 14% of the area to the right. ‘Solution: (a) using table A.3, the z-value that corresponds to the area of 0.45 is z= - 0.13. 0.13 X= 6(-0.13) + 40 = 39.22 (b) using table A.3, the z-value that corresponds to the area of (1 - 0.14) or 0.86 is 2= 1,08. 5. Applications of the Normal Distribution Finding the areas under the normal curve is just a means or device to help us solve ‘actual problems in statisties. I is however, important to take note of the following important conditions ~ that the distributions of the population in the problem we are concemed with, ‘must approximate a normal distribution or that the problem assumes a normal distribution, Although most problems assume a normal distribution, one may have to check through sample survey and find out whether or not the resulting histogram tends to follow a normal curve. Only under this condition we ean solve problems by using the technique involving areas under the normal curve. Example 1.) _A certain type of storage battery lasts on the average 3 years, with a standard deviation of 0.5 year. Assuming that the battery lives are normally distributed, find the probability that a given battery will lasts less than 2.3 years. Given: w=3 B= 0S Required: P(x <2.3)=? x=23 Solution; 2-733 m 1.4 Using table A.3: P(x <23)=P@<-14) B= 40 = 0.0808 = 8.08% 2#Xample 2.) An electrical fm manufactures lit bulbs that have a length of Ife that fs Normally distributed with mean equal to 800 lioury and a standard deviation of 40 hours. ind the probability that a bulb burns between 778 und 834 hours, Salution; 7, = ZU 55 py wll 4-000 A 8S Using table A.3: W778 43) = =40 Solution: z= 2 Pox > 43) =P + 6.68% of the resistors will have a resistan Example 6.) In un examination the average grade was 74 and the standard deviation was 7. If 12% of the class are given A’s, and the grades are curved to follow a normal distribution, what is the lowest possible A and the highest possible B? Given: p=74 8=7 Solution: \ ~ 0.12 = 0.88 (area ofthe unshauled portion) Using table A.3, look for the value of with corresponding area of 0.88. from table A.3, A aie wale 118 08810 fc 088 H 17 0.8790 11g-z 118-117 0.8810-0.88 0.8810-0.8790 2 P(z< 1.175) = 0.88 1 a 0.001 0.002 7 x = (7)(1.175) + 74 = 82.225 175 + the lowest A is 83 and the highest B is 82 Exercises: 1) Out of 800 families with 5 children each, how many would you expect to have (a) 3 boys, (b) 5 girls, () either 2 of 3 boys? Assume equal probabilities for boys and girls. 2), What is the probability of getting a 9 exactly once in 3 throws with a pair of dice? 3) If the heights of 300 students are normally distributed with mean 68.0 inches and standard deviation 3,0 inches, how many students have heights (a) greater than 72 inches, (b) less than or equal to 64 inches, (c) between 65 and 71 inches inclusive, (4) equal to 68 inches. 4) On a statistics examination the mean was 78 and the standard deviation was 10. (a) Determine the standard scores of two students whose grades were 93 and 62 respectively, (b) determine the grades of two students whose standard scores were -0.6 and 1.2 respectively.LESSONIV. SAMPLING THEORY Objectives: At the end of the lesson, the student should be able to: 1. define sample & population, sampling with & without replacement. 2. explain the importance of the most commonly used statistics for measuring the center of set data, il problems. and variances. 4. compute sampling distributions of means, proportion ss size, interval & cla define frequency distribution, class frequency, clas: ncy distribution, 6. construct a frequ sures of variability and quantiles 7. compute the measures of central tendency, me ol the frequency distribution, 8. compute the measures of central tendency, me of the frequency distribution. 24IV. SAMPLING THEORY ._, Often in practice, we are interested in drawing vs of individuals or objects. Instead of examining the entire group. called population, which maybe difficult or impossible to do, one may arrived at the idea of examining only a small hart of this population, which is called sample. ‘This is done by the aim of inferring certain facts about the population from results found in the sample, a process known as statistical inference. The process of oblaining samples is called sampling. Sampling where each member of a population may be chosen more than once is called sampling with replacement, while if each member cannot be chosen more than once is called sampling without replacement. ‘The reliable of conclusions drawn conceming a population depends on whether the sample is properly chosen to as to represent the population sufficiently well, and one of the important problems of the statistical inference is just how to chose a sample, To make sure that cach member of the population has the same chance of being in the sample and to inate any possibility of bids in the sampling procedure, it is des ‘Sample in the sense that the observations are made independently and at random. let Xi, Xx... . Xa be n independent random variable each having the same Probability distribution f(x). We then define Xj, X:.... ., Xq to be a random sample of size n from the population f(x) and write its joint probability distributions as WX ages Xa) = M1) Ma)... Ma) Any quantity obtained from a sample for the purpose of estimating a population Parameter is called sample statistic or statistic. In the previous topics or chapters, we jons about a large group reduced the (wo parameters and 82, which measures the center of location and the variability of the probability distribution, We shall ine some important statistics that describe corresponding measures of a random sample. ‘The most commonly used statistics for measuring the center of a set of data, arranged in order of magnitude are the mean, median and mode. If X1, Xz,.-., Xa represent a random sample of size n, then the sample mean is defined by the statist ya thoe 2 If X1, Xz... Xa represent a random sample of size n, arranged in increasing order of magnitude, then the sample median is defined by the statistic X(o+1y2, ———> ifrnis odd RPO 5 —> ifniseven If Xs. Xa... Xay not measuring not necessarily all different, represent a random sample of size n, then the mode M is that value of the sample that occurs most often or with greatest frequency. The mode may not exist, and when it does it does not necessarily unique. “The most important statistics for measuring the variability of a random sample are the range and the variance. ‘The range of the random sample X;, Xa, .., Xn is defined by the statistic Range =X.—X1 where X, and X; are respectively, the largest and the smallest ‘observations in the sample 25It X, x; defined by the statistic Fepresent a random sample of size n, then the sample variance is 7 Bains? n=1 inion” Ste standard deviation denoted by S, i the posiive square root ofthe sample Variation, Hsumple |.) ‘food inspector examined a random 1c of 7 curs of a certain brand of tune 40 determine the pereent of foreign impurities. The following data were recorded: 1.8, 211.7, 1.60.9, 2.7,and 1.8, Compute te sample meon Solutom: X= Wetter Ter erasia7e19 Hample 2.) ‘the number of foreign ships arriving at an East Coast Port on 7 randomly selected days were 8, 3, 9, 5,6, 8 and 5. Find the sample median, Soluion: Arranging the observation in increasing order of magnitude, 3556889 ¥=6 Hxample 3.) ‘The nicotine contents of a random sample of 6 ci found to be 2.3, 2.7, 2.5, 2.9, 3.1 and 1.9 mi en 25427 aa X=] =26 milligrams Hample 4.) IC the donation of a random sample of residents of Fairway Forest toward the Vi ia Lung Association are recorded as 9, 10, 5, 9, 9, , 8, 6, 10, and 11 dollars, then the mode is M = $9, the value that occurs with the greatest frequency. ‘ample 5.) ‘the number of movies attended last month by a random sample of 12 high school students were recoded as follows: 2, 0, 3, 1, 2, 4, 2, 5, 4, 0, 1, and 4. In this Example 6.) The 1Q's of a random sample of 5 members of a sorority are 108, 112, 127, 118, and 113. Find the range. Solution: range = 127-108 = 19 xample 7.) ‘A comparison of coffee prices at 4 randomly selected grocery stores in San Diego showed increases from the previous month of 12,15, 17, £426 ‘cents for a 200 tram per jar, Find the variance ofthis random sample of price ineneace =, 12415417420 Solution; X= TS = 16 cents + fay(*1~26)? _ 02-16)? + (15~16)24(17-16) 24 (20-16 > Ss 07 5) 3 3 = CHF) 24 54 SECU? 4)? 3 3 3Using the tabular form: ™ a-® [@r-%)* | 12 |_4 i6 | 15-1 1 | 17 1 J 20 4 16 ras at 3 A. FREQUENCY DISTRIBUTION refers to the tabular arrangement of data by ex OF culegories together with their corresponding class frequencies. Class frequency relers to the number of observations belonging to a class interval, or the number of items with in weutegory. elas interval fs a grouping or category defined by lower limit and an upper Steps in c 1. Deter 2. Determine the number of elass intervals or categories desired. The ideal number of class interval is somewhere between 5 and 15, 3. Determine the approximate size of the class interval by dividing the range by the desired number of class intervals. Write the class intervals starting with the lowest lower limit as determined by the fsserchers choice. The upper imi is determined ty the size ofthe cass interval minus 1 5. Determine the elass frequencies for cach class interval by referring to the tally column, ©. Compute tor tne class mark by adding the lower and upper fi antervai, then dividing the sum by 2 its of the class Formuta for the Grouped Data (N>30) 1) Mean (y= Te o §=6®) ad where: f; of frepresents the frequency N—total frequency Xj or X - class mark By coded deviation method: ays (2H 1a Kole xe + FE): @ where: d= unit coded deviation X = each ofthe class mark = assumed mean which can be represented by any class mark (with highest frequency is usually used) i = the sizeof the clas interval Np -Eh 2) Median Kae Lm + ( A where: Ln it boundary of the median class Zfyy ~ sum of all frequencies before the median class frequency or the cumulative frequency before that of the median class. frequency of the median class lower a3) Mode M= Ln (SH) Where: Loy ~ lower limit of the modal class 41 - is the difference between the highest frequency and the frequency just above 42 - is the difference between the highest frequency and the frequency just below it, Example: Given a set of data as follows. Construct a frequency table and solve for mean, median and mode, 49 5286S 57. 562624 16 91 29 4B BB) SR 298.998 DOE eSB ROT 440-470 6748 4 71 59 bt 820 633838 Sv 65 3973 S40 Tl a2 8S The Quantites are natural extension of the median concept in that they are values which divide a set of data into equal parts. While the median divides the distribution into two ‘equal parts, the quantiles which divides the distribution into four parts are called quartiles; those which divide the distribution into ten parts ure deciles; and those which divide the distribution into one hundred parts are called percentiles, $s mee ian Median 1 " mM Vv -— t+ + sF€ouartite a Q a @ 1 mW oWweovoovw vm vmx x DECILES Di Dr Dy De Ds DED Dh DB Dy -———_—_—_—_———_+—_________, PERCENTILES Po Pr Poo ‘The seml-Interquartile range (quartile deviation) is the amount of spread between the first quartile and the median or the median and the third quartile, x“, meget al 2 9-% Qd 2 28M, SAMPLING DISTRIBUTIONS . . A sample watintic which is computed from Xt, X2e +++» Xn is a function of these random varlubles and fy therefore itself a random variable, The probability distribution of a sumple statistic Is often culled the sampling distriburlon of the stat 1, Sampling Distributlon of MEANS Let f(x) be the probability distribution of some given population from which we draw 1 sumple of alze n, Then It fs natural to look for the probability distribution of the sample ftatisle"R, which ls called the sampling distribution for the sample mean or the sampling distributton of means, “The following theorems are important in this conneetion: 1, The mean of the sampling distribution of means, denoted by Hr is given by BOX) yy > (1) (the expected value of the sample mean Is ‘the population ‘mean) 2, ifm population is infinite or if sampling is with replacement, then the variance of the sampling distribution of means, denoted by 6}, is given by Hila why = B= Se (2) Got is the varlance of the population) ment and if the sample 3. I the population is of size N, if sampling is without repla size is nN, then equation (2) is replaced by a= H (EX) +) mn \N=1, 4, Ifthe population from which samples are taken is normally distributed with mean and varlance 8? then the sample mean is normally distributed with mean # and A e variance ©, 5, Suppose that the population from which samples are taken has a probability distribution with mean and variance 6? that is not necessarily a normal distribution. Then the standardized variable associated with’x, given by xn . 2% = 73 is asymptotically normal, va Example: An electsical finn manufactures light bulbs that have a length of life that is tpproximately normally distributed, with mean equal to 800 hours and a standard deviation of 40 hours, Find the probability that a random sample of 16 bulbs will have fan average life of less than 775 hours. Given: j= 800, 8= 40, n= 16 ‘Let x represents the number of random sample 5 40 bE He 10 ~ 2775-000 rT) 5 a . 3 in715 +25 4, P(x <775) = P(z. < 2.5) = 0.0062 z ‘Assume that the heights of 3000 male students at a university are normally buted with mean 68 inches and standart deviation 3 inches. If 80 samples consisting of 25 sade st are obiained, what would be the expected mean and standard deviation o sampling distribution of means if sampli sone enon oe pling ditibuton of means if sampling were done 29Solution: (a) us = = 68 inches, , Fan Fez ahd () Hx = 4 = 68 inches &-=( |% =3_ [300-25 dab viel eS Ya \yN=1) ~ Y25\y 3000-1 Example: Referring to the above example, how many samples would you expect to find thee mean (a) between 66.8 and 68.3 inches (b) less than 66.4 inches? Solution: (a) P(66.8 < x < 68,3)=? X68 06 =-2.0 683-68 == 0.5 06 £P(G6.8 < x < 68.3) = P(2 < 0.5) — Plz < -2,0) = 0.6915 ~ 0.0228 = 0.6687 ~ the expected number of samples = (80)(0.6687) = 53 7 8 66.860 (b) 67 06 P(x < 66.4) = Pz <-2.67) = 0.0038 ‘Then the expected number of samples = (80)(0.0038) = 0.304 ~ 0 2. Sampling Distribution of PROPORTIONS. Suppose that a population is infinite and binomially distributed, with p and q = J - p being the respective probabilities that any given member exhibits or does not exhibit a certain property. For example, the population may be all possible tosses of a fair coin, in which the probubility of the event “heads” is p = ¥4. Consider ull possible sumples of size n drawn {rom this population and for each sample determine the statistic which is the proportion p of suceesses. In the case of the coin p would be the proportion of heads turning up in n tosses. ‘Then we obtain a sampling distribution of proportions whose mean i and standard deviation 6, are given by frag _ four») 1 n For large values of n (n > 30) the sampling distribution is very neatly a normal distribution. =p and by Example: Find the probability that in 120 tosses of u fair coin (a) between 40% and 60% will be heads, (b) 5/8 or more will be heads. Solution: p =A probability of heads q=1-4=% probability of tails 30