8 variate in the population are distribute called probability distributions. De assified into two categories, distributions, when the value of the can be expressed mathematically are .m variable, the probability distributions are ¢ acc, Pending the type of rand (Discrete probability distributions ) Cor probability distributions In this chapter we shall study discrete probabi utions Ii ution and continuous probability distribution, ie. Normal distribution. 8.2. Binomial Distribution — (PT, ‘bution is an important distribution used when there are two possible outcomes ¢, wered by Swiss scientist James Bernulli and hence also known as Ber, lity distributions Tike Binomial distribution, », Binomial dist DT was distribution. A discrete random variable X is said to follow binomial distribution if it assumes only non., values and its probability mass function is given by "Cy pig” *:x20.12, P(X =x)=p(x)= |"Cae"a 0 otherwise The two independent constants n and p are known as the parameters of the distribution. ‘n’ is zs sometimes. known as the degree of the binomial distribution. Binomial distribution is a discrete distribution as X can take only the integral values, viz, 0,1, Any random variable which follows binomial distribution is known as binomial variate. We shall use the notation X ~ B (n, p) to denote that the random variable X follows bind distribution with parameters and p. The probability p(x) is also sometimes denoted as b(t, ,p). Remarks : 1. The assignment of probabilities is permissible because . m9 Dow = > Jota la let x20 x= 2. Let us suppose that trials constitute an ex periment. Then, if this experiment is repeated N tit* the frequency function of the binomial distribution is given by : 5 10)-Nxpe)-Nx S| m) kgn-x pg 5x=0, 1,2, x=0 Xx, and the expected frequencies of 0, 1, 2, ++ M successes are the successive terms of the bit?” expansion of N (q+ p)",.q+ 214 Scanned with CamScannerions for Binomial distr lion . 2011, 2013) jinomial di bution under the followi goto al results in two exha ’ : NG experimental conditions sch ustive and mutual ilure. ee ly disjoint outcomes, termed as success and fai re number of Wils is Finite and fixed (ye riats are independent of each other "he probability of success *p" is constant for each trial ) Ane * oo trials satisfying the conditions (i), (iii) and (iv) are also called Bernoulli trials. 10 tos 8 coin o throwing of dice or drawing cards from a pack of cards Im ferent ead 0 binomial probability dstibutions 7 a pinomial distribution is important not ont seaher probability distributions. The sta any © oblems relating £0 tossing of ¢ ly because of its wide applicability, but because it gives rise tistical tables for p(x) are available for various values of 7 tperivation of Binomial Distribution : o : " tus consider a set of 7 independent (n is finite) trials, in which the probability p of success of any axis constant and q the probability of failure, ie. g= 1 —p, The probability of x successes and consequently (n— x) failures in m independent trails, in a specified ie (sty) SSFSFFFS.....FSF (where S represents success and F represents failure) is given by the x pound probability theorem by the expression : p (SSESFFFS....FSF) = P(S)P(S)P(F)P(S)P(F)P(F)P(F)P(S) x = P P9494 Pon DY x P(F)P(S)P(F) (x factors) (n—x factors). But x successes in n trials can occur in "C, ways and the probability for each of these ways is some, vz p"q"-*, Hence, the probability of x successes in » trials in any order is given by the addition theorem «fprobability by the expression "C, p*q""*. The probability distribution ofthe number of successes, so obtained is called the Binomial probability firibution, for the obvious reason that the probabilities of 0, 1, 2, ... m successes, viz. q”,"C, q”"'p, "cy q?p?,.... p", are the successive terms of the binomial expansion (q+ p)". '22 Properties of Binomial Distribution (P.7.U. 2004) | Itis a discrete probability distribution in which random variable can take only a countable number of Values 0, 1,2, 3, ..... The probability function for B.D. represents probability of having a fixed number of success (r) out of 4 fixed number of trial (n), ie. P(X =") = "C, PY q"~" , where p is the probability of success in a ‘Mle tial and p-+q=1, r=0, 1,217 ; "(oumber of trials) and p (probability of success ina single trial) are the only two parameters, Scanned with CamScannerProof: Let X ~ B.D. (np) P(K=n="C, p'q"": pta By definition, Mean (X) = E(X) ¥irpx-n ¥r.tc, pg rao r=0 : 2 = 0."Cy pag” +1"; pig +2. "Cy peqn +. pr? rot g 2 MMAD 52 gre? gg MO Din 2) agr3 = O4npa' 123! tect pl” DQ=2) 9 93 a onal am +(n-Dpqh? + CNOA? 5 2h at pl nol gn n-2 .n-l =: nl -1 =nplat! +" c, pq? +8 lc, prgt 3+. CP] =np(qtpy! =npoyt =u=np ( p+qey 5. Variance of B.D. is np q- (P-7.U.2019 Proof : Var (X)= E (X2)—(E (x) = B(X2)-(w)? = E(X?)- (np)? . PPKan-(np = YP", pra" np)? iM: " = Yirere-mtc, ofa" (0 pF = Dre, pal Sore", pal tne? r=0 r=0 r=0 =npt2.1"Cy. an 743.2% p qt 3+... tn(n-l)p"= (n py? =np+2x1 2d = prgt? 43x 22a Dn?) 39-3 5 ant lp" (ap? Tx2x3 =nptn(n—l)p lq"? +(n-2)pq +... +p" 2] - (np)? =nptan— De lg 24" 7G, pqt 3+... "Cyan pr] - (np? =nptn(n- Ip (q+ py ?— (np? snp (rnp (y"? = (np)? Scanned with CamScanneruvDSTRISUTIONS 8: ye 217 =np+ Wf —n)p~(n py enpte Panpa ep [vv wenpl =np-"P=np(1~p) Variance = 0? =n pq «forthe BD. variance is always less than mean, mere pot Let X~ B.D. (7), then Mean=np and variance =n pg since g=1-p and O variance < mean, 1. Recurrence Relation for the moments of Binomial Distribution (Renovsky Formula) Proof: By definition, we know that =E{X- BOO! = Ye- wy("Jora qn x=0 Differentiating with respect to p, we get = a x" Jove mp)! p*q* + (x=np)" xp*“"q""* -(n—2) pq} =) 8] Cs q=1-p) = ("leony per +3 "Jo- mp)’ p¥q"* ( x20! n x (=) sane Y (x= np)! ped emmy’ we x30 x= snr SY (x= np)! p@) n 1 Pale > omy P= mr Hyg Meth fa Pd x20 s du, Mes = pq | nr t,_) + “ich i also known as Renovsky formula. - Scanned with CamScannerXG MATHEM AT Way 218 | e gel On taking r= 1, 2 and 3 suce in above result, We B¢ dit Mo = Vand yy ° 1] i} Hy oy (ny mq di 40079) — pg “pp Hy = pq [ao ap 4D = npq fe (p- p?) = npq (1-2 p) = npa (q-P) du. d = and ly =pq [aa 4) =pq [>more mata »} d 2 3 2 = 2 —(p-3p" +2p") -1a[30? pen p-n)0-20)] =r 3 patina (PSP 2p = pq [3n? pq+n(1~6 p+6 p*)] = pq [3n? pq +n (1-6 pq) = npq (3 npq + 1-6 pq] = npq [1+ 3 pq (n—2)] = 3n°p?q? +n pq(\-6 pq) 8. Coefficient of skewness for B.D. is 2 tnpq(q- py ie Hy (npg? - 9- py ie B= STaaE ae irs Hence, if q>pthen y,>0 > apositively skewed distribution Pearson's coefficient = 7, = If q=p then Y, =9 > asymmetrical distribution If q anegatively skewed distribution, 9. Coefficient of kurtosis for B.D. is p,-th = 31? p? ¢ +npgil-6 pq) =3,126p9 i Pg tn pail-6 pq) _ ay (npqy "pq Pearson's coefficient = y, = 1-6 pq "pq 10. Additive Property IF X~B.D. (,. p) and ¥~B.D. (ny, p), then X+¥~B.p. (n, +n, p) ‘ . a . o_ ins ie Sum of two binomial variates s.a binomial variate provided the probability of success i 25 trial always remains constant 7 Scanned with CamScanner111 DISTRIBUTIONS N pao jp Mode of Binomial Distribution in binomial distribution, the probabili Y OF x success is aa sis given by PO Mee Pa O12, Mode is the value of x for which p (x) is ma ener han oF equal to P (x Ty and Pe +), en PQ SPO)E POs dy conser P(r 1) SPQ) imum, i.e. the mode is that value of x for which P (x) is nt nt @-Dia-xepi? = Flap? or xq S(n+1)p-xp or (pt gS(ntl)p or xS(n+I)p Ai) Similarly, on considering P (x) = P(x +1), we have x2(n+I)p-1 ol) From (i) and (ii), modal value x satisfy the inequality iii) (n+ I)p-1sxs(n4+l)p Case. If (n+ 1) p= np + p= k= an integer, then (np+p)-1 =(n+ 1) p—1=k-1 is also an integer. P(x=h)=P (x= h- in this case P (x) increase tll x = k~ 1 and then (iv) holds and after that it begins to decrease, kand x = k— | are two mode. distribution become bimodal with modal values as.x = k= np +p and.x = k— ie, =np+p-1 Cel If(n + 1) p =n p+ p= k= not an integer. Let np p=a (an integer) +/(a fraction) When x takes the value ‘a’ (which is obviously less than & and greater &~ 1) from (i) and (ii), we have P(a—1)P(a+) integral part of (7 Pp + p)= [np +p] = [alis the mode. Scanned with CamScanner8 F (Mean of B.D = np = Mean of the given distribution : ingle trial for given n number of trials, (2) Find, p> probability of suecess in a single trial for given 1 Gi) N > Total frequency zy, (®) Find the expected frequen P(X=N=NSP (Xen) =NX"C, pl gt": y given by Example 1. Determine is the binomial distribution (or B.D.) whose mean is 9 and whose standard evitio, Sol. Mean=9, $.D. 3 2 3 a Putting value of p in (1), we have 3. mass > n=9x 2219 n=12 1 3 12 binomial distribution is (t + 3) Example 2. if the sum of mean and variance of bit distribution, jal distr . omial distribution is 4.8 for five trials. Find (P.7.U.2019 Sol. Here n=5 and mean + variance = 4.8 = np+npq=4g 5P+Sp(l\-p)=48 apt (Ce mean = np, variance ="?4 SP+Sp-Sp=48 > a gel = 4 > 5p?-10 p44 =0 10+ fi0o~ p= 2100-96. = 1042 12 10 10” ~ T9°qp = 12.08 . Scanned with CamScannerrry DISTRIBUTIONS — . 221 S lalways 1.2 and we have p= 0.8 08 =0.2 BD.= (4+ P)" = (0.240.8)5, guample3- The probability of a man hitting a target ig ping atleast twice the target 2 find that how many tim Also fi 'y times must he fire 80 that probability of hitting the target atleast once is 2 peoerthan (P-T.U. 2010) gel + sol, Here, 9 =7,'P 27, q ‘ 44 requited probability = P (hitting atte =1-[P(O)+P(Iy) « 7 17 4y6 7e (3) a7e(1) (3 =1-|"cyf=] +7 cf 4] (3) | _ (3) (7) (; 729 5 _ 3645 _ 4547 ; : 3) 13,7 FI-fo} j4=] = —. 4) [404 4096 4096 8192 (i) Let mbe the number of trials required such that ast twice) P (hitting the target atleast once) > 2 . 2 > 1-P(oo iting the target)> 2 if = 1c [3] 52 °l4 3 * = 1/3] 52 | > yet 4) °3 [log 3 — log 4] < [log 1 - log 3] "(0.4771 — 0.6020} <[0- 0.4771] "382 > nad . Scanned with CamScanner22 o ind the probability Hon ie 4, Fight coins ave dros simuttaneons: nd ity of not getting a Head, then aut and the probabil Sol, Let p denote the probability of getting Me +1 own simultaneously . - en 8 coins are th probability of getting at least sik heads when 8 col Po) 1 PCT) + PB) re(Y (ee (9 s Tie Re, 8 (4) [*c, He, HC 4 37 1 [gx7 jog +84 = a alot a! 236 Example §. A pair of dice is thrown 7 times. If getting a total of 7 is considered a success, what js the probability of (no success? (ii) 6 successes ? (iti) at least 6 successes ? (iv) at most 6 successes ? Sol. Here n= 7. Let p be the probability of getting a total of 7. peg eee Pe 6 6 7-0 /1\0 7 3 1 3 (i) Pino success) = PO) = 7C, (3) (4) -(3 ess) POV "Cy(Z] [z) =lF 1-6/6 6 (ii) PG successes) = P(6) = 7C (3) (4) -145,(4) VG) M6) 1676 (iii) P(at least 6 (successes) = P(6) + P(7) (iv) P(at most 6 successes) P(not 7 success) 1= P= 1-te, (8) (4) - 6, Scanned with CamScanner223 times, Howy to show five ANY time do you expect at least three N=72% n=6 Here & a! 2 the probability of ge ae Hing S oF 6 With one geile 3 die. 3 the expected number of times at least three dice showing 5 oF 6. (3) + (R04) ea (4)4 = 799 233 | m9(2 33) ass, pumple 7. A and B play a game in which their xwinningateast three games out ofthe five gam chances of winning are in the ratio 3 : 2. Find A°s chance es played. (P.T.U. 2013) sul Letp be the probability that “A* wins the game, Here, we are given ma) ~p= 2. By binomial probability law, the probability that out of S games played, A wins ‘x games is given b rr (JGIGP aa The required probability that *A’ wins alteast three games is given by 2G Choe = 0-68. 27x(40+30+9) 3125 ‘ample 8. With the usual notation, find p for a binomial variate X, if = 6 and 9 P(X = 4) = P(X =2). (P.T.U. 2010) '0L For the binomial random variable X with parameters 1 = 6 and p, the probability function is Po=ne(t Sora T 3r=0,1,2,..6. Weare given 9P(X = 4) = P(X =2) 6 6 > 452 = ‘(> ve (s]oat Scanned with CamScanner= opr =(l-py = 1+ p?-2p -24 f4+32 _ -246 2:8 16 1 ; is rejected. Hence, p= >. = 8prs2p-1-0 spr Since probability cannot be negative, p= istribution are 4 and respectively, Fi Example 9, The mean and variance of binomial distribution are 4 and respectively. Find By | Sol. Let X ~ B (n, p). Therefore we have Mean = np =4 4 and vartX) = npg = 5 P(X21)=1-P(KX=0)=1-q" <= =0-99863. 729 Example 10. Check the correctness of statement, “Mean of a B.D is 3 and variance is 5.” (P.TU.200 Sol. Mean of B.D =n p =3 Variance of B.D=npq=5 On dividing (i by (), we get mP4 235 gy ge5 >) np 3 3 which is not possible, as 0 < q <1 Therefore, the given statement is not correct, Example 11. If on an average one ship out of 10 is wrecl ked, find the probability that out of 5%? expected to arrive the port, atleast four will arrive safely, (P.T.U. 20042 Sol. Given, on average one ship out of 10 is wrecked probability a ship is wrecked (damaged) = g probability a ship reached safely = p = 1-g 10 10 . : 5 Let X be the random variable representing the number of ships expected to arrive safely out of Scanned with CamScannerry DISTRIBUTIONS m8 {10} required probability = P (out of S ships, atleast 4 wil arive safely) ~ POX 2A) PIX = 4) POX 5) | (9) ; “ei | J e,(§) wrt othe (10) | (io) "yor tok = 0-91854 ample 12> Ifthe probability that a new born child is a male is 0.6. Find the probability that i= fami twp tere are exactly thre boys, (P.T.U. 2015, 2 water —rensiay oe artchd bare gc l-p=1-06=04 LaX be the Sodom variable representing the number of male children in a family of $ children. 8, binomial distribution, the probability of having ‘r’ male children out of a family of n = 5 children's pox=n=5C, p’ g’-" = SC, (0.6)' (04)5-" required probability = P(X = 3) = Sc, (0.6)° (0.4)? = 10 0.216 « 0.16 = 0.3456. fxample 13. Find the mean of binomial distribution B (s +}. (P.T.U. 2014) Sel Given 2 random variable X ~ B.D (s } 1 eee m4 pms . 1 & mean=mp= 4x5 = 1.533. Example 14, If the mean of a B.D is 3 and variance is ;. Find the probability of obtaining atleast A scces, (P.1.U. 2017) | Si.Given, Mean = n p =3 ~O | ad variance =npq= 3 ii) on dividing (i by (0), we get Pare mp 2? 2 Scanned with CamScanner226 From (i), np=3 > od] -3 9 n-6 atrial of Let X be the random variable representing number af success out of be v Vey " p=q- 6 eer ft 6 P (atleast 4 success) p(x 24) =P(X=4) +P(X=5)# P(X = 6) safes eal) 1 = . 3p=Sq=S(1-p) 3 3 e pad =1-p=2 Pry s ie qal-pas 10 x, p®q!® = 10000 G = 0.549. * required frequency = N x P(X = 0) = 10000 « "ey P’ 4 3 Scanned with CamScannerSPECTRUM ENG 230 : s 1.92. find othe Example 28. Mean of B.D. is 4 and its third moment about mean i er conv ample 25. Mean . is distribution. Sol. Given, Mean = np =4 and wt, =npq(q—p)= 1.92 4q(q-p)= 1.92 or g(2q-1)=048 or 2q?-q-048 =0 or (24 +0.6)(q-0.8)=0 g=08 as q# -03 p= 1-q=1-08=02 4 =< =20 from (i) n 02 0.2, q=08 For Mode : Here m p + p= 4.2 =not an integer. n=20, mode = [np +p] =[4.2]=4 } Variance = 1, =p q= 20 (0.2) (0.8) = 3.2 | 2 SD= i = 2 Also wy =apq(1+3pq(n-2)) = 3.2 [1 +3 (0.2) (0.8) 18] =(3.2) (9.64) = 30.848 2 1,92) coeff of skewness = , = “8 = O92) ~o.1125 6.2) H, coeff of kurtosis = B, = 4, = 32 ta 3.0125 4° G2) = 0.3354 and 7, = A, -3 = 0.0125. Example 26. Out of 800 families with 5 children each, how many should you expect to have (4) (8) 5 girls (c) either 2 or 3 boys. Assume equal probability for boys and girls. cet." Sol. Since given that chance of a boy or a girl is equally probable p= probability ofa boy = probability of a girl = Let X be the random variable representing the number of boys ina family with 5 children. Scanned with CamScannerWSTRIBUT 1 DST expected number of families out of a total of N = 800, having “r* boys is AXeneN* PIX == 800 Sc, “s(3) +) The expected number of families having $ girls (0 boy) is s A(X = 0) = 800 » *c,{2) =< =25 ) The expected number of families having either 2 or 3 boys is Ss 5 fX=2)=f(X = 3) = 800 » FC, (3) +800%5C, (3) = 250 + 250 = 500. ttample 27, The following data are the number of seeds germinating out of 10 on damp filter paper for $0 xcs of seeds. Fit a binomial distribution to this data : No.ofseeds(x) : 0 1 2 3 2 28:12 8 6 0 0 0 0 0 80 4 5 6 7 8 9 10 Total Frequency (f) : 6 SiLHere, n= 10,N=E f= 80 a + mean = ¥ of B.D. = np) . 174 P= —— = (+2175 800 02 * g> p= 0.7825. Scanned with CamScanner; ; , al distribution, the probabil Perens Me, ph gl = Me, 0.2178)" (0.7825)"~" the expected frequency of getting ‘7° seeds germinating = /(X = 7) = N» P(X =r), = 80 « c, (0.2175)" (0.7825)!0-+ On taking r= 0,1, 2.3 .....9 10, we get FX = 0)= 80s Me, (0.7825)! =7 FE 5 FX == 80s We, (0.2175)! (0.7825)? ~ 19 F(X =2)= 80x 'c, (0.2175)? (0.7825)* = 24 Similarly, f(X = 3)= 18, f(X =4)=8, f(X=5)~ 1, f(X=7)=0, f(X=8)=0, FO 0, f(X=10)=0 required fitting of binomial distribution is x 0 1 2 3 4 5 6 7 8 9 140 f 7 19 4 BW 8 3 1 0 0 0 Oo, Example 28. Fit a B.D. for the following data : ~ 2 U 2 3 4 5 f 2 4 20 34 2 if (P.T.U. 2015 Sol. Mean of B.D. is given by z M=np Efx _ 0+14+40+102488440 tf 100 = np= 2471 100 25 Here, n=5 el 1 = SP 55? P= 7, = 0.568 and q=1-p=1~-0.568 = 0.432 Here total frequency, N = 100 Now, the expected frequency of Binomial distributi ion is given by S(K=N= Nx" pig’? Pq fe FO) 100% 5c, (as6ey (0.439)8-r Scanned with CamScanner1y DISTRIBUTIO: when =1,f(1) = 100% 8¢ i when” 1 (0.568) (0.432y4 = 9.85 = 19 =2,2)= 100% 5 2 when r= 2.2) = 100 ©2 00.568) (04399 f@) 5 ~ 26.01 ~ 26 nen r= 3,3) = 100x Se (0.568)3 Ww 3 (0.432)? ~M2~34 7 =100x § when r= 4.£(4) = 100 x c, (0.568) (0.439) = 22.48 ~29 “ nal : nen 5.F08) = 100% 5c, (0,569)5 (0.432)5 = 5.91 ¢ | ene fitting of binomial distribution i ; 0 | : 1 2 3 2 e 10 26 a 7 ° EXERCISE 8 (a) 1, Find the binomial distribution whose (mean is 3 and variance 2, (i _ mean is 10 and standard deviation 2-y2 (iii) mean is 6 and variance 4. 2 (a) If the mean and variance of a binomial distrib, ution are respectively 9 and 6, find the distribution. (b) For a binomial distribution, the mean is 6 and the standard deviation is V2. Write all the terms of the distribution. 3. Bring out the fallacy, if any, in the statement : “The mean of a binomial distribution is 5 and its variance is 9”. ee | 4% @ ~The sum of mean and variance of a binomial distribution is nel for 5 trials. Find the distribution. (6) Find the binomial distribution when the sum of its mean and variance for 5 trials is 1-8, (©) If the sum of mean and variance of a binomial distribution for 18 trials is 10, find the su distribution. : ; @ a a .d sum of mean and variance of a binomial distribution is 7, then find it. n= 16 ands = | and n= 10, find its mean and varian ith p= — and n= 10, ariance, (2) Fora binomial distribution with p = 7 i of a binomial distribution are 24 and 128 the mean and variance | (6) The sum and product o respectively. Find the distribution. Scanned with CamScanner(d) (c) @ (e) * (s) in h s considered a success, F; A die is thrown 120 times and “getting 1 or 5” is const ind the he A die is thrown 121 n variance of successes. A pair of dice is thrown 200 times. If getting a sum of 9 is considered a sucgg, of of successes, : mean and variance of the number of successe: ' it ead is considered a success, Fj A coin is thrown 10 times and getting a head is consider ind the an standard deviation of the number of succes Four coins are tossed, Find the mean and variance of the number of heads obtaine ‘our coins are tossed. There is @ group of 10 families each having 5 children ees : Are BOYS ad 3 a One childs selected from each family, each child of the family being equally ja i selected. Find the probability that among the 10 children so selected; there are Crag girls. (A pair of dice is thrown 4 times. If a doublet is considered a success, find, probability of 2 successes. (ii) A pair of dice is thrown 10 times. If getting a doublet is considered a sui Iecess, fi probability of getting 4 successes. A box contains 100 tickets each bearing one of the numbers from | to 100. IF 5 tickets 2 drawn successively with replacement from the box, find the probability that all the tick bear numbers divisible by 10. A bag contains 5 white, 7 red and 8 black balls. If for ur balls are drawn one by one wis replacement, what is the probability that (i) none is white ? (i) allare white 2 (iii) only 2 are white ? (iv) at least one is white 2 Five cards are drawn successivel 'y with replacement from a well shuffled deck of 52 cars What is the probability that (O allthe five cards are spades? (ti) only 3 cards are spades (iii) none is a spade ? A bag contains 5 white, 7 red and 8 replacement, what isthe probability th (i) none is white black balls. If four balls are drawn, one by one, wit lat (i) allare white (ii) at least one is white (iv) only 2 are white 2 The probability that a pen manufactured by a company will be defective is 1. 1f 12% Pens are manufactured, find the Probability that W exactly wo will be defective : (ii) at least two will be defective (ii) none will be defective Scanned with CamScanner@ f (a) (b) 3) (b) (c) S| S le pry DISTRIBUTIONS 235 Four cards are drawn at a time getting all the four cards of the from a Find the probab k of $2 playing cards (i same suit D Gi) same number Five cards are drawn at random w probability of getting four spades The items produced by ith replacement from a deck of $2 cards. What is the & company contain 10% defective items. Show that the probability of getting 2 defective Bx 9° items in a sample of 8 items is 2 The items produced by a company contain 5% defective items. Show that the probability of getting 2 defective items in a sample of 10 items is 45212 10 20 A bag ene 10 balls each marked with one of the digits 0 to 9. If four balls are drawn successively with replacement from the bag, what is the probability that none is marked with the digit 02 During war, | ship out of 9 was sunk on an average in making a certain voyage. What was the probability that exactly 3 out ofa convoy of 6 ships would arrive safely ? There are 5 Percent defective items in a large bulk of items. What is the probability that a sample of 10 items will include not more than one defective item ? The items produced by a firm are supposed to contain 5% defective items. What is the probability that a sample of 8 items will contain less than 2 defective items ? There are 5% defective items in large bulk of items. Find the probability that a sample of 5 items will include not more than 2 defective items. There are 6% defective items in a large bulk of items. Find the probability that a sample of 8 items will include not more than one defective item ? The items produced by a firm are supposed to contain 5% defective items. What is the probability that a sample of 8 items will contain less than 2 defective items ? There are 8 % defective items in a large bulk of items. Find the probability that a sample of 10 items will include not more than 3 defective items. in how many cases one can expect 8 heads and 4 tails. ry will fuse after 150 days of use is 0-05. In 256 sets of 12 tosses of a coin, The probability that a bulb produced by a facto Find the probability that out of 5 such bulbs (i) none (ii) not more than one (ii) more than 1 (iv) at least one will fuse after 150 days of use. 7 / The probabilities that a bulb produced by @ factory will fuse after 160 days is 0-06. Find the Seca that out of 5 such bulbs, at the most one bulb will fuse after 160 days of use. pre i ine are defective, find the probability that out ts produced by a machine are i ' a tae a vec random ( none will be defective, (i) one will be defective, and (ii) at 5S rivets chosen at ra least two will be defective. Scanned with CamScannerth 13. 14. @ 0) 1) @ (e) oO () (hy 0 () (a) (b) (©) @ © (a) (6) 0) @ (@ @ (6) (What is the chance that 5 of th ~ (i. What is the probability that al In four throws twice? A pair of dic probability of at least 5 suc ; ; y of getting a sum of 9 at least twice in 10 throws with two dice, is thrown 6 times. If getting a total of 9 is considered a success, \yhay is Find the probability aor A pair of dice is thrown 6 times, If getting a total of 7 is considered a success, Whay ist probability of at least 4 succes es? A pair of dice is thrown 6 times probability of at least five successes. Ina throw of 4 dice, find the probability that at least one die shows up 4. A coin is tossed 6 times. What is the probability of getting at least two heads ? A fair coin is tossed 6 times, What is the probabilities of obtaining at least four heads 9 . If getting a total of 7 is considered a success, find t A coin is tossed 5 times, What is the probabilities of obtaining at least 2 tails 2 A fair coin is tossed 7 times. Find the probability of obtait A coin is tossed 3 times. Find the probability of at least two heads. ing at least 5 tails. A die is thrown 5 times. If getting an odd number is success, find the probability o at least 4 successes. ‘getting A die is thrown 6 times, If getting an odd number is a success, what is the probability of least 5 successes ? A die is thrown 6 times. Getting a number greater than 4 is considered a success, Find te probability of at least two successes. An unbiased die is thrown 3 times. If getting a 2 or 5 is considered a success, find te probability of at least 2 successes. Five dice are thrown simultaneously. If the occurrence of 3, 4 or 5 in a single dies considered a success, find the probability of at least three successes, A coin is tossed 5 times. What is the probability that head appears an even number times ? (Take 0 as an even number), A coin is tossed 7 times. What is the probability that head appears an odd muntert times ? A coin is tossed 7 times. What is the probability that tail appears an odd number of times? A coin is tossed 5 times. What is the probability that head appears an odd number of tines” Past experience shows that 80 % o f the operations performed by a d 2 successtil he performs 4 operations i : rformed by a doctor are sucess bearecessnil ae ina day, what is the probability that at least three operations lines are busy 2 I the lines are busy Scanned with CamScannero w @) a) (a) (b) (©) W@ @) A die is thrown 6 times. If “getting an odd nu @ (iid) An unbiased coin is tossed six times. Find the pr @ (iy 1D) (in (ix) by one with four balls are drawn on AL Teast one is white ? get is + He tees 7 times. What isthe probability oF the probability of a man hitting a 4 his hitting at least twice the target he probability that a man hits a 4 what is the arget when he fites is +. if he fires 10 rounds, 5 probability of his hitting the target at least twice ? Ina ae race, a player has to cross 10 hurdles, The probability that he will clear each hurdle is &. What is the probability that the will knock down fewer than 2 hurdles ? A pce fires 6 bullets on a dacoit, The probability that the dacoit will be Killed by @ bullet is 0-6. What is the probability that the dacoit is still alive ? The probability that a bomb dropped from a plane will strike the target is + If six bombs are dropped, find the probability that (i exactly two will strike the target, (ii) at least two will strike the target. A student is given a true-false examination with 8 questions. If he gets 6 or more correct answers, he passes the examination. Given that the guesses at the answer to each question, compute the probability that he passes the examination. A pair of dice is thrown 7 times. If getting a total of 9 is considered a success, what is the probability of at most 6 successes ? Five dice are thrown simultaneously. If the occurrence of an even number is considered as a success, find the probability of at the most 3 successes. ‘A die is thrown 6 times and getting a multiple of 3 is a success. Find the probability of getting at most 5 successes. A coin is tossed 5 times. What is the probability of getting () at least 3 heads (ii) at most 2 heads A pair of dice is thrown 6 times. If getting a total of 8 is considered a success, what is the probability of (iat least 4 successes ? (ii) at most 5 successes ? imber” is a success, What is the probability of 5 successes ? (ii) at least 5 successes ? at most 5 successes ? obability of obtaining (ii) less than 3 heads (iv) more than 4 heads and less than 6 heads (vi) at least 4 heads (viii) 2 heads exactly 4 heads more than 4 heads more than 6 heads at most 4 heads at least 2 heads Scanned with CamScanner21, 22. 23. 24, (a) Ina box containing 100 bulbs, 10 sample of 5 bulbs (i) none is defective (H) A box contains 100 tickets each bearing one of the numbers from 110 109, jp nent from the box, find the probability that drawn successively with replac bear numbers divisible by 10. (©) In sampling a large number of parts manufactured by a machine, the mean ~ defectives ina sample of 20 is 2. Out of 1000 such samples, how many would be expe contain at least 3 defective parts. ‘ed, (d)_ Ina bombing action there is 50% chance that any bomb will strike the target, 7 Wo din are needed to destroy the target completely. How many bombs are required to be ros give a 99% chance or better of completely destroying the target ? Pe, An urn contains 25 balls of which 10 balls bear a mark ‘X’ and the remaining 15 bear A ball is drawn at random and it is replaced, If 6 balls are drawn in this way, fj that () all balls bear mark X (ii) not more than 2 balls bear mark Y (iii) number of balls with X mark and Y mark equal (iv) at least one ball with bear mark Y. (a) _ If “getting a 6” in a throw of an unbiased die is a success and the random vz the number of successes in five throws of the die, find P (2 OW ale 55g 256 128 or ea (ii) 0-2834 (4) 0-2301 Gi) 03412 ~~ Scanned with CamScanner13. 14, 16. 17, 18. + (a) (g) 31 Me (ey (6) 0-9681 171 1296 31 & 6 13 @ Te (a) > 16 1 () Bi 1 (a) z (@) 57905 «asy® 4547 © Fis (d) 00-0041 7 off @ot 3 OF (ii) © (6) oO (6) () ® w Gi) 15 () = 1024 ( 2) neo) 19) 27 20) * 20 2)’ 21 19)" 27 20) “30 $ (8) 5 \20 () 0-59049 =e 331441 Gal 1296 29 198 ae 64 a 2 (0) 0-02579 0-6242 (i) 0-246 13 16 Nia 2|~ © (g) () (©) (i) © (i) [3 (ii) © (2) x 23 20) * 200 ‘ { (Cf) 27847 x 23 (25)!0 7 6(19)* | (iii) 1-(2) (iv) -(Qy | 0, GH 0°32805 Gi) O.9g146 9 1-2(3) @ 648 57 Ba u 64 es al 2 5 (2) e224 1 @ = 2 a 1 z (e) 0-8192 1-024 x 10-7 is, 1S 256 0-4845 ; 37 0-345 N35 728 729 4 (p 2537065) G6)® (ii) 63 64 Scanned with CamScanner1y DISTRIBUTIONS I asl v7 Cc (i) 0-3438 i i" (ii) 01094 (iv) 0-0938 ow) wo? 32 0) 2 (viii) 4 37 Of +59049 (i) woe 0-00001 033 @ Os ) 864 y) 13561 ah 7502: 3125 3125 1 5 1 5 2 030(2) -25(3) 16 2 t 6 5 729 (90-3585, 0, 0°3773, 0 1887, 0-0596 3 30 (®) 600 “4 «(0300 (i) 750 (a 250 (i) 25 (it) 500 53 5 (0-514 by 2 7 : B (0) (6) 3035 (c) 0-91854 (d) 99°83 (iii) (wv) 550 4%, (a) 100 (0-432 + 0-568)" (6) 80 (0-7825 +0-2175)'° _(c) 200 (0-554 + 0-446)" {4 Poisson Distribution Poisson distribution was discovered by the French mathematician Simeon Denis Poisson. When saber of trials ‘n’ are not fixed, ie. n takes an infinite number of values and probability of success p for ‘sit is indefinitely small, ie. p > 0, the binomial distribution is hard to apply or we can say that it is ‘xaplicable. Under these situations, ie. when n> , p 0, the distribution applicable appropriately is distribution, Poisson distribution is also called distribution of rare events, as it is applicable for the ®t which are rare to occur, i.e. for the events whose chance of occurrence is very small, p — 0. Mision : A random variable X is said to follow a Poisson distribution if it assumes only non- negative ‘aes and its Probability mass function is given by PUG A)= P(X = x) = Jy TROND? otherwise sgt is known as the parameter of the distribution. We shall use the notation X ~ P (2), to denote 'SaPoisson variate with parameter 2. "SM: shuld be noted that Yrw-nee x=0 =O % aX Poisson distribution occurs when there are events which do not occur as outcomes of a definite lg OF trials (unlike that in binomial distribution) of an experiment but which occur at random points of rll tae wherein our interest les only in the number of OFcurEnces of the event, notin its non ees, * Scanned with CamScannerPoisson di ‘ollowing are some instances/examples where ‘ iden (A Number of deaths from a disease (not in the form of an epi or due to snake bite. (ii) Number of suicides reported in a particular city. (iit) The number of defective material in a packing manufactured by a good concery, (vi) The number of misprints in a news paper. (¥) The number of accidents in some kind of time say | minute. 8.3.1 Derivation of Poisson Distribution The Poisson distribution can be derived from () Asa limiting case of Binomial Distribution. (ii) Exponential expansion of e*. (@ Poisson Distribution as a limiting case of Binomial Distribution (P-T.U. 2005, 2007, 2009, 291), Poisson distribution can be derived as limiting case of the Binomial distribution under the fal Conditions : (Hn the number of trials is indefinitely large, (i) p, iano, the constant probability of success for each trial is indefinitely small, i.e, p> (iii) np = i (say) is finite, A . tos, Thus p= 7".q~1~ =, where is a positive real number, | By binomial distribution, the probability of x suecesses in a series of n independent trials is: n be:np)= ("Jorarrin =0,1,2, 40 dig We want the limiting form of (i) under the above conditions , i.e, rine OOM P)= tim AL A)" aynnx nove n= xn—»i\_ n, From (2) result (i), we have Lt =b(inp)= mt (ay "oe nih, “OG imp) Semem(] 1-4 Scanned with CamScanner1 DISTRIBUTIONS n(n D(M=2) vassal Ne vin : ( ie Lt beim p) = 5 ¥=0,1,2,3, 0000 a which is the probability function of the Poisson distribution with parameter os the Poisson distribution is a limiting case of the Binomial x! Ths, under some very general conditions, éxbuton, (a Poisson Distribution as Exponential Expansion of é By exponential expansion of e#, we have 2 3 #4, 2 3! xt Onmultiplying both sides with e* , we get 0 1 2 td nak Ah yet e Ce ne eo —_ me —The RAS. is the sum of the probabilities that the random With a total of probability equal to ane Hence, the terms on R.IVS. are the probabilities following different values of random variable Hence, the probability law for Poisson distribution 1s Poisson distribution ¢ orres TSP. 8.3.2 Properties of Poisson Distribution 1. It isa discrete probability distribution 2. nthe number of trials is indefinitely large i 3. pu the probability of suecess in a single tial is very small, p>. be. to ‘rare events’ and hence, also called distribution of rare events. hye ap= £170, 1,2,3,. Poisson distribution i apy. ‘The probability function for Poisson distribution is P (X JF, quae arl Pearson's coefficient = 7, F PD. is alwaysa positively skewed distribution in nature. h Parameter A is 10, Coefficient of Kurtosis of B.D. v Red aot > 0, always. | Karl Pearson’s coefficient = 7, > By P.D. is always Leptokurtic in nature 11. P.D. isa limiting case of B.D, as > %, p+ 0 Binomial distribution tends to Poisson's distribution tion 12. Mode of the Poisson Dis ‘The mode is that value of x for which P (x) is greater than or equal to P (x-I)and P(x +1), ie, | P(x 1) SPQ) 2 Pt Consic P(x-1) SPQ) my x m id sore or ——— s (x-D! or xrsm Similarly, on considering P (x) = P(x + 1), we have xzm-l A From (i) and (ii) modal value x satisfies the inequality m-lsxem ll Case — 1; If'm is an integer, (m ~ 1) is also an integer. Now —POCem em em™ (m=)! I ae a D mt mgd P (v= m)=P(e= m1) af inthis case ease till x= in his ease P(x) increase tilly = m — 1 and then (iv) holds and after that it begins to dect®* Hence, distribution is bimodal with modes m — land m, Scanned with CamScannerIBUTIONS, we , 7 oo cm isnot an integer, let “an integer) + (a fraction) value “a” (which is | J ates the vale ess than m but greater than m ate apP(at 1) ( 7 1= [m] = areatest integer less th ~ x 1) from (i) and (ii) 'an m is the mode. istribution is unimodal wit a se istrbuto i ‘odal with mode as greatest integer less than or equal to 7 et Reproductive Property of Independent Poisson Variates pendent Poisson variates is also a P, of indet ‘oisson variate. If X, (i= 1, 2p) are independent es with parameters A,, i= 1, jate with 7 Tespectively, then )) X,_ is also a Poisson vari im sa variat ig If X,~ PDA) and X, ~P.D.(4,), then X, +X, ~ P.D.(A, +4). _gpeereence Formula for the Probabil of Poisson Distribution (Fitting of Poisson Distrib fora Poisson distribution with parameter A, we have pi potl=——_: pxtl) A P(x) (x41) A 2 part = > pe “hich i the required recurrence formula. +1 P)= [pix+)] 29 = [4] (0), Ix=0 7)= [port Deas = [4] pil), ix=l 1) [p(x+ Dag = [4] PQ Ix=2 and so on, ‘Scanned with CamScannerSPECIRUM ENGINES May My ly Fitting a Poisson Distribution / . determine the following from thy, rss For fitting a Poisson distribution to the given set of da (i) Parameter of P.D, = A = Mean of the given distribution (ii) N= Total frequency = ¥ (iii) Find the expected frequency given by P(X=-N&P(X> 1) ILLUSTRATIVE EXAMPLES Example 1, Six coins are tossed 6,400 times. Using the Poisson distribution, find the appr. probability of getting six heads. : Sol. The probability of obtaining six heads in one throw of six coins (a single trial), is p - |! assuming that head and tail are equally probable. 16 2.= Mean = np = 6,400 x (3) = 100. Therefore by using Poisson probability law the required probability of getting 6 heads r times is givea’s Ax _ 67! Gooy" rt rt P(X=r) 0,1, 2) eras aon uv Example 2. In a book of 520 pages, 390 typographical error occur. Assuming Poisson law for the nc of errors per page, find the probability that a random sample of 5 pages will contain no error. required probability = P (X = 1) = = 100¢~ 100 Sol. The average number of typographical errors per page in the book is given by 4 = Mean = 22 =0"8 5: By using Poisson probability law, the probability of x errors per page is given by : oA 0.75, . Pixex= 24 8025) a x! ix=0,1,2... ‘The required probability that a random sample of 5 pages will contain no error is given by [P(X= 0] = (¢-P75)5 = @-375 Scanned with CamScanner-y DISTRIBUTIONS gio ie ng out the fallacy, inthe 2 aan Ys e follow; Z “te ne oisson drain 5 what tement eo ia Mle its ‘Standar jatic ” 3 One 5 and standard deviation ~ mene ear 5 and variance = (§.p, (ay m= and m=16 vis = 16, which is not possible a "given omen is wrong. - o parandom variable x hag ” 8 Poisson distribu; wt ean and standard deviation, “Stbution such that P (r= 2) =9 p(x = 4) +90 P (x= 6), ve PQ)= we have ot ae aw . 3 + = 4237243! o M+30-4=0 = @-1I)@+4=0 * 2= 2 Bl del «mean =A=1, $.D.= y2=y1 =1 tuumple 5. Suppose that X has Poisson distribution. If P(X = 2) = 2 P (X= 1), then find P(X = 0). (P.T.U. 2017) SLla X~P.D. (a) WA yx “ P(X=x= 24 ke Singe P(X = 2) = z P(X=1) wee RB | 38L4a=0 = 264-4 _4 =0 @ 420,475 Scanned with CamScanner4 we have But 4 #0. therefore on taking ans: ae =e 3 =0.2636 P(X=0) each day to hospital is found to have Poisson dist ere will be no emergency admission, PTL. ry Example 6, The number of emergeney admission 626 St uty sah swcan 4. Find the probability that on a particular day Sol. Given, Mean = 4 =4 Let X be the random variable ret 4k presenting number of emergencies on @ particular day. By P.D,, P(X=x the required probability = P (X = 0) 4.40 + = 6-4 =0-0183 12 Example 7. A car hire firm has two cars which it hires out day by day. The number of demands for a care: zach day is distributed as a Poisson distribution with mean 1.5. Calculate the number of days in a yeara which (i) neither car is on demand, (ii) A car demand is refused. (P.T.U. 2019 Sol. Given, mean = 4 = 1-5 Let X be the random variable representing the number of cars in demand out of a maximum oft + x= 0,1,2 Here N = Total frequency = | year = 365 days ‘Therefore, expected number of days in a year, x cars in on demand is (X= x)=N¥P(X=x) eS ae k (i) The expected number of days when no car is on demand is ais 0 =/(K=0)=365 x £365 , )) io 365 * 0.2231 = 81-44~81 days = 365% Scanned with CamScannerQe § & 2 2 g 2 a z = 3 S 2 2 py a O geDNe PIXE “P(X =0)- P(X =1 e 8 4.5)0 1 2365 | 1-25" 365 [1-0-2931 9-3346] ~ 161-43 = 161 days je8 Five COIS ATE £08SCU 3200 times, wy a rat is bil 'S the probability of getting 5 heads two times ? (P.T.U. 2016) f ility of obtaining five heads j _ probability of 8 five heads in on 7 ae : ¢ throw of five coins ( (1) ‘a single trial) is assuming that head and tail ar p nd ail are equally probable, 5 _— I mean =A =n p= 3200 x (3) 3200. e109 therefore by Poisson distribution, the probability of getting sineads “times is given by 2H _ "Aggy Lr [r sida On 203 eae P(X=r) . eye - 100 (100)? the required probability = P (X = 2) = = 000) 100 fumple 9. Find the probability that at the most 5 defective fuses will be found in a box of 200 fuses, if agerience shows that 2 percent of such fuses are defective. St Here n= 200, oe m=np=200 x= = 100 I o2 4 442.47 -=.4 aon 6 We wish to find the probability of having at most five defective fuses which is same as the probability “Sing, 1, 2, 3, 4 or 5 defective fuses. Required probability = P (0) + P (1) +P 2) + P (3) +P (4) + P(S) 2 2 = 44 5 4.4 -4,4 se Te RB 32, 32, 128) _ gigs x 43 = 795 -et[ieaese set 5 7 8 Tg Scanned with CamScanner252 Ma’ S GINEE| THEN Us, E ate 10, Assume that the probability that a bomb dropped from an aeroplane wil strigg ~~ Seg target is =. If 6 bombs are dropped, find the probability that i (i) exactly 2 will strike the target (ii) at least 2 will strike the target Use 124, 3p) Sol. Here p=+. n=6 m=np=6X4=12 np=6X= (Probability that exactly 2 will strike the target 2 ek (1:2)" xe an Mm xem =pa- C2 xe s P(xy= xe 2 E (x) ae - ieee = -2169 (approximately) (i) Probability that at least 2 will strike 1-[P@)+P()] 0 G2)" -12 Ty ete TL e =1-e!7 [1 + 1-2] = 1-0-3012) (2:2) = 1 - 0-6626 = 0-3374. Example 11. The probability that a man aged 50 years will die with in a year is 0.01125, what is t probability that out of 12 such men at least 11 will reach their 51st birthday. Sol. Here n=12, p=0.01125 '. Mean, m= np = 12 x 0.01125 = 0.135 * Now, P(X =x) = Te =, 1, sus 12 be the probability that a man aged 50 years die with x ayear. Now P(at least 11 men reach their 51st Birthday) = P(at most one man dies with in a year) m® e mi e”™ = P(0) + P(1)= feo = 6 PS (0,135) 5 = oF 0,135] = (0.8731)(1.135) = 0995 Example 12. An insurance company insures 4000 people against loss of both eyes in a car accident ‘on previous data, the rates were computed on the assumption that on the average 10 persons in i Me will have car accident each year that result in this type of injury. What is the probability that more U1 insured will collect on their policy in a given year. (PT. Scanned with CamScannerye MIMber of O09 Will have have car accident pea —l0 19-0001 po the random variable Fepres 100000 10000 val that result In the eyes injury 1900 oul of a total of 4000 insured will have iy, we have wh» “SIMO the Haber 7 pe doe pxen Pro 2 00001 (0-0001)" Lk ihe required probability = p (more Pin, att ne ‘stn 3 of injured will collect on their policy) ' 4000 i 4000 DP Kan = SLM o-c00n" : rea i Ir u fuample 13. A car hire firm has two cars which it hires out day o day. ‘The number of demands for a car peach day distributed as a Poissor a n distribution with mean 1.5, Calculate the proportion of days, {yon which there is no demand (i on which demand is refused (e"' = 0.2231) (P.1.U. 2008) sol Let ‘x* denotes the demand of car on each day. As itis given that demand is distributed as Poisson datibution with mean ‘m= 1.5, 5 (1,5)° [i (i) P(When demand is refused) = P(X > 2) = | - P(X $ 2) = 1 — [P(0) + P(1) + P(2)} “15 a] () P(when there is no demand) = P(X = 0) = 1S <9.2931 e595)! ie a = i-[e"s seas +ea.129) | = 1 =e S[L + 1.5 + 1.125] = 10.2231 (3.625) = 0.1913. | Sample 14, 1f the probability that an individual suffers a bad reaction from a certain injection is 0-001. ‘the probability that out of 2000 individuals. (exactly 3 individuals will suffer a bad reaction le (® none will suffer a bad reaction eau 200 (id) more th individual will suffer 4 an one individual (P.T.U. 2011) {) more than two individual will suffer Scanned with CamScannerSPECTRUM ENGINEERING M4 L Here p= 0.001, n= 2000 A= mp 2000 0-001 = 2 r ely c | | ()_P(exaetly 3 individual will suffer a bad reaction) Pin & O18 = ra--4 2 _ ow 0.135 (4 P (none will suffer) ~ P O78" (id) P (more than one) = P (2) + PB) + PA) + =... # P (2000) 1-[P@)+Pay=1 sie 1-30 (0-135) = 0-595 7 2! 22 (%) P (more than two) = 1 — [P (0) + P (1) +P. Q)] = I-] 7+ eel eL = 1-4 f1+2+2) =1-5 0-138) =0-325 2 Example 15. A product is 0-5 % defective and is packed in cartoons of 100. What percentage contains» more than 3 defective ? Sol. p= The probability that a product is defective = 0.5% 0-5 = £5 < 9-005 ?* j00 n= 100 4.= np~ 100 (0-005) = 0-5 Let X denotes the number of defective products (0-5) & 9S I P (not more than 3 defective) = P(X = 3)= P (0) + P(L) +P.) 4 B(3) 0-5) 95 5 eos OSE Cosh oO Sa A Oye G5 0-5)" oS lo 0 B B “S +O 1140-5422 = 0-6065 [1 + 0- 3+ 0-125 + 0-021] = (0-6065) (1-640) = 0-9983 (approx) Hence required percentage = 0-983 « 100 = 99-83%, Scanned with CamScanner25: bution n wi Hh unit mean, mean deviation about mean is (2/e) times (P.T.U. 2015) _ xe) ” —;: ean deviation about mean i ea gux7 XD EX= t= DivX =a) = ¢ x=0 We have. nL @t)-1_ (DE tN Gene :. Mean deviation about mean “tah setae) (a-a}i-a} 2 xls 7 X standard deviation, ot e Eample 17, For a Poisson variate with mean ‘m’ show E (X?) =m E (X +1). Gol LetX be a Poisson variate with mean ‘m’, ie. E (X)=m. Since, we know that variance = Mean for P.D. ‘. Variance = m > E(X2)-(E(X))2 =m 2 E(X?)-n? =m > E(X?) =m? +m =m (m+ I) wal) Now, mE (X +1) =m (E(X) +1) =m(n+l) wii) From (i) and (ii), we get E(X?) =mE(X+D). - ample 18, The Probability of getting no misprints in a page of book is 0.223. wha isthe probability that y St contains more than 2 misprints ? 7 “tps the probability of getting number of misprint in P=1~0.223 = 0.777 a page of book. m= mean no. of errors = np = 140.777) = 0.777 Scanned with CamScanner‘SPECTRUM ENGIN} he probability of getting ‘r’ error on a page r! required probability = P (a page contains more than 2 misprints) =P(X>2) P(X s2) {P(X =0) + P(X=1) + P(X=2)} 0777 09, a 2 yo Example 19. Fit Poisson distribution to the following and calculate theoretical frequencies Sol. Death : 0 1 2 3 4] Frequency : 122 60 15 2 i | (P.T.U, 2007, Let the random variable X follows Poisson’s distribution with parameter m. ‘m= mean of distributio Lf, 200 _ 60+30+6+4 200 05 By, Poisson distribution, the probability of having ‘r’ deaths is m 05 5)" P(X=7)= 05" r! rt expected frequency of| sv ‘deaths is S(K=1)=N xP (X= =Nx ceo rl OS r =200 x £05)" r! on taking r= 0, 1, 2,3 and 4, we get r=0; f(x=0)=200 x ost =122 =1; fee=)=200% S703" Scanned with CamScanner_ fr=3)= 200 x £05)? 7 95 9 90 eas fer=) = 200 x Os" oo gird fting of Poisson distribution ig 9 1 s F 7 122 61 a 2 4 gets Fite Poisson Distribution tothe given daw 2 0 w 0 1 109 65 x 5 e f . 3 1 (P.T.U. 2005) la Here yen of distribution is given by m= ZF _ M09) + 0X65) + QV+H)Q)+HD _ 122 a 109+ 654224341 ” 200 7 _ Required Poisson Distribution is given by 0.61 3 =0,1,2,3,4 = 200) (e791) .6D* _ (200) (05435) (0.6 _ 08.7) (61 L Le (108.7) (0.61)! _ »*=0,1,2,3,4 0 Sow p(0) = GEDOSY 1987 ~ 109, P= = 66.3 ~ 66 [2 [a 7 2 3 72) = 108-7) 0.61)" _ 5999, P(g) = 1087x061 4g 2 LB 4 4) = 1087x060" 97) L4 ‘equired fitting of Poisson distribution is x 0 1 2 [3 4 7 709 66 2 | 4 2 hay A 1 21. Ina certain factory turning out razor blades, there is a small chance —-— for any blade to be & .. tei ti: wt The blades are supplied in packets of 10. Use the Poisson distribution to calculate the number of packets containing no defective, one defestive and two defective blades i oan = "ely ina consignment of 10,000 packets given that «°"” = 0:9802. (.T.U. 2008) Scanned with CamScannerXt, " 258 Sti, N= 10000 Sol. RUM ENGINEERING M, Here p= sig: nt! ' \-5 002 m= np~ (0) (sin "5 0-02)" 002 ~ PQ) The expected number of packets containing no d (0-02)° 002 =N X P(x =0) = 10000 x —~———e = 10000 x ix (0-9802) = 9802 ‘The expected number of packets containing one defective 1 0-02)' 002 =N xX P(x=1)= 10000 x Coe = 10000 x (0-02) x (0-9802) = The expected number of packets contain (0 196.04 ing two defectives 2 =N x P(r=2)= 10000 x co = 10000 x (0.0002) x (0-9802) = 1.9604 EXERCISE 8 (5) Is the following statement correct ? “The mean and variance of the Poisson distribution are 3 and 4” ? (a) Ifa random variable has a Poisson distribution such that P(1) = P(2), find (ip PA) (®) X is a Poisson variable and it is found that the probability that X = 2 is two-thirds oft probability that X = |. Find the probability that X = 0 and the probability that X = 3. Wi the probability that X exceeds 3 ? (A mean of the distribution If a Poisson distribution has probability of 2 successes equal to probabiliy “ 3 successes, find the probability of 4 successes. ma Poisson distribution, the probability of O successes is 10%. Find the mean ofthe isribsi® If m is the mean of a Poisson distribution, any ol find the probability that the variable takes values 0, | or 2. Scanned with CamScannerace of the Poisson distribution i 9 sce relation of the distribution 1,2, 3,4 and $ from the 00-1353). 2. find the distribution for x that the chance of aad aan indivig vidual coalminer being killed in at the probability of an Y of an in coalmi dividual coalminer being killed in a mine accident during @ 00 & I Use Poisson's distribution to ¢ year 8 1 2 2400 alculate the probability that a mine employing 2 “nines there will be least one fatal accident in a year, oa book of 5: suppose 3 nea eed throughout ones Contains 43 typographical errors. If these errors are randomly 5 . What is the probability that 10 pages, selected at random. will be fom errors (Use «7 = 4795) rhe probability that a man aged 35 years will die before reaching the age of 40 years may be taken 0.018. Out of a group of 400 men, now aged 35 years, what isthe approximate probability that + ea will die within the next 5 years ? ‘Use ¢'2 = 000747) 4 pair of dice is thrown 200 times. If getting a sum of 9 is considered a success. find the mean and Ee variance of the number of successes. here are $0 telephone lines in an exchange. The probability that any one of them will be busy is 1. What is the probability that all the lines are busy ? ‘q insurance company has discovered that only about 0-1 percent of the population is involved in 2 certain type of accident each year. If its 10000 policy holders were randomly selected from the population. what is the probability that not more than 5 of its clients are involved in such an accident next year ? (c) A manufacture of screws known that 4% of his product is defective. If he sells the screws in boxes of 100 and guarantees that not more than 5 screws will be defective, what is the approximate probability that a box will fail to meet the guaranteed quality ? of the output in a factory manufacturing certain bolt is defi that (i) None is defective (i/) At most 3 defective (6) Assuming that on average 2% ina package of 200. What is the probability bolts may be found. box contains 200 tickets each bearing successively with replacement from the ‘tumbers divisible by 20. ; ; a “Ata busy traffic intersection, the probability p of an individual car having an accident is very small, say p = 0.0001. However during a certain part of the day, a a an of oa say, 1000, Pass through the intersection. Under these conditions, what is the probability of two or more ‘cidents occurring during that period ? one of the numbers from 1 t0 200, 20 tickets are drawn ox, Find the probability that at most 4 tickets bear Scanned with CamScannerthat an item produced by a pa ne are selected at compare the answers. ‘A cars hire firm has three cars which it hires out by the day. The number of demang, car on cach day is distributed as a Poisson distribution with mean equal to 2. Cafeyns™* proportion of days on which none of the cars is used, and the proportion of days oq," some demand is refused. 2) 19. A book has 200 pages and 200 contains @ ints distributed at random. What is the probability tha ae (exactly two misprints ? (ii) fewer than two misprints? (e!= pgp, 20. (a) If 5% of the electric bulbs manufactured by a company are defective, use py... distribution to find the probability that in a sample of 100 bulbs : (i) none is defective (ii) 5 bulbs will be defective. Given: 5 = g4 (8) Ifthe probability of a bad reaction from a certain injection is 0-001, determine the chang that out of 2,000 individuals more than two will get a bad reaction. 21. 10% of the tools produced in a certain factory turn out to be defective. Find the probability thay a sample of 10 tools chosen at random . (i) exactly two (i) more than two will be defective. (Given 22, A telephone exchange receives on an average 4 calls per minute. Find the probability of (i 2 or less calls per minute (ii) upto 4 calls per minute (iif) more than 4 calls per minute. (Given : e°*= 0.0183) 23. A manufacturer of bulbs knows that on an average 5% of his production is defective. He s bulbs is boxes of 100 pieces and guarantees that not more than 4 bulbs will be defective in ab What is the probability that a box will meet the guarantee ? (Given : e-* = 0.0061 24. (a) A certain screw making machine produces on average of 2 defective screws out of 100, packs them in boxes of $00. Find the probability that a box contains 15 defective screws (6) A manufacturer knows that the condensers he makes contain on the average 1% defect He packs them in boxes of 100. What is the probability that a box picked at random W! contain 3 or more faulty condensers ? (©) A care-hire firm has a two cars which it hires out day by day. The number of demands / car on each day is distributed as a Poisson distribution with mean 1-5. Calcul? Proportion of days (/) on which there is no demand, (ii) on which demand is refused- Scanned with CamScannera i - DISTRIBUTIONS we 261 wy The incidence of occupational ¢ ea chiance of suffering from What is a a an in from it? Pability that in a group of 7, five or more will suffer 500 articles were selected at randoy @ found tobe defective. How many A of # batch containing 10,000 articles, and 30 were the whole batch ? Sctive articles would you reasonably expect to have in 5 (P-7.U. 2016) ‘A systematic sample of 100 ' © peeved fequency distribution 3 ken fom a eoncise Oxford Dictionary and the foreign words per pa Telgn words per page was found to be the following. ‘ ig e No.0 2 o \ 203 4 5 6 y 5 Frequency £48 27 2 07 4 1 1 Fita Poisson distribution (6) Fita Poisson distribution to the following : ° 1 2 3 4 ic 46 38 22 9 1 (0. Fita Poisson distribution to the following data given the number of yeast cells per square for 400 squares : No. of cells per sq. : 0 1 2 3 4 5 6 7 8 9 10 No, of squares : 103 143 98 «42 8 4 2 0 0 0 0 (@ Data was collected over a period of 10 years, showing number of deaths from horse kicks in each of the 200 army corps. The distribution of deaths was as follows : No. of deaths : 0 1 2 3 4° Total Frequency : 109 650 (223 1 200 Fita Poisson distribution to the data and calculate the theoretical frequencies, (e) The following mistakes for page were observed in book No. of mistakes : 0 1 2 3 Aierotal Frequency : 21 9019S 0 325 Fita P.D. to the data and find the expected frequencies. (P.T.U. 2015) ANSWERS | Wrong (9 2 (i (b) P(0)=0-2636, P(3)=0-1041, P(<3)=0-1506 #25 m 026, 2.3026 Sete lemeTy, Scanned with CamScanner804, 0.0902, 0.0361 8022 9, 0.08 ML. 0.010362 12, 22-22; 22.22 Ws hy 0-0183, 0-4331 as. (h) 0 16. 170-0047 18. (a) 0-4059 ; 0-3758 19. (i) 0.04598 (ii) + 0-1839 20. (a) (i) 0-007 i) 0-1822 (6) 0°32 21. (1) 0-18394 (ii) 0-0803 22. (i) 0-2382 (ii) 0-6289 (iii) 03711 23. 0438 24. (a) 0-035 (6) 0-08 © (09-2231 Gi) 0-193 500 ,- 006 r 0-06) (a) 0-0008 (@ 10000 >> iemees (0200)8 r=0 L 25. (a) 38, 37-6, 182, 6,1-5,03, 005 (6) 44,43,21,7,1 (€) 109,142, 92, 40, 13,3, 1,0,0,01 108-7 x (0-61)? Lr ribution (d) + 109, 66, 20,4,1 (e) 209, 92, 20,3, 0 8.4. Normal Di (P.T.U, 2005, 2007 Definitior random variable Xs is the one of the most important continuous Probability distribution. A said to have a normal distribution with Parameters y (called ‘mean’) and o2 probability density function is given by the law -_! _Afx-n) eat r| (2) a? i202 WY 2a". wcrc = 00

0, (called ‘variance’) ifs or f(rsu,o)= When a random variable is normally distributed with mean j and standard deviation o, its ci to write that X is distributed as Nu, 6” ) and is expressed by X~N (u,07), Scanned with CamScannerel Xeon. then Z= SoA i fan 7 ndard Normal y; 7 ‘ariate with E(Z) = 0. and Var(Z) tabi’ density funetion of andar wet normal va ite Z is given by conesponding distribution fumetion, do . denoted by a(2) is 2) is given by: atte o-Ps -_l f Jan te De fet a, 2n ties of Normal Distributio: Propel nm (P.T.U. 2005, 2008, 2009, 2010, 2018) . = al Probability Curve are as follows : 1, isa continuous probability distribution with probability function 1 : eee se hie Characteristics ofthe Normal Distribution and Noam f@) S-@3)=1 — P(|Z| $3) = 0-0027. This property of the normal distribution forms the basis of entire large sample theory i.e. almost 100% of area under normal curve is covered upto a distance of 3 S.D. from central value. Many of the distributions of sample statistics (e.g. the distributions of sample mean, sample Variance, etc) tend to normality for large samples and as such they can best be studied with the help of the normal curves. The entire theory of small sample tests, viz. f, F, Z test, etc. is based on the fundamental ‘sumption that the parent populations from which the samples have been drawn follows normal istribution, (ny a . . ” Noma distribution finds large applications in statistical duality control in industry for setting limits, Scanned with CamScanner